diff --git a/dgp/utils/render_3d_to_2d.py b/dgp/utils/render_3d_to_2d.py
new file mode 100644
index 00000000..a8dfc406
--- /dev/null
+++ b/dgp/utils/render_3d_to_2d.py
@@ -0,0 +1,420 @@
+# Copyright 2023 Toyota Motor Corporation.  All rights reserved.
+import json
+import logging
+import math
+import os
+import time
+from collections import defaultdict
+from multiprocessing import Pool
+from typing import Optional, Tuple
+
+import numpy as np
+from matplotlib import pyplot as plt
+
+from dgp.annotations import ANNOTATION_TYPE_TO_ANNOTATION_GROUP
+from dgp.constants import ALL_ANNOTATION_TYPES, DATASET_SPLIT_NAME_TO_KEY
+from dgp.datasets.synchronized_dataset import (
+    SynchronizedScene,
+    SynchronizedSceneDataset,
+)
+from dgp.proto.dataset_pb2 import SceneDataset
+from dgp.utils.camera import Camera
+from dgp.utils.structures.bounding_box_3d import BoundingBox3D
+
+ANNOTATIONS_3D = 'bounding_box_3d'
+ANNOTATIONS_2D = 'bounding_box_2d'
+# The list of cameras' name
+FRONT_CAMERA = ["CAMERA_21"]
+# The list of Lidars' name
+LIDAR = ["LIDAR"]
+MAX_NUM_ITEMS = 2000
+LOGGING_SPAN = 200
+MIN_DIST = -20
+MAX_DIST = 100
+DIST_BIN = 10
+
+# Define the class names from bounding_box_2d to bounding_box_3d if the class names are different.
+ONTOLOGY_NAME_MAPPER_2D_to_3D = {
+    'Pedestrian': 'Person',
+    'Car': 'Car',
+}
+
+
+def render_bounding_box_3d_to_2d(bbox_3d: BoundingBox3D, camera: Camera) -> np.ndarray:
+    """Render the bounding box from 3d to 2d to get the centroid.
+    Parameters
+    ----------
+    bbox_3d: BoundingBox3D
+        3D bounding box (cuboid) that is centered at `pose` with extent `sizes.
+    camera: dgp.utils.camera.Camera
+        Camera used to render the bounding box.
+    Returns
+    ----------
+    centroid: np.ndarray
+        Centroid in image plane.
+    Raises
+    ------
+    TypeError
+        Raised if camera is not an instance of Camera.
+    """
+    if not isinstance(camera, Camera):
+        raise TypeError('`camera` should be of type Camera')
+    points2d = camera.project(bbox_3d.corners)
+    corners = points2d.T
+    if (bbox_3d.corners[:, 2] <= 0).any():
+        return None
+    # Get the centroid in image plane.
+    return camera.project(np.vstack([bbox_3d.pose.tvec, bbox_3d.pose.tvec, bbox_3d.pose.tvec])).astype(np.int32)
+
+
+def render_bounding_boxes_3d_of_lidars(
+    dataset: SynchronizedSceneDataset, camera_datum_names: Optional[list[str]], lidar_datum_names: Optional[list[str]],
+    max_num_items: Optional[int]
+) -> defaultdict[defaultdict[list]]:
+    """Load and project 3D bounding boxes to 2d image with given dataset, camera_datum_name and lidar_datum_names.
+    Parameters
+    ----------
+    dataset: SynchronizedSceneDataset
+        A DGP dataset.
+    camera_datum_names: Optional[list[str]]
+        List of camera names.
+        If None, use all the cameras available in the DGP dataset.
+    lidar_datum_names: Optional[list[str]]
+        List of lidar names.
+        If None, use all the lidars available in the DGP dataset.
+    max_num_items: Optional[int]
+        If not None, then show only up to this number of items. This is useful for debugging a large dataset.
+        Default: None.
+    Returns
+    -------
+    bbox_2d_from_3d: defaultdict[defaultdict[list]]
+        a dictionary with key is the camera name, value is a dictionary whose key is class_name of bounding_box_3d,
+        value is list of (bbox_3d, centroid_2d)
+    """
+    ontology = dataset.dataset_metadata.ontology_table.get(ANNOTATIONS_3D, None)
+    if ontology is None:
+        id_to_name = dict()
+    elif ontology is not None:
+        id_to_name = ontology.contiguous_id_to_name
+    else:
+        id_to_name = ontology.contiguous_id_to_name
+
+    if camera_datum_names is None:
+        camera_datum_names = sorted(dataset.list_datum_names_available_in_all_scenes(datum_type='image'))
+    if lidar_datum_names is None:
+        lidar_datum_names = sorted(dataset.list_datum_names_available_in_all_scenes(datum_type='point_cloud'))
+
+    bbox_2d_from_3d = defaultdict(lambda: defaultdict(list))
+
+    st = time.time()
+    for idx, datums in enumerate(dataset):
+        # no temporal context
+        datums = datums[0]
+        if idx == max_num_items:
+            break
+        if idx % LOGGING_SPAN == 0:
+            logging.info(f"2D:Frame {idx + 1} of {len(dataset)} in {time.time() - st:.2f}s.")
+
+        datums = {datum['datum_name']: datum for datum in datums}
+        lidar_datums = [datums[lidar_datum_name] for lidar_datum_name in lidar_datum_names]
+        camera_datums = [(camera_datum_name, datums[camera_datum_name]) for camera_datum_name in camera_datum_names]
+
+        for camera_name, camera_datum in camera_datums:
+            rgb = np.array(camera_datum['rgb']).copy()
+            # Render 3D bboxes
+            if ANNOTATIONS_3D in camera_datum:
+                for i, bbox_3d in enumerate(camera_datum[ANNOTATIONS_3D]):
+                    class_name = id_to_name[bbox_3d.class_id]
+                    center_2d = render_bounding_box_3d_to_2d(bbox_3d, Camera(K=camera_datum['intrinsics']))
+                    bbox_2d_from_3d[camera_name][class_name].append((bbox_3d, center_2d))
+    return bbox_2d_from_3d
+
+
+def render_bounding_boxes_2d_of_cameras(
+    dataset: SynchronizedSceneDataset, camera_datum_names: Optional[list[str]], max_num_items: Optional[int]
+) -> defaultdict[defaultdict[list]]:
+    """Load 2d bounding boxes with given dataset, camera_datum_name.
+    Parameters
+    ----------
+    dataset: SynchronizedSceneDataset
+        A DGP dataset.
+    camera_datum_names: Optional[list[str]]
+        List of camera names.
+        If None, use all the cameras available in the DGP dataset.
+    max_num_items: Optional[int]
+        If not None, then show only up to this number of items. This is useful for debugging a large dataset.
+        Default: None.
+    Returns
+    -------
+    bboxes_2d: defaultdict[defaultdict[list]]
+        a dictionary with key is the camera name, value is a dictionary whose key is class_name of bounding_box_2d,
+        value is list of boxes as (N, 4) np.ndarray in format ([left, top, width, height])
+    """
+    bboxes_2d = defaultdict(lambda: defaultdict(list))
+    if len(dataset):
+        if max_num_items is not None:
+            if max_num_items > len(dataset):
+                logging.info(
+                    "`max_num_items` is reduced to the dataset size, from {:d} to {:d}".format(
+                        max_num_items, len(dataset)
+                    )
+                )
+                max_num_items = len(dataset)
+
+        ontology_table = dataset.dataset_metadata.ontology_table
+
+        if ANNOTATIONS_2D in ontology_table:
+            ontology = ontology_table[ANNOTATIONS_2D]
+
+        if camera_datum_names is None:
+            camera_datum_names = sorted(dataset.list_datum_names_available_in_all_scenes(datum_type='image'))
+
+        st = time.time()
+        for idx, datums in enumerate(dataset):
+            # no temporal context
+            datums = datums[0]
+            if idx == max_num_items:
+                break
+            if idx % LOGGING_SPAN == 0:
+                logging.info(f"2D:Frame {idx + 1} of {len(dataset)} in {time.time() - st:.2f}s.")
+            datums = {datum['datum_name']: datum for datum in datums}
+            camera_datums = [(camera_datum_name, datums[camera_datum_name]) for camera_datum_name in camera_datum_names]
+            # Visualize bounding box 2d
+            if ANNOTATIONS_2D in dataset.requested_annotations:
+                for camera_datum_name, camera_datum in camera_datums:
+                    for bbox in camera_datum[ANNOTATIONS_2D]:
+                        bboxes_2d[camera_datum_name][ontology.contiguous_id_to_name[bbox.class_id]].append(bbox.ltwh)
+    return bboxes_2d
+
+
+def associate_lidar_and_camera_2d_bboxes(
+    bboxes_from_camera: list[np.ndarray], bboxes_from_lidar: list[Tuple[np.ndarray, np.ndarray]]
+) -> list[Tuple]:
+    """Associate 3d bounding boxes and 2d bounding boxes to the same object by checking
+       whether the projected centroid of 3d bounding box is inside the 2d bounding box or not.
+    Parameters
+    ----------
+    bboxes_from_camera: list[np.ndarray]
+        A list of 2d bounding boxes.
+    bboxes_from_lidar: list[Tuple[np.ndarray, np.ndarray]]
+        A list of Tuple (centroid in 2d image, 3d bounding box).
+    Returns
+    -------
+    associated: list[Tuple[bounding_box_2d, bounding_box_3d, centroid_2d]]
+        a dictionary with key is the camera name, value is a dictionary whose key is class_name of bounding_box_2d,
+        value is list of boxes as (N, 4) np.ndarray in format ([left, top, width, height])
+    """
+    associated = []
+    if bboxes_from_camera and bboxes_from_lidar:
+        for bbox_camera in bboxes_from_camera:
+            l, t, w, h = bbox_camera
+            for bbox_lidar, bbox_centroid_2d in bboxes_from_lidar:
+                if bbox_centroid_2d is None:
+                    continue
+                bbox_centroid_x, bbox_centroid_y = bbox_centroid_2d[0]
+                if bbox_centroid_x >= l and bbox_centroid_x < l + w and bbox_centroid_y >= t and bbox_centroid_y < t + h:
+                    associated.append((bbox_camera, bbox_lidar, bbox_centroid_2d[0]))
+                    break
+    return associated
+
+
+def associate_3d_and_2d_annotations(
+    dataset: SynchronizedSceneDataset, camera_datum_names: Optional[list[str]], lidar_datum_names: Optional[list[str]],
+    max_num_items: Optional[int]
+) -> defaultdict[defaultdict[list[Tuple]]]:
+    """Associate 3d bounding boxes and 2d bounding boxes to the same object with given dataset.
+    Parameters
+    ----------
+    dataset: SynchronizedSceneDataset
+        A DGP dataset.
+    camera_datum_names: Optional[list[str]]
+        List of camera names.
+        If None, use all the cameras available in the DGP dataset.
+    lidar_datum_names: Optional[list[str]]
+        List of lidar names.
+        If None, use all the lidars available in the DGP dataset.
+    max_num_items: Optional[int]
+        If not None, then show only up to this number of items. This is useful for debugging a large dataset.
+        Default: None.
+    Returns
+    -------
+    associated_bboxes: defaultdict[defaultdict[list[Tuple]]]
+        a dictionary with key is the camera name, value is a dictionary whose key is class_name of bounding_box_2d,
+        value is list of Tuple [bounding_box_2d, bounding_box_3d, centroid_2d]
+    """
+    bboxes_2d_from_lidars = render_bounding_boxes_3d_of_lidars(
+        dataset, camera_datum_names, lidar_datum_names, max_num_items
+    )
+    bboxes_2d_from_cameras = render_bounding_boxes_2d_of_cameras(dataset, camera_datum_names, max_num_items)
+    associated_bboxes = defaultdict(lambda: defaultdict(list))
+    for camera_name in camera_datum_names:
+        bboxes_2d_from_lidar = bboxes_2d_from_lidars[camera_name]
+        bboxes_2d_from_camera = bboxes_2d_from_cameras[camera_name]
+        for name_2d, name_3d in ONTOLOGY_NAME_MAPPER_2D_to_3D.items():
+            logging.info("{}: Associate {} to {}".format(camera_name, name_2d, name_3d))
+            bboxes_from_lidar = None
+            if name_3d in bboxes_2d_from_lidar:
+                bboxes_from_lidar = bboxes_2d_from_lidar[name_3d]
+            bboxes_from_camera = None
+            if name_2d in bboxes_2d_from_camera:
+                bboxes_from_camera = bboxes_2d_from_camera[name_2d]
+            associated_bboxes[camera_name][name_2d] = associate_lidar_and_camera_2d_bboxes(
+                bboxes_from_camera, bboxes_from_lidar
+            )
+    return associated_bboxes
+
+
+def associate_3d_and_2d_annotations_scene(
+    scene_json: str,
+    camera_datum_names: Optional[list[str]],
+    lidar_datum_names: Optional[list[str]],
+    max_num_items: Optional[int] = MAX_NUM_ITEMS
+) -> defaultdict[defaultdict[list[Tuple]]]:
+    """Associate 3d bounding boxes and 2d bounding boxes to the same object with given scene.
+    Parameters
+    ----------
+    scene_json: str
+        Full path to the scene json.
+    camera_datum_names: Optional[list[str]]
+        List of camera names.
+        If None, use all the cameras available in the DGP dataset.
+    lidar_datum_names: Optional[list[str]]
+        List of lidar names.
+        If None, use all the lidars available in the DGP dataset.
+    max_num_items: Optional[int]
+        If not None, then show only up to this number of items. This is useful for debugging a large dataset.
+        Default: None.
+    Returns
+    -------
+    associated_bboxes: defaultdict[defaultdict[list[Tuple]]]
+        a dictionary with key is the camera name, value is a dictionary whose key is class_name of bounding_box_2d,
+        value is list of Tuple [bounding_box_2d, bounding_box_3d, centroid_2d]
+    """
+    datum_names = camera_datum_names + lidar_datum_names
+    dataset = SynchronizedScene(
+        scene_json,
+        datum_names=datum_names,
+        requested_annotations=[ANNOTATIONS_2D, ANNOTATIONS_3D],
+        only_annotated_datums=True
+    )
+    return associate_3d_and_2d_annotations(dataset, camera_datum_names, lidar_datum_names, max_num_items)
+
+
+def associate_3d_and_2d_annotations_dataset(
+    scenes_dataset_json: str,
+    camera_datum_names: Optional[list[str]],
+    lidar_datum_names: Optional[list[str]],
+    max_num_items: Optional[int] = MAX_NUM_ITEMS
+) -> defaultdict[defaultdict[list[Tuple]]]:
+    """Associate 3d bounding boxes and 2d bounding boxes to the same object with given DGP dataset.
+    Parameters
+    ----------
+    scenes_dataset_json: str
+        Full path to the dataset scene json.
+    camera_datum_names: Optional[list[str]]
+        List of camera names.
+        If None, use all the cameras available in the DGP dataset.
+    lidar_datum_names: Optional[list[str]]
+        List of lidar names.
+        If None, use all the lidars available in the DGP dataset.
+    max_num_items: Optional[int]
+        If not None, then show only up to this number of items. This is useful for debugging a large dataset.
+        Default: None.
+    Returns
+    -------
+    associated_bboxes: defaultdict[defaultdict[list[Tuple]]]
+        a dictionary with key is the camera name, value is a dictionary whose key is class_name of bounding_box_2d,
+        value is list of Tuple [bounding_box_2d, bounding_box_3d, centroid_2d]
+    """
+    datum_names = camera_datum_names + lidar_datum_names
+    dataset = SynchronizedSceneDataset(
+        scenes_dataset_json,
+        datum_names=datum_names,
+        requested_annotations=[ANNOTATIONS_2D, ANNOTATIONS_3D],
+        only_annotated_datums=True
+    )
+    associated_bboxes = associate_3d_and_2d_annotations(dataset, camera_datum_names, lidar_datum_names, max_num_items)
+    return associated_bboxes
+
+
+def draw_bounding_box_2d_distance_distribution(
+    scenes_dataset_json: str,
+    output_dir: str,
+    camera_datum_names: Optional[list[str]],
+    lidar_datum_names: Optional[list[str]],
+    max_num_items: Optional[int] = MAX_NUM_ITEMS
+):
+    """Draw the distance's distributution histogram of 2d bounding boxes by associating bounding_box_3d of the same object.
+    Parameters
+    ----------
+    scenes_dataset_json: str
+        Full path to the dataset scene json.
+    output_dir: str
+        Path to save the histogram picture.
+    camera_datum_names: Optional[list[str]]
+        List of camera names.
+        If None, use all the cameras available in the DGP dataset.
+    lidar_datum_names: Optional[list[str]]
+        List of lidar names.
+        If None, use all the lidars available in the DGP dataset.
+    max_num_items: Optional[int]
+        If not None, then show only up to this number of items. This is useful for debugging a large dataset.
+        Default: None.
+    """
+    associated_bboxes = associate_3d_and_2d_annotations_dataset(
+        scenes_dataset_json, camera_datum_names, lidar_datum_names, max_num_items
+    )
+    os.makedirs(output_dir, exist_ok=True)
+    # Summarize statistics per camera per class over all scenes.
+    for camera_name in camera_datum_names:
+        for name_2d, name_3d in ONTOLOGY_NAME_MAPPER_2D_to_3D.items():
+            logging.info("Summarizing class {}".format(name_2d))
+            summarize_3d_statistics_per_class(associated_bboxes[camera_name][name_2d], output_dir, camera_name, name_2d)
+
+
+def summarize_3d_statistics_per_class(
+    associated_bboxes: list[Tuple], output_dir: str, camera_name: str, class_name: str
+):
+    """Accumulate distances of the associated bounding boxes and draw the histogram.
+    Parameters
+    ----------
+    associated_bboxes: list[Tuple]
+        A list of Tuple [bounding_box_2d, bounding_box_3d, centroid_2d]
+    output_dir: str
+        Path to save the histogram picture.
+    camera_name: str
+        camera name.
+    class_name: str
+        Class name.
+    """
+    dist = []
+    for _, bbox_lidar, __ in associated_bboxes:
+        dist.append(
+            int(
+                math.sqrt((bbox_lidar.pose.tvec[0]) * (bbox_lidar.pose.tvec[0]) + (bbox_lidar.pose.tvec[1]) *
+                          (bbox_lidar.pose.tvec[1]))
+            )
+        )
+    draw_hist(dist, output_dir, xlable='Dist', title=f"dist_{camera_name}_{class_name}")
+
+
+def draw_hist(data: list, output_dir: str, xlable: str, title: str):
+    """Draw the histogram of given data.
+    Parameters
+    ----------
+    data: list
+        A list of Tuple [bounding_box_2d, bounding_box_3d, centroid_2d]
+    output_dir: str
+        Path to save the histogram picture.
+    xlable: str
+        The label name of x.
+    title: str
+        The tile of the picture.
+    """
+    data = np.array(data)
+    bins = np.arange(MIN_DIST, MAX_DIST, DIST_BIN)  # fixed bin size
+    plt.hist(data, bins=bins)
+    plt.title(f'Distribution {title}(fixed bin size)')
+    plt.xlabel(f'variable {xlable} (bin size = 10)')
+    plt.ylabel('count')
+    plt.savefig(os.path.join(output_dir, f'histogram_{title}.png'))
diff --git a/tests/data/dgp/associate_2d_to_3d_scene/scene_01/bounding_box_2d/CAMERA_21/6d3e25d9abf1e015564f56ac176e8a7526cdd5ca.json b/tests/data/dgp/associate_2d_to_3d_scene/scene_01/bounding_box_2d/CAMERA_21/6d3e25d9abf1e015564f56ac176e8a7526cdd5ca.json
new file mode 100644
index 00000000..40e59d5d
--- /dev/null
+++ b/tests/data/dgp/associate_2d_to_3d_scene/scene_01/bounding_box_2d/CAMERA_21/6d3e25d9abf1e015564f56ac176e8a7526cdd5ca.json
@@ -0,0 +1,56 @@
+{
+  "annotations": [
+    {
+      "area": 127092,
+      "attributes": {},
+      "box": {
+        "h": 534,
+        "w": 238,
+        "x": 173,
+        "y": 1275
+      },
+      "class_id": 0,
+      "instance_id": 21,
+      "iscrowd": false
+    },
+    {
+      "area": 9800,
+      "attributes": {},
+      "box": {
+        "h": 140,
+        "w": 70,
+        "x": 1306,
+        "y": 974
+      },
+      "class_id": 0,
+      "instance_id": 25,
+      "iscrowd": false
+    },
+    {
+      "area": 2958,
+      "attributes": {},
+      "box": {
+        "h": 87,
+        "w": 34,
+        "x": 1605,
+        "y": 966
+      },
+      "class_id": 0,
+      "instance_id": 26,
+      "iscrowd": false
+    },
+    {
+      "area": 936,
+      "attributes": {},
+      "box": {
+        "h": 52,
+        "w": 18,
+        "x": 1963,
+        "y": 1008
+      },
+      "class_id": 0,
+      "instance_id": 32,
+      "iscrowd": false
+    }
+  ]
+}
\ No newline at end of file
diff --git a/tests/data/dgp/associate_2d_to_3d_scene/scene_01/bounding_box_3d/CAMERA_21/1345048_001.json b/tests/data/dgp/associate_2d_to_3d_scene/scene_01/bounding_box_3d/CAMERA_21/1345048_001.json
new file mode 100644
index 00000000..c72e5883
--- /dev/null
+++ b/tests/data/dgp/associate_2d_to_3d_scene/scene_01/bounding_box_3d/CAMERA_21/1345048_001.json
@@ -0,0 +1,193 @@
+{
+  "annotations": [
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.602,
+        "length": 0.923,
+        "occlusion": 0,
+        "pose": {
+          "reference_coordinate_system": "",
+          "rotation": {
+            "qw": -0.5460047245395266,
+            "qx": -0.5463773062342265,
+            "qy": 0.44794882501102434,
+            "qz": -0.4502138716032509
+          },
+          "translation": {
+            "x": -0.021767233204855074,
+            "y": -0.33786151698734557,
+            "z": 23.655119181323926
+          }
+        },
+        "truncation": 0.0,
+        "width": 0.702
+      },
+      "class_id": 0,
+      "instance_id": 4081736164,
+      "num_points": 488
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.458,
+        "length": 1.003,
+        "occlusion": 0,
+        "pose": {
+          "reference_coordinate_system": "",
+          "rotation": {
+            "qw": -0.515906332033461,
+            "qx": -0.5164238763720558,
+            "qy": 0.4821749584013948,
+            "qz": -0.4844113396394155
+          },
+          "translation": {
+            "x": -3.0012585309692668,
+            "y": 1.3998720942093428,
+            "z": 5.8925998920151414
+          }
+        },
+        "truncation": 0.0,
+        "width": 0.687
+      },
+      "class_id": 0,
+      "instance_id": 3157625369,
+      "num_points": 2506
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.7,
+        "length": 0.7,
+        "occlusion": 0,
+        "pose": {
+          "reference_coordinate_system": "",
+          "rotation": {
+            "qw": -0.6262508644615135,
+            "qx": -0.6261543455500395,
+            "qy": 0.32728740602920997,
+            "qz": -0.3295808613446478
+          },
+          "translation": {
+            "x": 21.405784649079266,
+            "y": -1.3684778965882174,
+            "z": 67.40673156544199
+          }
+        },
+        "truncation": 0.0,
+        "width": 0.7
+      },
+      "class_id": 0,
+      "instance_id": 4002157367,
+      "num_points": 7
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.7,
+        "length": 0.7,
+        "occlusion": 0,
+        "pose": {
+          "reference_coordinate_system": "",
+          "rotation": {
+            "qw": -0.39744937852144224,
+            "qx": -0.39515948875230333,
+            "qy": -0.5856921452824387,
+            "qz": 0.5855319640432897
+          },
+          "translation": {
+            "x": 5.950197640790634,
+            "y": -1.4554172491242525,
+            "z": 41.890144866234095
+          }
+        },
+        "truncation": 0.0,
+        "width": 0.7
+      },
+      "class_id": 0,
+      "instance_id": 3015682071,
+      "num_points": 75
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.7,
+        "length": 0.7,
+        "occlusion": 0,
+        "pose": {
+          "reference_coordinate_system": "",
+          "rotation": {
+            "qw": -0.5168602686509107,
+            "qx": -0.5173734033178335,
+            "qy": 0.4811559748520739,
+            "qz": -0.48339337200005283
+          },
+          "translation": {
+            "x": 1.1096138012673293,
+            "y": 6.686360433724587,
+            "z": -53.1512378533771
+          }
+        },
+        "truncation": 0.0,
+        "width": 0.7
+      },
+      "class_id": 0,
+      "instance_id": 3306246368,
+      "num_points": 71
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.7,
+        "length": 0.7,
+        "occlusion": 0,
+        "pose": {
+          "reference_coordinate_system": "",
+          "rotation": {
+            "qw": -0.5168602686509107,
+            "qx": -0.5173734033178335,
+            "qy": 0.4811559748520739,
+            "qz": -0.48339337200005283
+          },
+          "translation": {
+            "x": 0.37169697588876716,
+            "y": 6.63103626392018,
+            "z": -53.30554597065748
+          }
+        },
+        "truncation": 0.0,
+        "width": 0.7
+      },
+      "class_id": 0,
+      "instance_id": 279291877,
+      "num_points": 83
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.7,
+        "length": 0.7,
+        "occlusion": 0,
+        "pose": {
+          "reference_coordinate_system": "",
+          "rotation": {
+            "qw": -0.5021280729858156,
+            "qx": -0.5027080886060614,
+            "qy": 0.49645834492590357,
+            "qz": -0.49867934358967014
+          },
+          "translation": {
+            "x": 2.600034834051968,
+            "y": 9.379402753234501,
+            "z": -82.74383588414094
+          }
+        },
+        "truncation": 0.0,
+        "width": 0.7
+      },
+      "class_id": 0,
+      "instance_id": 129671060,
+      "num_points": 29
+    }
+  ]
+}
\ No newline at end of file
diff --git a/tests/data/dgp/associate_2d_to_3d_scene/scene_01/bounding_box_3d/LIDAR/1345048_001.json b/tests/data/dgp/associate_2d_to_3d_scene/scene_01/bounding_box_3d/LIDAR/1345048_001.json
new file mode 100644
index 00000000..2eaf4d18
--- /dev/null
+++ b/tests/data/dgp/associate_2d_to_3d_scene/scene_01/bounding_box_3d/LIDAR/1345048_001.json
@@ -0,0 +1,193 @@
+{
+  "annotations": [
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.602,
+        "length": 0.923,
+        "occlusion": 0,
+        "pose": {
+          "reference_coordinate_system": "",
+          "rotation": {
+            "qw": -0.9945361181899448,
+            "qx": 0.005844301846375331,
+            "qy": -0.04575480638969989,
+            "qz": 0.09364962062841337
+          },
+          "translation": {
+            "x": 26.5559912338922,
+            "y": 0.19018018179900764,
+            "z": 0.996752776279834
+          }
+        },
+        "truncation": 0.0,
+        "width": 0.702
+      },
+      "class_id": 0,
+      "instance_id": 4081736164,
+      "num_points": 488
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.458,
+        "length": 1.003,
+        "occlusion": 0,
+        "pose": {
+          "reference_coordinate_system": "",
+          "rotation": {
+            "qw": -0.9985009114869703,
+            "qx": 0.0028882970852891765,
+            "qy": -0.04603602841012219,
+            "qz": 0.029466448511131504
+          },
+          "translation": {
+            "x": 8.688338234722778,
+            "y": 3.041835891958385,
+            "z": 0.8581381595079947
+          }
+        },
+        "truncation": 0.0,
+        "width": 0.687
+      },
+      "class_id": 0,
+      "instance_id": 3157625369,
+      "num_points": 2506
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.7,
+        "length": 0.7,
+        "occlusion": 0,
+        "pose": {
+          "reference_coordinate_system": "",
+          "rotation": {
+            "qw": -0.9546205851977209,
+            "qx": 0.015040096910548492,
+            "qy": -0.04360566083379287,
+            "qz": 0.29423099793347873
+          },
+          "translation": {
+            "x": 70.372899118791,
+            "y": -20.94096488390045,
+            "z": -1.8244220886784461
+          }
+        },
+        "truncation": 0.0,
+        "width": 0.7
+      },
+      "class_id": 0,
+      "instance_id": 4002157367,
+      "num_points": 7
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.7,
+        "length": 0.7,
+        "occlusion": 0,
+        "pose": {
+          "reference_coordinate_system": "",
+          "rotation": {
+            "qw": 0.1857940747174927,
+            "qx": 0.045012389826135105,
+            "qy": 0.010076851391705489,
+            "qz": 0.9815054272025399
+          },
+          "translation": {
+            "x": 44.8594045019388,
+            "y": -5.654335267526108,
+            "z": 0.49063134648028495
+          }
+        },
+        "truncation": 0.0,
+        "width": 0.7
+      },
+      "class_id": 0,
+      "instance_id": 3015682071,
+      "num_points": 75
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.7,
+        "length": 0.7,
+        "occlusion": 0,
+        "pose": {
+          "reference_coordinate_system": "",
+          "rotation": {
+            "qw": -0.998440882943295,
+            "qx": 0.00297904410121062,
+            "qy": -0.046030245144616705,
+            "qz": 0.03143477525898902
+          },
+          "translation": {
+            "x": -50.56086723143903,
+            "y": -1.4905566498621283,
+            "z": 0.9585148271079902
+          }
+        },
+        "truncation": 0.0,
+        "width": 0.7
+      },
+      "class_id": 0,
+      "instance_id": 3306246368,
+      "num_points": 71
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.7,
+        "length": 0.7,
+        "occlusion": 0,
+        "pose": {
+          "reference_coordinate_system": "",
+          "rotation": {
+            "qw": -0.998440882943295,
+            "qx": 0.00297904410121062,
+            "qy": -0.046030245144616705,
+            "qz": 0.03143477525898902
+          },
+          "translation": {
+            "x": -50.71478800739544,
+            "y": -0.753365988206383,
+            "z": 1.0237169980551286
+          }
+        },
+        "truncation": 0.0,
+        "width": 0.7
+      },
+      "class_id": 0,
+      "instance_id": 279291877,
+      "num_points": 83
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.7,
+        "length": 0.7,
+        "occlusion": 0,
+        "pose": {
+          "reference_coordinate_system": "",
+          "rotation": {
+            "qw": -0.9989345200499858,
+            "qx": 0.0015970034043485057,
+            "qy": -0.04609889100571691,
+            "qz": 0.0014718969645083901
+          },
+          "translation": {
+            "x": -80.2643855030285,
+            "y": -3.192519044929213,
+            "z": 0.9625515506138242
+          }
+        },
+        "truncation": 0.0,
+        "width": 0.7
+      },
+      "class_id": 0,
+      "instance_id": 129671060,
+      "num_points": 29
+    }
+  ]
+}
\ No newline at end of file
diff --git a/tests/data/dgp/associate_2d_to_3d_scene/scene_01/calibration/e10c7424d73936c7c8306cd02e927b7d2639c1a6.json b/tests/data/dgp/associate_2d_to_3d_scene/scene_01/calibration/e10c7424d73936c7c8306cd02e927b7d2639c1a6.json
new file mode 100644
index 00000000..dca87874
--- /dev/null
+++ b/tests/data/dgp/associate_2d_to_3d_scene/scene_01/calibration/e10c7424d73936c7c8306cd02e927b7d2639c1a6.json
@@ -0,0 +1,94 @@
+{
+  "extrinsics": [
+    {
+      "reference_coordinate_system": "",
+      "rotation": {
+        "qw": 1.0,
+        "qx": 0.0,
+        "qy": 0.0,
+        "qz": 0.0
+      },
+      "translation": {
+        "x": 0.0,
+        "y": 0.0,
+        "z": 0.0
+      }
+    },
+    {
+      "reference_coordinate_system": "",
+      "rotation": {
+        "qw": 0.4771700483160217,
+        "qx": -0.5252321849265068,
+        "qy": 0.519020460103825,
+        "qz": -0.4765056448233028
+      },
+      "translation": {
+        "x": 2.968057416879674,
+        "y": 0.009892013289572787,
+        "z": 2.801236669326528
+      }
+    }
+  ],
+  "intrinsics": [
+    {
+      "alpha": 0.0,
+      "beta": 0.0,
+      "cx": 0.0,
+      "cy": 0.0,
+      "equirectangular": 0,
+      "fisheye": 0,
+      "fov": 0.0,
+      "fx": 0.0,
+      "fy": 0.0,
+      "k1": 0.0,
+      "k2": 0.0,
+      "k3": 0.0,
+      "k4": 0.0,
+      "k5": 0.0,
+      "k6": 0.0,
+      "p1": 0.0,
+      "p2": 0.0,
+      "s1": 0.0,
+      "s2": 0.0,
+      "s3": 0.0,
+      "s4": 0.0,
+      "skew": 0.0,
+      "taux": 0.0,
+      "tauy": 0.0,
+      "w": 0.0,
+      "xi": 0.0
+    },
+    {
+      "alpha": 0.0,
+      "beta": 0.0,
+      "cx": 1344.739990234375,
+      "cy": 1073.77001953125,
+      "equirectangular": 0,
+      "fisheye": 0,
+      "fov": 0.0,
+      "fx": 1976.449951171875,
+      "fy": 1977.06005859375,
+      "k1": 0.0,
+      "k2": 0.0,
+      "k3": 0.0,
+      "k4": 0.0,
+      "k5": 0.0,
+      "k6": 0.0,
+      "p1": 0.0,
+      "p2": 0.0,
+      "s1": 0.0,
+      "s2": 0.0,
+      "s3": 0.0,
+      "s4": 0.0,
+      "skew": 0.0,
+      "taux": 0.0,
+      "tauy": 0.0,
+      "w": 0.0,
+      "xi": 0.0
+    }
+  ],
+  "names": [
+    "LIDAR",
+    "CAMERA_21"
+  ]
+}
\ No newline at end of file
diff --git a/tests/data/dgp/associate_2d_to_3d_scene/scene_01/ontology/67f011a9c86852dfe1b2275cbbb6c0c7aa8d1848.json b/tests/data/dgp/associate_2d_to_3d_scene/scene_01/ontology/67f011a9c86852dfe1b2275cbbb6c0c7aa8d1848.json
new file mode 100644
index 00000000..f09afdf0
--- /dev/null
+++ b/tests/data/dgp/associate_2d_to_3d_scene/scene_01/ontology/67f011a9c86852dfe1b2275cbbb6c0c7aa8d1848.json
@@ -0,0 +1,26 @@
+{
+  "items": [
+    {
+      "color": {
+        "b": 20,
+        "g": 60,
+        "r": 220
+      },
+      "id": 0,
+      "isthing": true,
+      "name": "Person",
+      "supercategory": ""
+    },
+    {
+      "color": {
+        "b": 0,
+        "g": 142,
+        "r": 0
+      },
+      "id": 1,
+      "isthing": true,
+      "name": "Car",
+      "supercategory": ""
+    }
+  ]
+}
\ No newline at end of file
diff --git a/tests/data/dgp/associate_2d_to_3d_scene/scene_01/ontology/e77320974afa353aa67d28a8c3c59c595dd9037f.json b/tests/data/dgp/associate_2d_to_3d_scene/scene_01/ontology/e77320974afa353aa67d28a8c3c59c595dd9037f.json
new file mode 100644
index 00000000..7dc3d7e8
--- /dev/null
+++ b/tests/data/dgp/associate_2d_to_3d_scene/scene_01/ontology/e77320974afa353aa67d28a8c3c59c595dd9037f.json
@@ -0,0 +1,26 @@
+{
+  "items": [
+    {
+      "color": {
+        "b": 60,
+        "g": 20,
+        "r": 220
+      },
+      "id": 0,
+      "isthing": true,
+      "name": "Pedestrian",
+      "supercategory": ""
+    },
+    {
+      "color": {
+        "b": 142,
+        "g": 0,
+        "r": 0
+      },
+      "id": 1,
+      "isthing": true,
+      "name": "Car",
+      "supercategory": ""
+    }
+  ]
+}
\ No newline at end of file
diff --git a/tests/data/dgp/associate_2d_to_3d_scene/scene_01/point_cloud/LIDAR/1345048_001.npz b/tests/data/dgp/associate_2d_to_3d_scene/scene_01/point_cloud/LIDAR/1345048_001.npz
new file mode 100644
index 00000000..0039dbb0
Binary files /dev/null and b/tests/data/dgp/associate_2d_to_3d_scene/scene_01/point_cloud/LIDAR/1345048_001.npz differ
diff --git a/tests/data/dgp/associate_2d_to_3d_scene/scene_01/rgb/CAMERA_21/1345048_001.jpg b/tests/data/dgp/associate_2d_to_3d_scene/scene_01/rgb/CAMERA_21/1345048_001.jpg
new file mode 100644
index 00000000..08682c86
Binary files /dev/null and b/tests/data/dgp/associate_2d_to_3d_scene/scene_01/rgb/CAMERA_21/1345048_001.jpg differ
diff --git a/tests/data/dgp/associate_2d_to_3d_scene/scene_01/scene_6245881cb04e9f71ae6de99064e771dfa370329d.json b/tests/data/dgp/associate_2d_to_3d_scene/scene_01/scene_6245881cb04e9f71ae6de99064e771dfa370329d.json
new file mode 100644
index 00000000..f2e7696a
--- /dev/null
+++ b/tests/data/dgp/associate_2d_to_3d_scene/scene_01/scene_6245881cb04e9f71ae6de99064e771dfa370329d.json
@@ -0,0 +1,123 @@
+{
+  "creation_date": "2023-09-20T01:57:01.750472Z",
+  "data": [
+    {
+      "datum": {
+        "image": {
+          "annotations": {
+            "0": "bounding_box_2d/CAMERA_21/6d3e25d9abf1e015564f56ac176e8a7526cdd5ca.json",
+            "1": "bounding_box_3d/CAMERA_21/1345048_001.json"
+          },
+          "channels": 3,
+          "filename": "rgb/CAMERA_21/1345048_001.jpg",
+          "height": 1836,
+          "metadata": {},
+          "pose": {
+            "reference_coordinate_system": "",
+            "rotation": {
+              "qw": -0.11017830669879913,
+              "qx": 0.10803831368684769,
+              "qy": 0.6982220411300659,
+              "qz": -0.6990525126457214
+            },
+            "translation": {
+              "x": 433.2738037109375,
+              "y": 807.4990844726562,
+              "z": -29.08929443359375
+            }
+          },
+          "width": 2692
+        }
+      },
+      "id": {
+        "index": "0",
+        "log": "dummy",
+        "name": "CAMERA_21",
+        "timestamp": "2023-04-26T22:35:22.999530Z"
+      },
+      "key": "957a17d7c7c4e17a3693543306fb97af98c75b34",
+      "next_key": "7d1bb4ffb684d380f998dd09c61a182909e271c2",
+      "prev_key": ""
+    },
+    {
+      "datum": {
+        "point_cloud": {
+          "annotations": {
+            "1": "bounding_box_3d/LIDAR/1345048_001.json"
+          },
+          "filename": "point_cloud/LIDAR/1345048_001.npz",
+          "metadata": {},
+          "point_fields": [],
+          "point_format": [
+            "X",
+            "Y",
+            "Z",
+            "INTENSITY"
+          ],
+          "pose": {
+            "reference_coordinate_system": "",
+            "rotation": {
+              "qw": 0.5861750245094299,
+              "qx": -0.036432359367609024,
+              "qy": -0.02829030528664589,
+              "qz": -0.8088703155517578
+            },
+            "translation": {
+              "x": 434.11273193359375,
+              "y": 810.062744140625,
+              "z": -32.15201187133789
+            }
+          }
+        }
+      },
+      "id": {
+        "index": "0",
+        "log": "dummy",
+        "name": "LIDAR",
+        "timestamp": "2023-04-26T22:35:23.070990Z"
+      },
+      "key": "02eabaf3ca2fb9d13ece23c0f9ae74be098b2617",
+      "next_key": "b9442c27d742b2ac0fc232bea2db933518a8b933",
+      "prev_key": ""
+    }
+  ],
+  "description": "",
+  "log": "",
+  "metadata": {},
+  "name": "dummy",
+  "ontologies": {
+    "0": "e77320974afa353aa67d28a8c3c59c595dd9037f",
+    "1": "67f011a9c86852dfe1b2275cbbb6c0c7aa8d1848"
+  },
+  "samples": [
+    {
+      "calibration_key": "e10c7424d73936c7c8306cd02e927b7d2639c1a6",
+      "datum_keys": [
+        "957a17d7c7c4e17a3693543306fb97af98c75b34",
+        "02eabaf3ca2fb9d13ece23c0f9ae74be098b2617"
+      ],
+      "id": {
+        "index": "0",
+        "log": "dummy",
+        "name": "1345048_001",
+        "timestamp": "2023-04-26T22:35:23.070990Z"
+      },
+      "metadata": {}
+    }
+  ],
+  "statistics": {
+    "image_statistics": {
+      "count": "10",
+      "mean": [
+        117.7092,
+        127.629196,
+        117.40488
+      ],
+      "stddev": [
+        7.1080227,
+        6.942289,
+        7.652583
+      ]
+    }
+  }
+}
\ No newline at end of file
diff --git a/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_01/15616458249936530.json b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_01/15616458249936530.json
new file mode 100644
index 00000000..afc86af1
--- /dev/null
+++ b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_01/15616458249936530.json
@@ -0,0 +1,82 @@
+{
+  "annotations": [
+    {
+      "attributes": {},
+      "box": {
+        "height": 2.535,
+        "length": 6.5809999999999995,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": 0.5304017664397861,
+            "qx": 0.5193498394978048,
+            "qy": -0.4767493205222065,
+            "qz": 0.47080759950618184
+          },
+          "translation": {
+            "x": 5.806082944058559,
+            "y": -1.963184294101893,
+            "z": 79.99168241572625
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.925
+      },
+      "class_id": 1,
+      "instance_id": 443946110,
+      "num_points": 190
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.584,
+        "length": 4.588,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": 0.5788441361321942,
+            "qx": 0.5785921399924261,
+            "qy": -0.4071231246510714,
+            "qz": 0.4054890417492277
+          },
+          "translation": {
+            "x": 8.886862881455494,
+            "y": -1.7219724069470885,
+            "z": 92.19259417685407
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.048
+      },
+      "class_id": 2,
+      "instance_id": 3215172593,
+      "num_points": 40
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.4969999999999999,
+        "length": 4.433,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": 0.4844158364565127,
+            "qx": 0.47549688764560166,
+            "qy": 0.527733051586114,
+            "qz": -0.5106288608109525
+          },
+          "translation": {
+            "x": 0.7758863153653035,
+            "y": -0.9747296183397793,
+            "z": 69.245671238054
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.117
+      },
+      "class_id": 2,
+      "instance_id": 3357023490,
+      "num_points": 31
+    }
+  ]
+}
\ No newline at end of file
diff --git a/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_01/15616458250936520.json b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_01/15616458250936520.json
new file mode 100644
index 00000000..87020724
--- /dev/null
+++ b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_01/15616458250936520.json
@@ -0,0 +1,82 @@
+{
+  "annotations": [
+    {
+      "attributes": {},
+      "box": {
+        "height": 2.535,
+        "length": 6.5809999999999995,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": 0.5277507467813652,
+            "qx": 0.522005802646785,
+            "qy": -0.47526749989490125,
+            "qz": 0.47234510140198016
+          },
+          "translation": {
+            "x": 5.755194512655734,
+            "y": -2.103753196565094,
+            "z": 79.0251873956995
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.925
+      },
+      "class_id": 1,
+      "instance_id": 443946110,
+      "num_points": 208
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.584,
+        "length": 4.588,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": 0.5859698881373695,
+            "qx": 0.5866789138823866,
+            "qy": -0.396884821455614,
+            "qz": 0.39361095094040194
+          },
+          "translation": {
+            "x": 8.99858874257311,
+            "y": -1.8919932155365586,
+            "z": 91.35045110808187
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.048
+      },
+      "class_id": 2,
+      "instance_id": 3215172593,
+      "num_points": 45
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.4969999999999999,
+        "length": 4.433,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": 0.4838980233873106,
+            "qx": 0.4760665485686835,
+            "qy": 0.528085896485396,
+            "qz": -0.5102240980480743
+          },
+          "translation": {
+            "x": 0.6018264442741881,
+            "y": -1.0368721626507522,
+            "z": 66.94405907872215
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.117
+      },
+      "class_id": 2,
+      "instance_id": 3357023490,
+      "num_points": 39
+    }
+  ]
+}
\ No newline at end of file
diff --git a/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_01/15616458251936472.json b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_01/15616458251936472.json
new file mode 100644
index 00000000..49256b91
--- /dev/null
+++ b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_01/15616458251936472.json
@@ -0,0 +1,82 @@
+{
+  "annotations": [
+    {
+      "attributes": {},
+      "box": {
+        "height": 2.535,
+        "length": 6.5809999999999995,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": 0.5251036316795,
+            "qx": 0.524614597848685,
+            "qy": -0.4735143308462214,
+            "qz": 0.47416229099783813
+          },
+          "translation": {
+            "x": 5.703597680610184,
+            "y": -2.1929068961642315,
+            "z": 78.07271328987281
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.925
+      },
+      "class_id": 1,
+      "instance_id": 443946110,
+      "num_points": 207
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.584,
+        "length": 4.588,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": 0.5931218762695512,
+            "qx": 0.5945991847651969,
+            "qy": -0.38604426784487683,
+            "qz": 0.3816124639358163
+          },
+          "translation": {
+            "x": 9.130798986741596,
+            "y": -2.005049399226664,
+            "z": 90.51716573938165
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.048
+      },
+      "class_id": 2,
+      "instance_id": 3215172593,
+      "num_points": 54
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.4969999999999999,
+        "length": 4.433,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": 0.4836206853503111,
+            "qx": 0.4764069299029632,
+            "qy": 0.5283638291610611,
+            "qz": -0.5098814900307627
+          },
+          "translation": {
+            "x": 0.42496718948661716,
+            "y": -1.0515032728378628,
+            "z": 64.62893064112268
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.117
+      },
+      "class_id": 2,
+      "instance_id": 3357023490,
+      "num_points": 53
+    }
+  ]
+}
\ No newline at end of file
diff --git a/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_05/15616458249936530.json b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_05/15616458249936530.json
new file mode 100644
index 00000000..fc4e11dc
--- /dev/null
+++ b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_05/15616458249936530.json
@@ -0,0 +1,134 @@
+{
+  "annotations": [
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.8780000000000001,
+        "length": 4.605,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.6085607524096444,
+            "qx": -0.6168654299590625,
+            "qy": 0.3443959285004715,
+            "qz": -0.3612786962724606
+          },
+          "translation": {
+            "x": -15.658014313603644,
+            "y": -2.398683867584168,
+            "z": 62.66901499037658
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.12
+      },
+      "class_id": 2,
+      "instance_id": 715214751,
+      "num_points": 1
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.8780000000000001,
+        "length": 4.605,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.6085607524096444,
+            "qx": -0.6168654299590625,
+            "qy": 0.3443959285004715,
+            "qz": -0.3612786962724606
+          },
+          "translation": {
+            "x": -7.600298214896611,
+            "y": -2.501357225385391,
+            "z": 63.79046470134767
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.12
+      },
+      "class_id": 2,
+      "instance_id": 2110970748,
+      "num_points": 0
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.8780000000000001,
+        "length": 4.605,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.1931768575779799,
+            "qx": -0.19797931305576566,
+            "qy": 0.6649796253559954,
+            "qz": -0.6937499485835412
+          },
+          "translation": {
+            "x": -12.789521250117787,
+            "y": -1.873435912426885,
+            "z": 86.38273659054607
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.12
+      },
+      "class_id": 2,
+      "instance_id": 2556950328,
+      "num_points": 0
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 3.404,
+        "length": 8.859,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.6095396539841155,
+            "qx": -0.6146473106223558,
+            "qy": 0.34640743044642597,
+            "qz": -0.3614858031750856
+          },
+          "translation": {
+            "x": -19.62596820971453,
+            "y": -3.1794260477743137,
+            "z": 62.56267813690306
+          }
+        },
+        "truncation": 0.0,
+        "width": 3.266
+      },
+      "class_id": 1,
+      "instance_id": 3527146084,
+      "num_points": 0
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.8780000000000001,
+        "length": 4.605,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": 0.049684604339896854,
+            "qx": 0.04755974491532822,
+            "qy": 0.6908279001037925,
+            "qz": -0.7197404554374887
+          },
+          "translation": {
+            "x": -24.040295358825006,
+            "y": -3.302248895042567,
+            "z": 70.59089751412534
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.12
+      },
+      "class_id": 2,
+      "instance_id": 3668932913,
+      "num_points": 0
+    }
+  ]
+}
\ No newline at end of file
diff --git a/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_05/15616458250936520.json b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_05/15616458250936520.json
new file mode 100644
index 00000000..38347d63
--- /dev/null
+++ b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_05/15616458250936520.json
@@ -0,0 +1,134 @@
+{
+  "annotations": [
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.8780000000000001,
+        "length": 4.605,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.6084948742897922,
+            "qx": -0.616920832548318,
+            "qy": 0.3450407277809002,
+            "qz": -0.3606793180976261
+          },
+          "translation": {
+            "x": -16.663888781563628,
+            "y": -2.4397240008759127,
+            "z": 61.876856345466194
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.12
+      },
+      "class_id": 2,
+      "instance_id": 715214751,
+      "num_points": 1
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.8780000000000001,
+        "length": 4.605,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.6084948742897922,
+            "qx": -0.616920832548318,
+            "qy": 0.3450407277809002,
+            "qz": -0.3606793180976261
+          },
+          "translation": {
+            "x": -8.60638646596476,
+            "y": -2.5551467801967647,
+            "z": 62.998602313204174
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.12
+      },
+      "class_id": 2,
+      "instance_id": 2110970748,
+      "num_points": 0
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.8780000000000001,
+        "length": 4.605,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.19355747052926098,
+            "qx": -0.1975823588507192,
+            "qy": 0.6654831315179182,
+            "qz": -0.6932740574537652
+          },
+          "translation": {
+            "x": -13.795861903038485,
+            "y": -1.9429694554685284,
+            "z": 85.59124832050247
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.12
+      },
+      "class_id": 2,
+      "instance_id": 2556950328,
+      "num_points": 0
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 3.404,
+        "length": 8.859,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.609475013071249,
+            "qx": -0.6147017641821768,
+            "qy": 0.3470507639096846,
+            "qz": -0.3608846309041527
+          },
+          "translation": {
+            "x": -20.632956768612758,
+            "y": -3.214644676169655,
+            "z": 61.76951920752299
+          }
+        },
+        "truncation": 0.0,
+        "width": 3.266
+      },
+      "class_id": 1,
+      "instance_id": 3527146084,
+      "num_points": 1
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.8780000000000001,
+        "length": 4.605,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": 0.049159707046413204,
+            "qx": 0.048100627878299995,
+            "qy": 0.6911618973723336,
+            "qz": -0.7194198248738366
+          },
+          "translation": {
+            "x": -25.047868856747755,
+            "y": -3.33936220910482,
+            "z": 69.79738771610073
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.12
+      },
+      "class_id": 2,
+      "instance_id": 3668932913,
+      "num_points": 0
+    }
+  ]
+}
\ No newline at end of file
diff --git a/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_05/15616458251936472.json b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_05/15616458251936472.json
new file mode 100644
index 00000000..50da6904
--- /dev/null
+++ b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_05/15616458251936472.json
@@ -0,0 +1,134 @@
+{
+  "annotations": [
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.8780000000000001,
+        "length": 4.605,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.6083291788415417,
+            "qx": -0.617056447055441,
+            "qy": 0.34552583103455414,
+            "qz": -0.36026219813515314
+          },
+          "translation": {
+            "x": -17.665622983127605,
+            "y": -2.486603603194226,
+            "z": 61.08775079653992
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.12
+      },
+      "class_id": 2,
+      "instance_id": 715214751,
+      "num_points": 0
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.8780000000000001,
+        "length": 4.605,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.6083291788415417,
+            "qx": -0.617056447055441,
+            "qy": 0.34552583103455414,
+            "qz": -0.36026219813515314
+          },
+          "translation": {
+            "x": -9.60833094364989,
+            "y": -2.610352334396566,
+            "z": 62.210119382209314
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.12
+      },
+      "class_id": 2,
+      "instance_id": 2110970748,
+      "num_points": 0
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.8780000000000001,
+        "length": 4.605,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.19373679932244514,
+            "qx": -0.1973506695723212,
+            "qy": 0.6659292865792363,
+            "qz": -0.6928614227128831
+          },
+          "translation": {
+            "x": -14.799351314606838,
+            "y": -2.016296623291055,
+            "z": 84.80289422994338
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.12
+      },
+      "class_id": 2,
+      "instance_id": 2556950328,
+      "num_points": 0
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 3.404,
+        "length": 8.859,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.6093104339865528,
+            "qx": -0.6148369658142916,
+            "qy": 0.34753502442223594,
+            "qz": -0.3604659585914189
+          },
+          "translation": {
+            "x": -21.635371438198945,
+            "y": -3.2578706629249155,
+            "z": 60.97926888085044
+          }
+        },
+        "truncation": 0.0,
+        "width": 3.266
+      },
+      "class_id": 1,
+      "instance_id": 3527146084,
+      "num_points": 0
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.8780000000000001,
+        "length": 4.605,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": 0.04884609845567672,
+            "qx": 0.04846717328825534,
+            "qy": 0.6915003175778534,
+            "qz": -0.7190913033605907
+          },
+          "translation": {
+            "x": -26.05113708097997,
+            "y": -3.3867309426168504,
+            "z": 69.00660248649751
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.12
+      },
+      "class_id": 2,
+      "instance_id": 3668932913,
+      "num_points": 0
+    }
+  ]
+}
\ No newline at end of file
diff --git a/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_06/15616458249936530.json b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_06/15616458249936530.json
new file mode 100644
index 00000000..a3799438
--- /dev/null
+++ b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_06/15616458249936530.json
@@ -0,0 +1,30 @@
+{
+  "annotations": [
+    {
+      "attributes": {},
+      "box": {
+        "height": 2.343,
+        "length": 6.236,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": 0.6281455293825682,
+            "qx": 0.6172186407074127,
+            "qy": -0.3414068929660027,
+            "qz": 0.3285052159635969
+          },
+          "translation": {
+            "x": -2.815619609081068,
+            "y": 0.016023213189555463,
+            "z": 23.1623846354089
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.747
+      },
+      "class_id": 2,
+      "instance_id": 1740587446,
+      "num_points": 3126
+    }
+  ]
+}
\ No newline at end of file
diff --git a/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_06/15616458250936520.json b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_06/15616458250936520.json
new file mode 100644
index 00000000..c5f1e2f7
--- /dev/null
+++ b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_06/15616458250936520.json
@@ -0,0 +1,30 @@
+{
+  "annotations": [
+    {
+      "attributes": {},
+      "box": {
+        "height": 2.343,
+        "length": 6.236,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": 0.6275663593811421,
+            "qx": 0.6177853908061366,
+            "qy": -0.34120343813383097,
+            "qz": 0.3287581014747193
+          },
+          "translation": {
+            "x": -1.7997894739946787,
+            "y": -0.023757241389148476,
+            "z": 22.397718576682337
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.747
+      },
+      "class_id": 2,
+      "instance_id": 1740587446,
+      "num_points": 3539
+    }
+  ]
+}
\ No newline at end of file
diff --git a/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_06/15616458251936472.json b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_06/15616458251936472.json
new file mode 100644
index 00000000..dd06e906
--- /dev/null
+++ b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_06/15616458251936472.json
@@ -0,0 +1,30 @@
+{
+  "annotations": [
+    {
+      "attributes": {},
+      "box": {
+        "height": 2.343,
+        "length": 6.236,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": 0.6271662219401032,
+            "qx": 0.6181580223983153,
+            "qy": -0.3409676597891742,
+            "qz": 0.3290657143791756
+          },
+          "translation": {
+            "x": -0.7896143632035546,
+            "y": -0.04930589464447621,
+            "z": 21.63727011272067
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.747
+      },
+      "class_id": 2,
+      "instance_id": 1740587446,
+      "num_points": 3649
+    }
+  ]
+}
\ No newline at end of file
diff --git a/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_07/15616458249936530.json b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_07/15616458249936530.json
new file mode 100644
index 00000000..7888aca0
--- /dev/null
+++ b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_07/15616458249936530.json
@@ -0,0 +1,30 @@
+{
+  "annotations": [
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.94,
+        "length": 4.276,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": 0.28574619093218734,
+            "qx": 0.27310598830227506,
+            "qy": 0.6518881238355256,
+            "qz": -0.647150761046747
+          },
+          "translation": {
+            "x": -7.1185863677576435,
+            "y": -3.1020348387824015,
+            "z": 99.49680207834444
+          }
+        },
+        "truncation": 0.0,
+        "width": 1.9060000000000001
+      },
+      "class_id": 2,
+      "instance_id": 1793247213,
+      "num_points": 0
+    }
+  ]
+}
\ No newline at end of file
diff --git a/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_07/15616458250936520.json b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_07/15616458250936520.json
new file mode 100644
index 00000000..2038f640
--- /dev/null
+++ b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_07/15616458250936520.json
@@ -0,0 +1,30 @@
+{
+  "annotations": [
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.94,
+        "length": 4.276,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": 0.2854611217802568,
+            "qx": 0.2734216595365504,
+            "qy": 0.6513564686963327,
+            "qz": -0.6476783883500212
+          },
+          "translation": {
+            "x": -8.186482909337428,
+            "y": -2.991190405032512,
+            "z": 100.20658820074686
+          }
+        },
+        "truncation": 0.0,
+        "width": 1.9060000000000001
+      },
+      "class_id": 2,
+      "instance_id": 1793247213,
+      "num_points": 0
+    }
+  ]
+}
\ No newline at end of file
diff --git a/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_07/15616458251936472.json b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_07/15616458251936472.json
new file mode 100644
index 00000000..c3d92c9e
--- /dev/null
+++ b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_07/15616458251936472.json
@@ -0,0 +1,30 @@
+{
+  "annotations": [
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.94,
+        "length": 4.276,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": 0.28516826788262606,
+            "qx": 0.27377457661689925,
+            "qy": 0.6510061774570789,
+            "qz": -0.6480104143482452
+          },
+          "translation": {
+            "x": -9.252877356124372,
+            "y": -2.9315270671982034,
+            "z": 100.91046259791028
+          }
+        },
+        "truncation": 0.0,
+        "width": 1.9060000000000001
+      },
+      "class_id": 2,
+      "instance_id": 1793247213,
+      "num_points": 0
+    }
+  ]
+}
\ No newline at end of file
diff --git a/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_08/15616458249936530.json b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_08/15616458249936530.json
new file mode 100644
index 00000000..57879a34
--- /dev/null
+++ b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_08/15616458249936530.json
@@ -0,0 +1,3 @@
+{
+  "annotations": []
+}
\ No newline at end of file
diff --git a/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_08/15616458250936520.json b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_08/15616458250936520.json
new file mode 100644
index 00000000..57879a34
--- /dev/null
+++ b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_08/15616458250936520.json
@@ -0,0 +1,3 @@
+{
+  "annotations": []
+}
\ No newline at end of file
diff --git a/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_08/15616458251936472.json b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_08/15616458251936472.json
new file mode 100644
index 00000000..57879a34
--- /dev/null
+++ b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_08/15616458251936472.json
@@ -0,0 +1,3 @@
+{
+  "annotations": []
+}
\ No newline at end of file
diff --git a/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_09/15616458249936530.json b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_09/15616458249936530.json
new file mode 100644
index 00000000..408ceec1
--- /dev/null
+++ b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_09/15616458249936530.json
@@ -0,0 +1,82 @@
+{
+  "annotations": [
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.526,
+        "length": 4.588,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.510626950101513,
+            "qx": -0.5149086256931243,
+            "qy": 0.48081794500737773,
+            "qz": -0.49289281672157514
+          },
+          "translation": {
+            "x": 6.496073126167644,
+            "y": -0.19000261537121332,
+            "z": 140.2667667453279
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.048
+      },
+      "class_id": 2,
+      "instance_id": 497050057,
+      "num_points": 7
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 2.048,
+        "length": 4.542,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": 0.4927802725071928,
+            "qx": 0.49636663786461394,
+            "qy": 0.5074664777899055,
+            "qz": -0.5032549431075908
+          },
+          "translation": {
+            "x": 0.36808857684525265,
+            "y": 0.9251738487239436,
+            "z": 21.94803691434481
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.504
+      },
+      "class_id": 2,
+      "instance_id": 1545514913,
+      "num_points": 1341
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 2.0,
+        "length": 5.089,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.5083657579311281,
+            "qx": -0.5029377373290085,
+            "qy": 0.4829267506612237,
+            "qz": -0.5053707965734467
+          },
+          "translation": {
+            "x": 5.494641292804232,
+            "y": 0.8362237023932266,
+            "z": 103.38875661967359
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.493
+      },
+      "class_id": 2,
+      "instance_id": 1868710109,
+      "num_points": 12
+    }
+  ]
+}
\ No newline at end of file
diff --git a/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_09/15616458250936520.json b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_09/15616458250936520.json
new file mode 100644
index 00000000..cb8fba44
--- /dev/null
+++ b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_09/15616458250936520.json
@@ -0,0 +1,82 @@
+{
+  "annotations": [
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.526,
+        "length": 4.588,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.5110033758938265,
+            "qx": -0.5145069646936269,
+            "qy": 0.4803835672811857,
+            "qz": -0.49334547873986556
+          },
+          "translation": {
+            "x": 6.587505057119074,
+            "y": 0.0763385686213951,
+            "z": 143.04421770245926
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.048
+      },
+      "class_id": 2,
+      "instance_id": 497050057,
+      "num_points": 8
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 2.048,
+        "length": 4.542,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": 0.4963056322398272,
+            "qx": 0.4929351041320033,
+            "qy": 0.5062590305632801,
+            "qz": -0.5043783267494003
+          },
+          "translation": {
+            "x": 0.3444414355228247,
+            "y": 0.9716794761195615,
+            "z": 21.80972129868769
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.504
+      },
+      "class_id": 2,
+      "instance_id": 1545514913,
+      "num_points": 1389
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 2.0,
+        "length": 5.089,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.5087312309110361,
+            "qx": -0.5025377667773864,
+            "qy": 0.48248285467410124,
+            "qz": -0.5058246955257033
+          },
+          "translation": {
+            "x": 5.568406914071616,
+            "y": 1.0255390290080868,
+            "z": 106.24567205917538
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.493
+      },
+      "class_id": 2,
+      "instance_id": 1868710109,
+      "num_points": 17
+    }
+  ]
+}
\ No newline at end of file
diff --git a/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_09/15616458251936472.json b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_09/15616458251936472.json
new file mode 100644
index 00000000..03868359
--- /dev/null
+++ b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/CAMERA_09/15616458251936472.json
@@ -0,0 +1,82 @@
+{
+  "annotations": [
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.526,
+        "length": 4.588,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.5113636204288473,
+            "qx": -0.5140982950858334,
+            "qy": 0.48015003779819027,
+            "qz": -0.49362549761346286
+          },
+          "translation": {
+            "x": 6.672995694725429,
+            "y": 0.2916503562632897,
+            "z": 145.84531062152428
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.048
+      },
+      "class_id": 2,
+      "instance_id": 497050057,
+      "num_points": 11
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 2.048,
+        "length": 4.542,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": 0.49969560307001426,
+            "qx": 0.4896193049750717,
+            "qy": 0.5050215103046456,
+            "qz": -0.5055002617188625
+          },
+          "translation": {
+            "x": 0.318628403642208,
+            "y": 1.0065267573140773,
+            "z": 21.636380245882265
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.504
+      },
+      "class_id": 2,
+      "instance_id": 1545514913,
+      "num_points": 1411
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 2.0,
+        "length": 5.089,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.5090850396952281,
+            "qx": -0.5021296650849186,
+            "qy": 0.48223984199809233,
+            "qz": -0.5061056772946453
+          },
+          "translation": {
+            "x": 5.638415631753617,
+            "y": 1.178199992531745,
+            "z": 109.12765734907634
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.493
+      },
+      "class_id": 2,
+      "instance_id": 1868710109,
+      "num_points": 12
+    }
+  ]
+}
\ No newline at end of file
diff --git a/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/LIDAR/15616458250027900.json b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/LIDAR/15616458250027900.json
new file mode 100644
index 00000000..b2334515
--- /dev/null
+++ b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/LIDAR/15616458250027900.json
@@ -0,0 +1,342 @@
+{
+  "annotations": [
+    {
+      "attributes": {},
+      "box": {
+        "height": 2.535,
+        "length": 6.5809999999999995,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": 0.9997595245843511,
+            "qx": -0.011796705976182834,
+            "qy": 0.0063950714667915,
+            "qz": -0.01734456087420122
+          },
+          "translation": {
+            "x": 81.65145121268597,
+            "y": -0.10194900923829664,
+            "z": 2.8571381300696785
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.925
+      },
+      "class_id": 1,
+      "instance_id": 443946110,
+      "num_points": 190
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.526,
+        "length": 4.588,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.017323969936230088,
+            "qx": -0.006450643117770046,
+            "qy": -0.015001750579201764,
+            "qz": -0.9997165682074973
+          },
+          "translation": {
+            "x": -140.2143312938024,
+            "y": 4.272096955986058,
+            "z": 4.6217691616556635
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.048
+      },
+      "class_id": 2,
+      "instance_id": 497050057,
+      "num_points": 7
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.8780000000000001,
+        "length": 4.605,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.9822822496497678,
+            "qx": 0.0006012872284046553,
+            "qy": -0.011873938590447728,
+            "qz": -0.18703002448540557
+          },
+          "translation": {
+            "x": 28.029121113358087,
+            "y": 59.38059836733623,
+            "z": 2.722515277987
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.12
+      },
+      "class_id": 2,
+      "instance_id": 715214751,
+      "num_points": 1
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 2.048,
+        "length": 4.542,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": 0.9998685613568776,
+            "qx": -0.007044895414966162,
+            "qy": 0.014414877829238967,
+            "qz": -0.002332542794719006
+          },
+          "translation": {
+            "x": -21.857910325578814,
+            "y": 0.11974173075759609,
+            "z": 1.0674473309452992
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.504
+      },
+      "class_id": 2,
+      "instance_id": 1545514913,
+      "num_points": 1341
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 2.343,
+        "length": 6.236,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": 0.7280698407397354,
+            "qx": -0.01005839339450611,
+            "qy": 0.00041911527015593686,
+            "qz": -0.685429033576729
+          },
+          "translation": {
+            "x": 17.649988992246108,
+            "y": -17.24356762386833,
+            "z": 1.7026659926518306
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.747
+      },
+      "class_id": 2,
+      "instance_id": 1740587446,
+      "num_points": 3126
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.94,
+        "length": 4.276,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": 0.6445804388531142,
+            "qx": -0.014832522774785596,
+            "qy": -0.007172481739316183,
+            "qz": -0.7643589533862752
+          },
+          "translation": {
+            "x": -60.11799661699115,
+            "y": 79.25966132119754,
+            "z": 3.0702808718010246
+          }
+        },
+        "truncation": 0.0,
+        "width": 1.9060000000000001
+      },
+      "class_id": 2,
+      "instance_id": 1793247213,
+      "num_points": 0
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 2.0,
+        "length": 5.089,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.0028450651807097604,
+            "qx": 0.0034936742113693634,
+            "qy": -0.015094914866918085,
+            "qz": -0.9998759139962237
+          },
+          "translation": {
+            "x": -103.35439841583684,
+            "y": 3.8771678272361214,
+            "z": 2.8237101483989306
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.493
+      },
+      "class_id": 2,
+      "instance_id": 1868710109,
+      "num_points": 12
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.8780000000000001,
+        "length": 4.605,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.9822822496497678,
+            "qx": 0.0006012872284046553,
+            "qy": -0.011873938590447728,
+            "qz": -0.18703002448540557
+          },
+          "translation": {
+            "x": 35.048003103286646,
+            "y": 55.269874902976426,
+            "z": 2.902037452192218
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.12
+      },
+      "class_id": 2,
+      "instance_id": 2110970748,
+      "num_points": 0
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.8780000000000001,
+        "length": 4.605,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.5765007273122139,
+            "qx": -0.00439525827832565,
+            "qy": -0.026908650716228156,
+            "qz": -0.8166416090487846
+          },
+          "translation": {
+            "x": 44.97602359193206,
+            "y": 76.19868118456338,
+            "z": 1.8284701255447047
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.12
+      },
+      "class_id": 2,
+      "instance_id": 2556950328,
+      "num_points": 0
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.584,
+        "length": 4.588,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": 0.9902671505582219,
+            "qx": -0.004616985525206665,
+            "qy": 0.002982862166245057,
+            "qz": -0.13907104840065682
+          },
+          "translation": {
+            "x": 94.02996499255823,
+            "y": -2.354662748855162,
+            "z": 2.526512346342976
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.048
+      },
+      "class_id": 2,
+      "instance_id": 3215172593,
+      "num_points": 40
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.4969999999999999,
+        "length": 4.433,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.005534684056901218,
+            "qx": -0.0005146409377720929,
+            "qy": 0.009972891192122744,
+            "qz": -0.9999348198049541
+          },
+          "translation": {
+            "x": 70.582664648422,
+            "y": 4.18605059878405,
+            "z": 1.934261997337785
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.117
+      },
+      "class_id": 2,
+      "instance_id": 3357023490,
+      "num_points": 31
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 3.404,
+        "length": 8.859,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.9819429108289287,
+            "qx": 0.0031509310783181792,
+            "qy": -0.011428347079248644,
+            "qz": -0.18880567891138045
+          },
+          "translation": {
+            "x": 24.850070455509012,
+            "y": 61.771984869808875,
+            "z": 3.4576557479754726
+          }
+        },
+        "truncation": 0.0,
+        "width": 3.266
+      },
+      "class_id": 1,
+      "instance_id": 3527146084,
+      "num_points": 0
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.8780000000000001,
+        "length": 4.605,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.26228015573107977,
+            "qx": -0.0059829183571183785,
+            "qy": -0.028969936496766668,
+            "qz": -0.9645382664140323
+          },
+          "translation": {
+            "x": 26.361219900605192,
+            "y": 70.80889357854721,
+            "z": 3.3914413650132786
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.12
+      },
+      "class_id": 2,
+      "instance_id": 3668932913,
+      "num_points": 0
+    }
+  ]
+}
\ No newline at end of file
diff --git a/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/LIDAR/15616458251018358.json b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/LIDAR/15616458251018358.json
new file mode 100644
index 00000000..f3ec2fb1
--- /dev/null
+++ b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/LIDAR/15616458251018358.json
@@ -0,0 +1,342 @@
+{
+  "annotations": [
+    {
+      "attributes": {},
+      "box": {
+        "height": 2.535,
+        "length": 6.5809999999999995,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": 0.9998056582625341,
+            "qx": -0.007635264009049943,
+            "qy": 0.005473369111294217,
+            "qz": -0.017331782375318017
+          },
+          "translation": {
+            "x": 80.69873432533313,
+            "y": -0.11521452980355207,
+            "z": 2.992672327046421
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.925
+      },
+      "class_id": 1,
+      "instance_id": 443946110,
+      "num_points": 208
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.526,
+        "length": 4.588,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.017290622962113755,
+            "qx": -0.005602035997374068,
+            "qy": -0.015066085293856963,
+            "qz": -0.9997212934734288
+          },
+          "translation": {
+            "x": -142.98525967259366,
+            "y": 4.311714097269828,
+            "z": 4.408963987166089
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.048
+      },
+      "class_id": 2,
+      "instance_id": 497050057,
+      "num_points": 8
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.8780000000000001,
+        "length": 4.605,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.982283191624324,
+            "qx": 0.0008375504098016061,
+            "qy": -0.011056852275349787,
+            "qz": -0.18707425258277754
+          },
+          "translation": {
+            "x": 26.761804295217644,
+            "y": 59.383478758235015,
+            "z": 2.7588562831058425
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.12
+      },
+      "class_id": 2,
+      "instance_id": 715214751,
+      "num_points": 1
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 2.048,
+        "length": 4.542,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": 0.9999066381871451,
+            "qx": -0.009334825727109627,
+            "qy": 0.009737085636859509,
+            "qz": -0.0021829111817008306
+          },
+          "translation": {
+            "x": -21.70739294041914,
+            "y": 0.09756964605071516,
+            "z": 1.0177069285959988
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.504
+      },
+      "class_id": 2,
+      "instance_id": 1545514913,
+      "num_points": 1389
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 2.343,
+        "length": 6.236,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": 0.7281010566370028,
+            "qx": -0.009535322296594569,
+            "qy": -0.0002518349050302551,
+            "qz": -0.6854034326817762
+          },
+          "translation": {
+            "x": 16.391540076474485,
+            "y": -17.24181445089289,
+            "z": 1.7335023692523706
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.747
+      },
+      "class_id": 2,
+      "instance_id": 1740587446,
+      "num_points": 3539
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.94,
+        "length": 4.276,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": 0.6446085560967735,
+            "qx": -0.014235686720161598,
+            "qy": -0.007779168410795493,
+            "qz": -0.7643406564937364
+          },
+          "translation": {
+            "x": -61.38762429350572,
+            "y": 79.2543752252891,
+            "z": 2.954207446589905
+          }
+        },
+        "truncation": 0.0,
+        "width": 1.9060000000000001
+      },
+      "class_id": 2,
+      "instance_id": 1793247213,
+      "num_points": 0
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 2.0,
+        "length": 5.089,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.0028110119947967194,
+            "qx": 0.004341277045121877,
+            "qy": -0.015171059516490016,
+            "qz": -0.9998715369877927
+          },
+          "translation": {
+            "x": -106.20277958241695,
+            "y": 3.8991885273792377,
+            "z": 2.690975317250299
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.493
+      },
+      "class_id": 2,
+      "instance_id": 1868710109,
+      "num_points": 17
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.8780000000000001,
+        "length": 4.605,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.982283191624324,
+            "qx": 0.0008375504098016061,
+            "qy": -0.011056852275349787,
+            "qz": -0.18707425258277754
+          },
+          "translation": {
+            "x": 33.780754438690565,
+            "y": 55.27343822045623,
+            "z": 2.950912684359672
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.12
+      },
+      "class_id": 2,
+      "instance_id": 2110970748,
+      "num_points": 0
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.8780000000000001,
+        "length": 4.605,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.576485623131715,
+            "qx": -0.003657097138682411,
+            "qy": -0.026484970623930716,
+            "qz": -0.8166697608544148
+          },
+          "translation": {
+            "x": 43.70863250209095,
+            "y": 76.20300110842595,
+            "z": 1.8908634040087406
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.12
+      },
+      "class_id": 2,
+      "instance_id": 2556950328,
+      "num_points": 0
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.584,
+        "length": 4.588,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": 0.9874512632407924,
+            "qx": -0.005030832976660219,
+            "qy": 0.0016755644614559065,
+            "qz": -0.15783499588957178
+          },
+          "translation": {
+            "x": 93.2124823385584,
+            "y": -2.521613192837549,
+            "z": 2.6894724984837097
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.048
+      },
+      "class_id": 2,
+      "instance_id": 3215172593,
+      "num_points": 45
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.4969999999999999,
+        "length": 4.433,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.005479747730854134,
+            "qx": 0.000331529693236729,
+            "qy": 0.009802472262804288,
+            "qz": -0.999936885003452
+          },
+          "translation": {
+            "x": 68.2887887939105,
+            "y": 4.205092543559658,
+            "z": 2.004088643699774
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.117
+      },
+      "class_id": 2,
+      "instance_id": 3357023490,
+      "num_points": 39
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 3.404,
+        "length": 8.859,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.9819431921863968,
+            "qx": 0.0033886494619700357,
+            "qy": -0.010611569348107246,
+            "qz": -0.1888477666523602
+          },
+          "translation": {
+            "x": 23.581290806612742,
+            "y": 61.77468443182261,
+            "z": 3.4882350430095244
+          }
+        },
+        "truncation": 0.0,
+        "width": 3.266
+      },
+      "class_id": 1,
+      "instance_id": 3527146084,
+      "num_points": 1
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.8780000000000001,
+        "length": 4.605,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.2622601491748063,
+            "qx": -0.0051441635171359575,
+            "qy": -0.028824050158671843,
+            "qz": -0.96455291501761
+          },
+          "translation": {
+            "x": 25.091709815219474,
+            "y": 70.81172350293309,
+            "z": 3.4231562779591087
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.12
+      },
+      "class_id": 2,
+      "instance_id": 3668932913,
+      "num_points": 0
+    }
+  ]
+}
\ No newline at end of file
diff --git a/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/LIDAR/15616458252028828.json b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/LIDAR/15616458252028828.json
new file mode 100644
index 00000000..c0544d2a
--- /dev/null
+++ b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/bounding_box_3d/LIDAR/15616458252028828.json
@@ -0,0 +1,342 @@
+{
+  "annotations": [
+    {
+      "attributes": {},
+      "box": {
+        "height": 2.535,
+        "length": 6.5809999999999995,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": 0.9998333370202224,
+            "qx": -0.0031844023015159643,
+            "qy": 0.004888547333588338,
+            "qz": -0.017299129167596183
+          },
+          "translation": {
+            "x": 79.73384900473502,
+            "y": -0.12787212515945612,
+            "z": 3.072881183759229
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.925
+      },
+      "class_id": 1,
+      "instance_id": 443946110,
+      "num_points": 207
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.526,
+        "length": 4.588,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.017240523329003277,
+            "qx": -0.005091377056554247,
+            "qy": -0.014926566347134044,
+            "qz": -0.9997269826568133
+          },
+          "translation": {
+            "x": -145.80315832875885,
+            "y": 4.347755301631764,
+            "z": 4.289779777853482
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.048
+      },
+      "class_id": 2,
+      "instance_id": 497050057,
+      "num_points": 11
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.8780000000000001,
+        "length": 4.605,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.982278144652347,
+            "qx": 0.0008053065342827348,
+            "qy": -0.010529161621147247,
+            "qz": -0.18713133028781176
+          },
+          "translation": {
+            "x": 25.47502002845704,
+            "y": 59.38579856159845,
+            "z": 2.8011432379817833
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.12
+      },
+      "class_id": 2,
+      "instance_id": 715214751,
+      "num_points": 0
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 2.048,
+        "length": 4.542,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": 0.9999181252182221,
+            "qx": -0.011460283766955223,
+            "qy": 0.0053159700187135756,
+            "qz": -0.002035981045734936
+          },
+          "translation": {
+            "x": -21.547118185714226,
+            "y": 0.0742934572510876,
+            "z": 0.9850212640161189
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.504
+      },
+      "class_id": 2,
+      "instance_id": 1545514913,
+      "num_points": 1411
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 2.343,
+        "length": 6.236,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": 0.7281412078365146,
+            "qx": -0.009088845295078033,
+            "qy": -0.0005355176854917368,
+            "qz": -0.685366681100266
+          },
+          "translation": {
+            "x": 15.114571979048378,
+            "y": -17.240405591034232,
+            "z": 1.7450923989915452
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.747
+      },
+      "class_id": 2,
+      "instance_id": 1740587446,
+      "num_points": 3649
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.94,
+        "length": 4.276,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": 0.6446499863884391,
+            "qx": -0.013759286071331553,
+            "qy": -0.008010011030890935,
+            "qz": -0.7643120546082465
+          },
+          "translation": {
+            "x": -62.67683361705667,
+            "y": 79.24658887558508,
+            "z": 2.9113973251245966
+          }
+        },
+        "truncation": 0.0,
+        "width": 1.9060000000000001
+      },
+      "class_id": 2,
+      "instance_id": 1793247213,
+      "num_points": 0
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 2.0,
+        "length": 5.089,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.002762262340376187,
+            "qx": 0.004853914601955211,
+            "qy": -0.015038369690662547,
+            "qz": -0.9998713201491722
+          },
+          "translation": {
+            "x": -109.10038776179044,
+            "y": 3.919094921384044,
+            "z": 2.6268693813098167
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.493
+      },
+      "class_id": 2,
+      "instance_id": 1868710109,
+      "num_points": 12
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.8780000000000001,
+        "length": 4.605,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.982278144652347,
+            "qx": 0.0008053065342827348,
+            "qy": -0.010529161621147247,
+            "qz": -0.18713133028781176
+          },
+          "translation": {
+            "x": 32.49423958722673,
+            "y": 55.2765084221744,
+            "z": 2.9993132049770566
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.12
+      },
+      "class_id": 2,
+      "instance_id": 2110970748,
+      "num_points": 0
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.8780000000000001,
+        "length": 4.605,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.5764519996008381,
+            "qx": -0.003312810555209725,
+            "qy": -0.026082898781458752,
+            "qz": -0.8167079036188999
+          },
+          "translation": {
+            "x": 42.4208054871965,
+            "y": 76.20748063891801,
+            "z": 1.954917927571529
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.12
+      },
+      "class_id": 2,
+      "instance_id": 2556950328,
+      "num_points": 0
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.584,
+        "length": 4.588,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": 0.9842128575794213,
+            "qx": -0.005269888399949194,
+            "qy": 0.0007407291651478987,
+            "qz": -0.1769088199381459
+          },
+          "translation": {
+            "x": 92.37904055134823,
+            "y": -2.709527094645182,
+            "z": 2.7907741686254326
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.048
+      },
+      "class_id": 2,
+      "instance_id": 3215172593,
+      "num_points": 54
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.4969999999999999,
+        "length": 4.433,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.0054177598175843555,
+            "qx": 0.0008418931623845223,
+            "qy": 0.009838006883544158,
+            "qz": -0.9999365743461046
+          },
+          "translation": {
+            "x": 65.9551124616969,
+            "y": 4.225173295494187,
+            "z": 2.0243351221700863
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.117
+      },
+      "class_id": 2,
+      "instance_id": 3357023490,
+      "num_points": 53
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 3.404,
+        "length": 8.859,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.9819381501620765,
+            "qx": 0.0033573327521272435,
+            "qy": -0.010083674888694877,
+            "qz": -0.18890345966607286
+          },
+          "translation": {
+            "x": 22.293487678182828,
+            "y": 61.77645021030776,
+            "z": 3.5278898228923126
+          }
+        },
+        "truncation": 0.0,
+        "width": 3.266
+      },
+      "class_id": 1,
+      "instance_id": 3527146084,
+      "num_points": 0
+    },
+    {
+      "attributes": {},
+      "box": {
+        "height": 1.8780000000000001,
+        "length": 4.605,
+        "occlusion": 0,
+        "pose": {
+          "rotation": {
+            "qw": -0.2622191297838359,
+            "qx": -0.004682827700854757,
+            "qy": -0.02856363589936213,
+            "qz": -0.9645741639730676
+          },
+          "translation": {
+            "x": 23.80293937911756,
+            "y": 70.8136782441436,
+            "z": 3.4667258875275735
+          }
+        },
+        "truncation": 0.0,
+        "width": 2.12
+      },
+      "class_id": 2,
+      "instance_id": 3668932913,
+      "num_points": 0
+    }
+  ]
+}
\ No newline at end of file
diff --git a/tests/data/dgp/test_scene/scene_02/autolabels/test-model/ontology/16322f7584a52ca979ed1c7049f17a7e420e86b1.json b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/ontology/16322f7584a52ca979ed1c7049f17a7e420e86b1.json
new file mode 100644
index 00000000..ebd63b35
--- /dev/null
+++ b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/ontology/16322f7584a52ca979ed1c7049f17a7e420e86b1.json
@@ -0,0 +1,114 @@
+{
+  "items": [
+    {
+      "color": {
+        "b": 100,
+        "g": 60,
+        "r": 0
+      },
+      "id": 3,
+      "isthing": true,
+      "name": "Bus/RV/Caravan",
+      "supercategory": ""
+    },
+    {
+      "color": {
+        "b": 100,
+        "g": 80,
+        "r": 0
+      },
+      "id": 4,
+      "isthing": true,
+      "name": "Motorcycle",
+      "supercategory": ""
+    },
+    {
+      "color": {
+        "b": 30,
+        "g": 170,
+        "r": 250
+      },
+      "id": 5,
+      "isthing": true,
+      "name": "Wheeled Slow",
+      "supercategory": ""
+    },
+    {
+      "color": {
+        "b": 110,
+        "g": 0,
+        "r": 0
+      },
+      "id": 6,
+      "isthing": true,
+      "name": "Train",
+      "supercategory": ""
+    },
+    {
+      "color": {
+        "b": 142,
+        "g": 0,
+        "r": 0
+      },
+      "id": 7,
+      "isthing": true,
+      "name": "Towed Object",
+      "supercategory": ""
+    },
+    {
+      "color": {
+        "b": 230,
+        "g": 0,
+        "r": 0
+      },
+      "id": 8,
+      "isthing": true,
+      "name": "Bicycle",
+      "supercategory": ""
+    },
+    {
+      "color": {
+        "b": 90,
+        "g": 0,
+        "r": 0
+      },
+      "id": 9,
+      "isthing": true,
+      "name": "Trailer",
+      "supercategory": ""
+    },
+    {
+      "color": {
+        "b": 60,
+        "g": 20,
+        "r": 220
+      },
+      "id": 0,
+      "isthing": true,
+      "name": "Person",
+      "supercategory": ""
+    },
+    {
+      "color": {
+        "b": 70,
+        "g": 0,
+        "r": 0
+      },
+      "id": 1,
+      "isthing": true,
+      "name": "Truck",
+      "supercategory": ""
+    },
+    {
+      "color": {
+        "b": 142,
+        "g": 0,
+        "r": 0
+      },
+      "id": 2,
+      "isthing": true,
+      "name": "Car",
+      "supercategory": ""
+    }
+  ]
+}
\ No newline at end of file
diff --git a/tests/data/dgp/test_scene/scene_02/autolabels/test-model/scene.json b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/scene.json
new file mode 100644
index 00000000..64fe929c
--- /dev/null
+++ b/tests/data/dgp/test_scene/scene_02/autolabels/test-model/scene.json
@@ -0,0 +1,878 @@
+{
+  "data": [
+    {
+      "datum": {
+        "point_cloud": {
+          "annotations": {
+            "1": "bounding_box_3d/LIDAR/15616458250027900.json"
+          },
+          "filename": "point_cloud/LIDAR/15616458250027900.npz",
+          "metadata": {},
+          "point_fields": [],
+          "point_format": [
+            "X",
+            "Y",
+            "Z",
+            "INTENSITY"
+          ],
+          "pose": {
+            "reference_coordinate_system": "",
+            "rotation": {
+              "qw": -0.701507293064849,
+              "qx": -0.005770785693231001,
+              "qy": 0.015431988162520002,
+              "qz": 0.712471802635488
+            },
+            "translation": {
+              "x": 111.45486229951824,
+              "y": -2261.3842407442175,
+              "z": -12.733956682582992
+            }
+          }
+        }
+      },
+      "id": {
+        "index": "0",
+        "log": "TRI_INTERNAL_LOG",
+        "name": "LIDAR",
+        "timestamp": "2464-11-12T01:04:10.027900Z"
+      },
+      "key": "2504076f8a5d7b56696e5938eef364256281e804",
+      "next_key": "",
+      "prev_key": "8060ee6e11a59335baef639af9881f06276d86cf"
+    },
+    {
+      "datum": {
+        "image": {
+          "annotations": {
+            "0": "bounding_box_2d/CAMERA_01/15616458250027900.json",
+            "1": "bounding_box_3d/CAMERA_01/15616458249936530.json"
+          },
+          "channels": 3,
+          "filename": "rgb/CAMERA_01/15616458249936530.jpg",
+          "height": 1216,
+          "metadata": {},
+          "pose": {
+            "reference_coordinate_system": "",
+            "rotation": {
+              "qw": -0.026737673843549,
+              "qx": 0.010073240707172,
+              "qy": -0.7046769876230721,
+              "qz": 0.708952727432206
+            },
+            "translation": {
+              "x": 111.67133170999641,
+              "y": -2262.8032891568937,
+              "z": -11.14430549826587
+            }
+          },
+          "width": 1936
+        }
+      },
+      "id": {
+        "index": "0",
+        "log": "TRI_INTERNAL_LOG",
+        "name": "CAMERA_01",
+        "timestamp": "2464-11-12T01:04:09.936530Z"
+      },
+      "key": "2050436a0bed451c45a7cd3f0ab9cab2e9b5216f",
+      "next_key": "",
+      "prev_key": "94d2a825e7efb020bb6a79a4196003cee863e081"
+    },
+    {
+      "datum": {
+        "image": {
+          "annotations": {
+            "0": "bounding_box_2d/CAMERA_05/15616458250027900.json",
+            "1": "bounding_box_3d/CAMERA_05/15616458249936530.json"
+          },
+          "channels": 3,
+          "filename": "rgb/CAMERA_05/15616458249936530.jpg",
+          "height": 1216,
+          "metadata": {},
+          "pose": {
+            "reference_coordinate_system": "",
+            "rotation": {
+              "qw": -0.304385087431559,
+              "qx": 0.30227730504870104,
+              "qy": -0.6333704409210771,
+              "qz": 0.6440652404603241
+            },
+            "translation": {
+              "x": 111.8415099171323,
+              "y": -2262.8453927741903,
+              "z": -11.125282283208845
+            }
+          },
+          "width": 1936
+        }
+      },
+      "id": {
+        "index": "0",
+        "log": "TRI_INTERNAL_LOG",
+        "name": "CAMERA_05",
+        "timestamp": "2464-11-12T01:04:09.936530Z"
+      },
+      "key": "4eb3efc14eebf085905f15fd334e9ef3dcd152c1",
+      "next_key": "",
+      "prev_key": "c80ac79b82a10faf7c17a73307186576cec1a083"
+    },
+    {
+      "datum": {
+        "image": {
+          "annotations": {
+            "0": "bounding_box_2d/CAMERA_06/15616458250027900.json",
+            "1": "bounding_box_3d/CAMERA_06/15616458249936530.json"
+          },
+          "channels": 3,
+          "filename": "rgb/CAMERA_06/15616458249936530.jpg",
+          "height": 1216,
+          "metadata": {},
+          "pose": {
+            "reference_coordinate_system": "",
+            "rotation": {
+              "qw": 0.3094128061743,
+              "qx": -0.332425373787537,
+              "qy": -0.627460071821294,
+              "qz": 0.632495805920937
+            },
+            "translation": {
+              "x": 110.97219253292165,
+              "y": -2262.846122593118,
+              "z": -11.19356886200419
+            }
+          },
+          "width": 1936
+        }
+      },
+      "id": {
+        "index": "0",
+        "log": "TRI_INTERNAL_LOG",
+        "name": "CAMERA_06",
+        "timestamp": "2464-11-12T01:04:09.936530Z"
+      },
+      "key": "32bfe434973c7b3fa742ce955debafd211e97c57",
+      "next_key": "",
+      "prev_key": "9ad65962ecc8c367af4ae71ec2e8c71c89fdaa7e"
+    },
+    {
+      "datum": {
+        "image": {
+          "annotations": {
+            "0": "bounding_box_2d/CAMERA_07/15616458250027900.json",
+            "1": "bounding_box_3d/CAMERA_07/15616458249936530.json"
+          },
+          "channels": 3,
+          "filename": "rgb/CAMERA_07/15616458249936530.jpg",
+          "height": 1216,
+          "metadata": {},
+          "pose": {
+            "reference_coordinate_system": "",
+            "rotation": {
+              "qw": -0.617968419234546,
+              "qx": 0.623853853416071,
+              "qy": -0.332191776572331,
+              "qz": 0.344339986037626
+            },
+            "translation": {
+              "x": 111.81825645400964,
+              "y": -2262.4313553874504,
+              "z": -11.14427596300068
+            }
+          },
+          "width": 1936
+        }
+      },
+      "id": {
+        "index": "0",
+        "log": "TRI_INTERNAL_LOG",
+        "name": "CAMERA_07",
+        "timestamp": "2464-11-12T01:04:09.936530Z"
+      },
+      "key": "4fc6300299fb51341b4e521503ece5cd96443184",
+      "next_key": "",
+      "prev_key": "3dd01103bb34bbed9ec8b8210a4bca87adf7ee63"
+    },
+    {
+      "datum": {
+        "image": {
+          "annotations": {
+            "0": "bounding_box_2d/CAMERA_08/15616458250027900.json",
+            "1": "bounding_box_3d/CAMERA_08/15616458249936530.json"
+          },
+          "channels": 3,
+          "filename": "rgb/CAMERA_08/15616458249936530.jpg",
+          "height": 1216,
+          "metadata": {},
+          "pose": {
+            "reference_coordinate_system": "",
+            "rotation": {
+              "qw": -0.6196394552156801,
+              "qx": 0.6370433227734571,
+              "qy": 0.33247468256698504,
+              "qz": -0.315726679109874
+            },
+            "translation": {
+              "x": 110.93134665409706,
+              "y": -2262.4099494070624,
+              "z": -11.17953434223646
+            }
+          },
+          "width": 1936
+        }
+      },
+      "id": {
+        "index": "0",
+        "log": "TRI_INTERNAL_LOG",
+        "name": "CAMERA_08",
+        "timestamp": "2464-11-12T01:04:09.936530Z"
+      },
+      "key": "af8ef5088767a54a6b88266b9109ecaf44009497",
+      "next_key": "",
+      "prev_key": "9f5103c7c965103cfc9084c7f3a12ce0643c43fa"
+    },
+    {
+      "datum": {
+        "image": {
+          "annotations": {
+            "0": "bounding_box_2d/CAMERA_09/15616458250027900.json",
+            "1": "bounding_box_3d/CAMERA_09/15616458249936530.json"
+          },
+          "channels": 3,
+          "filename": "rgb/CAMERA_09/15616458249936530.jpg",
+          "height": 1216,
+          "metadata": {},
+          "pose": {
+            "reference_coordinate_system": "",
+            "rotation": {
+              "qw": -0.709680353959914,
+              "qx": 0.704472865391225,
+              "qy": 0.006552993865234001,
+              "qz": 0.005369860539106
+            },
+            "translation": {
+              "x": 111.54045551661851,
+              "y": -2261.47283021645,
+              "z": -11.199511108285467
+            }
+          },
+          "width": 1936
+        }
+      },
+      "id": {
+        "index": "0",
+        "log": "TRI_INTERNAL_LOG",
+        "name": "CAMERA_09",
+        "timestamp": "2464-11-12T01:04:09.936530Z"
+      },
+      "key": "bf5b106fcbb34d0a6949c968e0c091243624df6c",
+      "next_key": "",
+      "prev_key": "0065274b90ef246ad3d72bd972fd5825da40d097"
+    },
+    {
+      "datum": {
+        "point_cloud": {
+          "annotations": {
+            "1": "bounding_box_3d/LIDAR/15616458251018358.json"
+          },
+          "filename": "point_cloud/LIDAR/15616458251018358.npz",
+          "metadata": {},
+          "point_fields": [],
+          "point_format": [
+            "X",
+            "Y",
+            "Z",
+            "INTENSITY"
+          ],
+          "pose": {
+            "reference_coordinate_system": "",
+            "rotation": {
+              "qw": -0.7014864755837661,
+              "qx": -0.00643004157145,
+              "qy": 0.014893784037226002,
+              "qz": 0.712498108303108
+            },
+            "translation": {
+              "x": 111.43516925360107,
+              "y": -2262.6411226813084,
+              "z": -12.71743392922662
+            }
+          }
+        }
+      },
+      "id": {
+        "index": "0",
+        "log": "TRI_INTERNAL_LOG",
+        "name": "LIDAR",
+        "timestamp": "2464-11-12T01:04:11.018358Z"
+      },
+      "key": "6a1eca098cb729b63fabd775f7664bbc270b2c8c",
+      "next_key": "",
+      "prev_key": "2504076f8a5d7b56696e5938eef364256281e804"
+    },
+    {
+      "datum": {
+        "image": {
+          "annotations": {
+            "0": "bounding_box_2d/CAMERA_01/15616458251018358.json",
+            "1": "bounding_box_3d/CAMERA_01/15616458250936520.json"
+          },
+          "channels": 3,
+          "filename": "rgb/CAMERA_01/15616458250936520.jpg",
+          "height": 1216,
+          "metadata": {},
+          "pose": {
+            "reference_coordinate_system": "",
+            "rotation": {
+              "qw": -0.026774750057927003,
+              "qx": 0.009995531443067,
+              "qy": -0.7053335342727101,
+              "qz": 0.708299235874834
+            },
+            "translation": {
+              "x": 111.65115147537942,
+              "y": -2264.0764362556565,
+              "z": -11.130321693139923
+            }
+          },
+          "width": 1936
+        }
+      },
+      "id": {
+        "index": "0",
+        "log": "TRI_INTERNAL_LOG",
+        "name": "CAMERA_01",
+        "timestamp": "2464-11-12T01:04:10.936520Z"
+      },
+      "key": "64a846ff4118412e81e71689e140859e3038e00f",
+      "next_key": "",
+      "prev_key": "2050436a0bed451c45a7cd3f0ab9cab2e9b5216f"
+    },
+    {
+      "datum": {
+        "image": {
+          "annotations": {
+            "0": "bounding_box_2d/CAMERA_05/15616458251018358.json",
+            "1": "bounding_box_3d/CAMERA_05/15616458250936520.json"
+          },
+          "channels": 3,
+          "filename": "rgb/CAMERA_05/15616458250936520.jpg",
+          "height": 1216,
+          "metadata": {},
+          "pose": {
+            "reference_coordinate_system": "",
+            "rotation": {
+              "qw": -0.304677122099694,
+              "qx": 0.30196144677311604,
+              "qy": -0.6339263086851411,
+              "qz": 0.643528220895218
+            },
+            "translation": {
+              "x": 111.82133902289591,
+              "y": -2264.118246897645,
+              "z": -11.111145214502097
+            }
+          },
+          "width": 1936
+        }
+      },
+      "id": {
+        "index": "0",
+        "log": "TRI_INTERNAL_LOG",
+        "name": "CAMERA_05",
+        "timestamp": "2464-11-12T01:04:10.936520Z"
+      },
+      "key": "eda53e13e84fab57889d88081cee537b28d75776",
+      "next_key": "",
+      "prev_key": "4eb3efc14eebf085905f15fd334e9ef3dcd152c1"
+    },
+    {
+      "datum": {
+        "image": {
+          "annotations": {
+            "0": "bounding_box_2d/CAMERA_06/15616458251018358.json",
+            "1": "bounding_box_3d/CAMERA_06/15616458250936520.json"
+          },
+          "channels": 3,
+          "filename": "rgb/CAMERA_06/15616458250936520.jpg",
+          "height": 1216,
+          "metadata": {},
+          "pose": {
+            "reference_coordinate_system": "",
+            "rotation": {
+              "qw": 0.30967404609688803,
+              "qx": -0.33220455505097,
+              "qy": -0.6280240148569091,
+              "qz": 0.631924010890849
+            },
+            "translation": {
+              "x": 110.9520243320044,
+              "y": -2264.1187325313654,
+              "z": -11.179486642300796
+            }
+          },
+          "width": 1936
+        }
+      },
+      "id": {
+        "index": "0",
+        "log": "TRI_INTERNAL_LOG",
+        "name": "CAMERA_06",
+        "timestamp": "2464-11-12T01:04:10.936520Z"
+      },
+      "key": "7206c564c1c632fdc60932f770df2b2f39ab3d89",
+      "next_key": "",
+      "prev_key": "32bfe434973c7b3fa742ce955debafd211e97c57"
+    },
+    {
+      "datum": {
+        "image": {
+          "annotations": {
+            "0": "bounding_box_2d/CAMERA_07/15616458251018358.json",
+            "1": "bounding_box_3d/CAMERA_07/15616458250936520.json"
+          },
+          "channels": 3,
+          "filename": "rgb/CAMERA_07/15616458250936520.jpg",
+          "height": 1216,
+          "metadata": {},
+          "pose": {
+            "reference_coordinate_system": "",
+            "rotation": {
+              "qw": -0.618520137138158,
+              "qx": 0.6232952963257811,
+              "qy": -0.33245695479931403,
+              "qz": 0.34410490658855203
+            },
+            "translation": {
+              "x": 111.79808958346497,
+              "y": -2263.7039955716764,
+              "z": -11.129326471836738
+            }
+          },
+          "width": 1936
+        }
+      },
+      "id": {
+        "index": "0",
+        "log": "TRI_INTERNAL_LOG",
+        "name": "CAMERA_07",
+        "timestamp": "2464-11-12T01:04:10.936520Z"
+      },
+      "key": "4cef12c4be4f9b76da8538fb6c15fe15c51acdce",
+      "next_key": "",
+      "prev_key": "4fc6300299fb51341b4e521503ece5cd96443184"
+    },
+    {
+      "datum": {
+        "image": {
+          "annotations": {
+            "0": "bounding_box_2d/CAMERA_08/15616458251018358.json",
+            "1": "bounding_box_3d/CAMERA_08/15616458250936520.json"
+          },
+          "channels": 3,
+          "filename": "rgb/CAMERA_08/15616458250936520.jpg",
+          "height": 1216,
+          "metadata": {},
+          "pose": {
+            "reference_coordinate_system": "",
+            "rotation": {
+              "qw": -0.620160169948729,
+              "qx": 0.636545648740605,
+              "qy": 0.33277500386061104,
+              "qz": -0.31539149875057504
+            },
+            "translation": {
+              "x": 110.91117928567564,
+              "y": -2263.682402085488,
+              "z": -11.164628196562553
+            }
+          },
+          "width": 1936
+        }
+      },
+      "id": {
+        "index": "0",
+        "log": "TRI_INTERNAL_LOG",
+        "name": "CAMERA_08",
+        "timestamp": "2464-11-12T01:04:10.936520Z"
+      },
+      "key": "4db70de2e8393ae3207420c968d4fd13abdb2ea7",
+      "next_key": "",
+      "prev_key": "af8ef5088767a54a6b88266b9109ecaf44009497"
+    },
+    {
+      "datum": {
+        "image": {
+          "annotations": {
+            "0": "bounding_box_2d/CAMERA_09/15616458251018358.json",
+            "1": "bounding_box_3d/CAMERA_09/15616458250936520.json"
+          },
+          "channels": 3,
+          "filename": "rgb/CAMERA_09/15616458250936520.jpg",
+          "height": 1216,
+          "metadata": {},
+          "pose": {
+            "reference_coordinate_system": "",
+            "rotation": {
+              "qw": -0.710265070013237,
+              "qx": 0.703882456647782,
+              "qy": 0.0065910385216740005,
+              "qz": 0.005438359475007
+            },
+            "translation": {
+              "x": 111.52031208454802,
+              "y": -2262.7451226658845,
+              "z": -11.182913851994364
+            }
+          },
+          "width": 1936
+        }
+      },
+      "id": {
+        "index": "0",
+        "log": "TRI_INTERNAL_LOG",
+        "name": "CAMERA_09",
+        "timestamp": "2464-11-12T01:04:10.936520Z"
+      },
+      "key": "b317cef1289e1cdc63c078a42cbf73330dd8a220",
+      "next_key": "",
+      "prev_key": "bf5b106fcbb34d0a6949c968e0c091243624df6c"
+    },
+    {
+      "datum": {
+        "point_cloud": {
+          "annotations": {
+            "1": "bounding_box_3d/LIDAR/15616458252028828.json"
+          },
+          "filename": "point_cloud/LIDAR/15616458252028828.npz",
+          "metadata": {},
+          "point_fields": [],
+          "point_format": [
+            "X",
+            "Y",
+            "Z",
+            "INTENSITY"
+          ],
+          "pose": {
+            "reference_coordinate_system": "",
+            "rotation": {
+              "qw": -0.701454166681016,
+              "qx": -0.006703930351764,
+              "qy": 0.014440759943522001,
+              "qz": 0.712536717521232
+            },
+            "translation": {
+              "x": 111.41493320146672,
+              "y": -2263.918036624573,
+              "z": -12.703077512164834
+            }
+          }
+        }
+      },
+      "id": {
+        "index": "0",
+        "log": "TRI_INTERNAL_LOG",
+        "name": "LIDAR",
+        "timestamp": "2464-11-12T01:04:12.028828Z"
+      },
+      "key": "2ba9c5c623ce0537e1dcc6856e1d151605c027b6",
+      "next_key": "",
+      "prev_key": "6a1eca098cb729b63fabd775f7664bbc270b2c8c"
+    },
+    {
+      "datum": {
+        "image": {
+          "annotations": {
+            "0": "bounding_box_2d/CAMERA_01/15616458252028828.json",
+            "1": "bounding_box_3d/CAMERA_01/15616458251936472.json"
+          },
+          "channels": 3,
+          "filename": "rgb/CAMERA_01/15616458251936472.jpg",
+          "height": 1216,
+          "metadata": {},
+          "pose": {
+            "reference_coordinate_system": "",
+            "rotation": {
+              "qw": -0.026675419764756,
+              "qx": 0.010024900157219001,
+              "qy": -0.70577839400566,
+              "qz": 0.7078592952783781
+            },
+            "translation": {
+              "x": 111.63133595400431,
+              "y": -2265.342786954348,
+              "z": -11.117845347784975
+            }
+          },
+          "width": 1936
+        }
+      },
+      "id": {
+        "index": "0",
+        "log": "TRI_INTERNAL_LOG",
+        "name": "CAMERA_01",
+        "timestamp": "2464-11-12T01:04:11.936472Z"
+      },
+      "key": "2f81ddf658a5ecfcc074620be3af04387a9d217a",
+      "next_key": "",
+      "prev_key": "64a846ff4118412e81e71689e140859e3038e00f"
+    },
+    {
+      "datum": {
+        "image": {
+          "annotations": {
+            "0": "bounding_box_2d/CAMERA_05/15616458252028828.json",
+            "1": "bounding_box_3d/CAMERA_05/15616458251936472.json"
+          },
+          "channels": 3,
+          "filename": "rgb/CAMERA_05/15616458251936472.jpg",
+          "height": 1216,
+          "metadata": {},
+          "pose": {
+            "reference_coordinate_system": "",
+            "rotation": {
+              "qw": -0.304783099080413,
+              "qx": 0.30180208204338504,
+              "qy": -0.6343991496178041,
+              "qz": 0.6430866852559021
+            },
+            "translation": {
+              "x": 111.80153618508534,
+              "y": -2265.3845471652303,
+              "z": -11.099000777534684
+            }
+          },
+          "width": 1936
+        }
+      },
+      "id": {
+        "index": "0",
+        "log": "TRI_INTERNAL_LOG",
+        "name": "CAMERA_05",
+        "timestamp": "2464-11-12T01:04:11.936472Z"
+      },
+      "key": "0f2578fcd12c338705d82988925ad4511a8356b5",
+      "next_key": "",
+      "prev_key": "eda53e13e84fab57889d88081cee537b28d75776"
+    },
+    {
+      "datum": {
+        "image": {
+          "annotations": {
+            "0": "bounding_box_2d/CAMERA_06/15616458252028828.json",
+            "1": "bounding_box_3d/CAMERA_06/15616458251936472.json"
+          },
+          "channels": 3,
+          "filename": "rgb/CAMERA_06/15616458251936472.jpg",
+          "height": 1216,
+          "metadata": {},
+          "pose": {
+            "reference_coordinate_system": "",
+            "rotation": {
+              "qw": 0.309987527744137,
+              "qx": -0.33195720855035404,
+              "qy": -0.6283936398342991,
+              "qz": 0.631532721044867
+            },
+            "translation": {
+              "x": 110.93221003423827,
+              "y": -2265.384813908222,
+              "z": -11.16714772320681
+            }
+          },
+          "width": 1936
+        }
+      },
+      "id": {
+        "index": "0",
+        "log": "TRI_INTERNAL_LOG",
+        "name": "CAMERA_06",
+        "timestamp": "2464-11-12T01:04:11.936472Z"
+      },
+      "key": "eb36c947c983949e32bc50a9e38aa8a8fe036584",
+      "next_key": "",
+      "prev_key": "7206c564c1c632fdc60932f770df2b2f39ab3d89"
+    },
+    {
+      "datum": {
+        "image": {
+          "annotations": {
+            "0": "bounding_box_2d/CAMERA_07/15616458252028828.json",
+            "1": "bounding_box_3d/CAMERA_07/15616458251936472.json"
+          },
+          "channels": 3,
+          "filename": "rgb/CAMERA_07/15616458251936472.jpg",
+          "height": 1216,
+          "metadata": {},
+          "pose": {
+            "reference_coordinate_system": "",
+            "rotation": {
+              "qw": -0.618877810650446,
+              "qx": 0.622913884040137,
+              "qy": -0.33277598314642404,
+              "qz": 0.34384399601486504
+            },
+            "translation": {
+              "x": 111.77832256401882,
+              "y": -2264.9702317077117,
+              "z": -11.116621266239243
+            }
+          },
+          "width": 1936
+        }
+      },
+      "id": {
+        "index": "0",
+        "log": "TRI_INTERNAL_LOG",
+        "name": "CAMERA_07",
+        "timestamp": "2464-11-12T01:04:11.936472Z"
+      },
+      "key": "1fd26abfd6801edfd2c64579ae550036cdaa88b9",
+      "next_key": "",
+      "prev_key": "4cef12c4be4f9b76da8538fb6c15fe15c51acdce"
+    },
+    {
+      "datum": {
+        "image": {
+          "annotations": {
+            "0": "bounding_box_2d/CAMERA_08/15616458252028828.json",
+            "1": "bounding_box_3d/CAMERA_08/15616458251936472.json"
+          },
+          "channels": 3,
+          "filename": "rgb/CAMERA_08/15616458251936472.jpg",
+          "height": 1216,
+          "metadata": {},
+          "pose": {
+            "reference_coordinate_system": "",
+            "rotation": {
+              "qw": -0.62062401872633,
+              "qx": 0.63612085305801,
+              "qy": 0.33288504546921105,
+              "qz": -0.31521997745652003
+            },
+            "translation": {
+              "x": 110.89140981083308,
+              "y": -2264.9484598446957,
+              "z": -11.151696087757145
+            }
+          },
+          "width": 1936
+        }
+      },
+      "id": {
+        "index": "0",
+        "log": "TRI_INTERNAL_LOG",
+        "name": "CAMERA_08",
+        "timestamp": "2464-11-12T01:04:11.936472Z"
+      },
+      "key": "1b2423efc6db20a327001e736dd84f105dc84490",
+      "next_key": "",
+      "prev_key": "4db70de2e8393ae3207420c968d4fd13abdb2ea7"
+    },
+    {
+      "datum": {
+        "image": {
+          "annotations": {
+            "0": "bounding_box_2d/CAMERA_09/15616458252028828.json",
+            "1": "bounding_box_3d/CAMERA_09/15616458251936472.json"
+          },
+          "channels": 3,
+          "filename": "rgb/CAMERA_09/15616458251936472.jpg",
+          "height": 1216,
+          "metadata": {},
+          "pose": {
+            "reference_coordinate_system": "",
+            "rotation": {
+              "qw": -0.710719106131501,
+              "qx": 0.7034254011586331,
+              "qy": 0.006478693661622001,
+              "qz": 0.005392931753123001
+            },
+            "translation": {
+              "x": 111.50062155906006,
+              "y": -2264.011060010517,
+              "z": -11.16890673407187
+            }
+          },
+          "width": 1936
+        }
+      },
+      "id": {
+        "index": "0",
+        "log": "TRI_INTERNAL_LOG",
+        "name": "CAMERA_09",
+        "timestamp": "2464-11-12T01:04:11.936472Z"
+      },
+      "key": "5f940a623ba7fe7f109b929e4ce4a7d265165705",
+      "next_key": "",
+      "prev_key": "b317cef1289e1cdc63c078a42cbf73330dd8a220"
+    }
+  ],
+  "description": "DGP scene for unittest.",
+  "log": "TRI_INTERNAL_LOG",
+  "metadata": {},
+  "name": "",
+  "ontologies": {
+    "0": "16322f7584a52ca979ed1c7049f17a7e420e86b1",
+    "1": "16322f7584a52ca979ed1c7049f17a7e420e86b1"
+  },
+  "samples": [
+    {
+      "calibration_key": "64b9fde6360457d8beddcfb06c512fec6e2989d8",
+      "datum_keys": [
+        "2504076f8a5d7b56696e5938eef364256281e804",
+        "2050436a0bed451c45a7cd3f0ab9cab2e9b5216f",
+        "4eb3efc14eebf085905f15fd334e9ef3dcd152c1",
+        "32bfe434973c7b3fa742ce955debafd211e97c57",
+        "4fc6300299fb51341b4e521503ece5cd96443184",
+        "af8ef5088767a54a6b88266b9109ecaf44009497",
+        "bf5b106fcbb34d0a6949c968e0c091243624df6c"
+      ],
+      "id": {
+        "index": "0",
+        "log": "TRI_INTERNAL_LOG",
+        "name": "",
+        "timestamp": "2464-11-12T01:04:10.027900Z"
+      },
+      "metadata": {}
+    },
+    {
+      "calibration_key": "64b9fde6360457d8beddcfb06c512fec6e2989d8",
+      "datum_keys": [
+        "6a1eca098cb729b63fabd775f7664bbc270b2c8c",
+        "64a846ff4118412e81e71689e140859e3038e00f",
+        "eda53e13e84fab57889d88081cee537b28d75776",
+        "7206c564c1c632fdc60932f770df2b2f39ab3d89",
+        "4cef12c4be4f9b76da8538fb6c15fe15c51acdce",
+        "4db70de2e8393ae3207420c968d4fd13abdb2ea7",
+        "b317cef1289e1cdc63c078a42cbf73330dd8a220"
+      ],
+      "id": {
+        "index": "0",
+        "log": "TRI_INTERNAL_LOG",
+        "name": "",
+        "timestamp": "2464-11-12T01:04:11.018358Z"
+      },
+      "metadata": {}
+    },
+    {
+      "calibration_key": "64b9fde6360457d8beddcfb06c512fec6e2989d8",
+      "datum_keys": [
+        "2ba9c5c623ce0537e1dcc6856e1d151605c027b6",
+        "2f81ddf658a5ecfcc074620be3af04387a9d217a",
+        "0f2578fcd12c338705d82988925ad4511a8356b5",
+        "eb36c947c983949e32bc50a9e38aa8a8fe036584",
+        "1fd26abfd6801edfd2c64579ae550036cdaa88b9",
+        "1b2423efc6db20a327001e736dd84f105dc84490",
+        "5f940a623ba7fe7f109b929e4ce4a7d265165705"
+      ],
+      "id": {
+        "index": "0",
+        "log": "TRI_INTERNAL_LOG",
+        "name": "",
+        "timestamp": "2464-11-12T01:04:12.028828Z"
+      },
+      "metadata": {}
+    }
+  ]
+}
\ No newline at end of file
diff --git a/tests/utils/test_render_3d_to_2d.py b/tests/utils/test_render_3d_to_2d.py
new file mode 100644
index 00000000..fc51e3e7
--- /dev/null
+++ b/tests/utils/test_render_3d_to_2d.py
@@ -0,0 +1,37 @@
+# Copyright 2023 Woven by Toyota.  All rights reserved.
+"""Unit test to merge dgp datasets."""
+import logging
+import os
+import tempfile
+import unittest
+import unittest.mock as mock
+
+import dgp.utils.render_3d_to_2d as render_engine
+from tests import TEST_DATA_DIR
+
+SCENE_JSON = 'scene_6245881cb04e9f71ae6de99064e771dfa370329d.json'
+
+
+class TestAssociateDGP3dto2d(unittest.TestCase):
+    logging.getLogger().setLevel(logging.INFO)
+
+    def test_associate_scene(self):
+        """Verifies the target bounding box can be associated successfully."""
+        # answer = gt_engine.associate_3d_and_2d_annotations_scene(scene_json=os.path.join(TEST_DATA_DIR,'dgp/test_scene/scene_03', SCENE_JSON))
+        answer = render_engine.associate_3d_and_2d_annotations_scene(
+            scene_json=os.path.join(TEST_DATA_DIR, 'dgp/associate_2d_to_3d_scene/scene_01', SCENE_JSON),
+            camera_datum_names=render_engine.FRONT_CAMERA,
+            lidar_datum_names=render_engine.LIDAR,
+        )
+        assert render_engine.FRONT_CAMERA[0] in answer
+        for class_name in render_engine.ONTOLOGY_NAME_MAPPER_2D_to_3D.keys():
+            if class_name == "Pedestrian":
+                assert len(answer[render_engine.FRONT_CAMERA[0]][class_name]) == 4
+            elif class_name == "Car":
+                assert len(answer[render_engine.FRONT_CAMERA[0]][class_name]) == 0
+            else:
+                raise RuntimeError('Unexpected class_name {}'.format(class_name))
+
+
+if __name__ == "__main__":
+    unittest.main()