From 348699b84042eda21fe2c7cfa05ff1af8a2c63d5 Mon Sep 17 00:00:00 2001 From: R Srinath <47494475+srinath1412001@users.noreply.github.com> Date: Sun, 13 Aug 2023 22:04:33 +0530 Subject: [PATCH] Create index.html --- index.html | 554 +++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 554 insertions(+) create mode 100644 index.html diff --git a/index.html b/index.html new file mode 100644 index 0000000..d8b3e62 --- /dev/null +++ b/index.html @@ -0,0 +1,554 @@ + + + + + + + + Strata-NeRF: Neural Radiance Fields for Stratified Scenes + + + + + + + + + + + + + + + + + + + + + + + +
+
+
+
+
+

Strata-NeRF: Neural Radiance Fields for Stratified Scenes

+
+ + Ankit Dhiman1,2, + + R Srinath1, + + Harsh Rangwani1, + + + Rishubh Parihar1, + + + Lokesh R Boregowda2, + + + Srinath Sridhar3, + + + R Venkatesh Babu1 + +
+ +
+ 1Vision and AI Lab, IISc Bangalore, + 2Samsung R&D Institute, Bangalore, + 3Brown University +
+ +
+
+ + + + + + + Paper + + + + + + + + arXiv + + + + + + + + + Video + + + + + + + + + Code + + + + + + + + + Data + +
+ +
+
+
+
+
+
+ + +
+
+ +
+
+

Abstract

+
+

+ Neural Radiance Field (NeRF) approaches learn the un- + derlying 3D representation of a scene and generate photo- + realistic novel views with high fidelity. However, most pro- + posed settings concentrate on modelling a single object or + a single level of a scene. However, in the real world, we + may capture a scene at multiple levels, resulting in a lay- + ered capture. For example, tourists usually capture a mon- + ument’s exterior structure before capturing the inner struc- + ture. Modelling such scenes in 3D with seamless switch- + ing between levels can drastically improve immersive ex- + periences. However, most existing techniques struggle in + modelling such scenes. We propose Strata-NeRF, a single + neural radiance field that implicitly captures a scene with + multiple levels. Strata-NeRF achieves this by condition- + ing the NeRFs on Vector Quantized (VQ) latent represen- + tations which allow sudden changes in scene structure. We + evaluate the effectiveness of our approach in multi-layered + synthetic dataset comprising diverse scenes and then fur- + ther validate its generalization on the real-world RealEstate + 10k dataset. We find that Strata-NeRF effectively captures + stratified scenes, minimizes artifacts, and synthesizes high- + fidelity views compared to existing approaches. +

+
+
+
+ + + +
+
+

Video

+
+ +
+
+
+ +
+
+ +
+
+
+
+

Novel Views from RealEstate10K

+ Double click on the videos to view full-screen. +

+

+

7 Rutledge Ave Highland Mills

+ + + + + + + + + + + + + + + + + + + + + + +
+

Mip-NeRF 360

+
+ +
+ + 		+

Strata-NeRF

+
+ +
+ +
+
+ +
+ + 		+
+ +
+ +
+
+ +
+ + 		+
+ +
+ +
+
+ +
+ + 		+
+ +
+ +
+
+ +
+ + 		+
+ +
+ +
+ +
+
+
+ +
+
+
+
+

Novel Views from Synthetic Dataset

+ Comparison between Ground Truth, Mip-NeRF 360 and Strata-NeRF (Ours). +

+

+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
+

+

+

Cube-Sphere-Monkey

+
+ +
+
+

+

+

Level 0

+
+ +
+
+

+

+

Level 1

+
+ +
+
+

+

+

Level 2

+
+ +
+
+

+

+

Dragon in Pyramid

+ +
+ +
+
+

+

+

Level 0

+
+ +
+
+

+

+

Level 1

+
+ +
+
+

+

+

Buddhist Temple

+ +
+ +
+
+

+

+

Level 0

+ +
+ +
+
+

+

+

Level 1

+
+ +
+
+

+

+

Level 2

+
+ +
+
+

+

+

Coffee Shop

+ +
+ +
+
+

+

+

Level 0

+
+ +
+
+

+

+

Level 1

+
+ +
+
+

+

+

Level 2

+
+ +
+
+ +
+
+
+ + +
+
+

BibTeX

+ 
@article{park2021nerfies,
+  author    = {Park, Keunhong and Sinha, Utkarsh and Barron, Jonathan T. and Bouaziz, Sofien and Goldman, Dan B and Seitz, Steven M. and Martin-Brualla, Ricardo},
+  title     = {Nerfies: Deformable Neural Radiance Fields},
+  journal   = {ICCV},
+  year      = {2021},
+}
+
+
+ + + + + +