Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

通过Inference.py里的Inferencer推理自己的rgb和depth,得到的恢复深度畸变严重 #26

Open
Jingranxia opened this issue Sep 24, 2024 · 4 comments

Comments

@Jingranxia
Copy link

image
作者您好,感谢您的工作,我使用 kernel size=1的 模型权重进行推理,通过D435相机保存rgb与depth,其中depth = depth / 1000.0 ,出现了上面那种情况,其中可视化程序是
rgbd = o3d.geometry.RGBDImage.create_from_color_and_depth(o3d_rgb, o3d_depth, convert_rgb_to_intensity=False)
pinhole_camera_intrinsic = o3d.camera.PinholeCameraIntrinsic(intrinsics.width, intrinsics.height,
intrinsics.fx, intrinsics.fy,
intrinsics.ppx, intrinsics.ppy)
cloud = o3d.geometry.PointCloud.create_from_rgbd_image(rgbd, pinhole_camera_intrinsic,
project_valid_depth_only=False)
内参使用的是我的相机的内参,这样会对您的深度图的结果有何影响吗?

@Jingranxia
Copy link
Author

0030
RGB图

@Jingranxia
Copy link
Author

Uploading image.png…

@Jingranxia
Copy link
Author

refine_depth = inferencer.inference(color_image, depth_image, target_size=(640, 480))

@Galaxies99
Copy link
Owner

Galaxies99 commented Sep 24, 2024

您好!能提供一下其他角度的图片吗,这个角度这些畸变看得不太明显。您的代码应该没问题。

由于跟训练数据在不同的domain,对于新场景的补全效果确实会受到一定影响,不过可能对后续的抓取的影响不大。如果需要效果更佳的模型,可以考虑在应用domain内采集少量的数据进行finetune。

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants