-
Notifications
You must be signed in to change notification settings - Fork 1
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
Reprojection of 3D keypoints #3
Comments
Have you solved the problem? Looking forward to your reply. Thanks! |
Hi @luoxue-star, |
Hi! @mshooter May I ask how you performed the projection? The JSON annotation files provided by the authors do not include camera intrinsic parameters. When I set empirical values for projection, they do not align with the images. I'm looking forward to your response! Thank you! |
Hi @ShirleyMaxx I have not been able to do so. |
`def projection(points, k): data = read_json_file(path) # read data from json file k[0, 0], k[1, 1] = 1000., 1000. @mshooter You can do this. But the projected 3D keypoints can only correspond to reproj_kp_2d, not to 2D keypoints. |
@luoxue-star Indeed that as the approach however, the reprojected 2D keypoints are not as accurate as the true 2D ground truths. Which might affect the networks performance. Thank you though! |
@mshooter @luoxue-star Thank you for your reply! I didn't use PyTorch3D, but instead followed @luoxue-star approach and wrote the projection in Python. However, I chose the focal length as |
Thank you all for replying and confirming for having similar issues :) |
Hi,
I am reprojecting the keypoint_3d data, however, they do not corresponds to the keypoint_2d. They do correspond to the reproj_kp_2d. But it is slightly off of the keypoint_2d ground truth. Which library did you use to reproject the keypoints?
The text was updated successfully, but these errors were encountered: