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

[CLIFF]the problem about 2d keypoints #208

Open
pppkkk611 opened this issue Nov 22, 2023 · 0 comments
Open

[CLIFF]the problem about 2d keypoints #208

pppkkk611 opened this issue Nov 22, 2023 · 0 comments

Comments

@pppkkk611
Copy link

pppkkk611 commented Nov 22, 2023

Hi! thank you for amazing work.
I checked #119

    points_3d = pred_output.joints
    batch_size = points_3d.shape[0]
    img_w_value = img_w[0].item()
    img_h_value = img_h[0].item() 
    camera_center = torch.tensor([[img_w_value / 2, img_h_value / 2]], device=points_3d.device)
    camera_center = camera_center.expand(batch_size, 2)
    keypoints_2d = perspective_projection(points=points_3d,
                                  rotation=torch.eye(3, device=points_3d.device).unsqueeze(0).expand(batch_size, -1, -1),
                                  translation=pred_cam_full,
                                  focal_length=focal_length,
                                  camera_center=camera_center)

visualization:
1700646556088

    points_3d = pred_output.joints
    batch_size = points_3d.shape[0]
    img_w_value = img_w[0].item()
    img_h_value = img_h[0].item() 
    camera_center = torch.tensor([[img_w_value / 2, img_h_value / 2]], device=points_3d.device)
    camera_center = camera_center.expand(batch_size, 2)
    keypoints_2d = perspective_projection(points=points_3d,
                                  rotation=torch.eye(3, device=points_3d.device).unsqueeze(0).expand(batch_size, -1, -1),
                                  translation=pred_cam_crop,
                                  focal_length=focal_length,
                                  camera_center=camera_center)

visualization:
1700646642283

translation=pred_cam_crop is in the right proportion, but not in the center
translation=pred_cam_full the key point is not in the right proportion, but in the center
I don't know how to fix it.

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

1 participant