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

Control Points #51

Open
aartykov opened this issue Jul 25, 2024 · 1 comment
Open

Control Points #51

aartykov opened this issue Jul 25, 2024 · 1 comment

Comments

@aartykov
Copy link

Hello! Thanks for the great project. My question is how to get the resultant control points after training? I want to visualize them on the canonical space.

@yihua7
Copy link
Owner

yihua7 commented Jul 27, 2024

Hi,
Thanks for your interest!

  • You can visualize the control points by clicking the node button on the control panel when using the GUI window.

  • You can also refer to the definition of control points (in the canonical space) at

    self.nodes = nn.Parameter(torch.randn(node_num, 3+self.hyper_dim))
    and export them as point cloud by writing some codes (e.g import trimesh;trimesh.Trimesh(verts=nodes[..., :3].detach().cpu().numpy()).export('control_points.ply')). Please remember to load the checkpoint before doing that. : )

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