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

Compatibility with ZJU format #26

Open
KhanhNgoDuy opened this issue Dec 7, 2024 · 0 comments
Open

Compatibility with ZJU format #26

KhanhNgoDuy opened this issue Dec 7, 2024 · 0 comments

Comments

@KhanhNgoDuy
Copy link

Hi, thank you for your work.

Currently, I am training GauHuman on your dataset. I tried to reuse the Dataloader for ZJU, however the training result is always black. It seems that your dataset is using a different format with the ZJU Monocap dataset.

I only modify the data of camera translation by multiplying with camera_scale.pkl. The way I convert original data of MVHuman to ZJU format is:

  1. new_params: taken from smpl/smplx.
  2. new_vertices: taken from smpl_param
  3. cams: taken from camera_intrinsics, camera_extrinsics
  4. kpts2d: taken from openpose

Questions/notices:

  1. The SMPL parameters has shape of (1, 87), while it is (1, 72) in ZJU.
  2. Is the camera convention in MVHuman the same as in ZJU?
  3. How can I convert the MVHuman data to the exact format of ZJU?

Thank you!

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