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

Keypoint Validation in "InitTranslation" #426

Open
Daaohame opened this issue Jul 17, 2024 · 0 comments
Open

Keypoint Validation in "InitTranslation" #426

Daaohame opened this issue Jul 17, 2024 · 0 comments

Comments

@Daaohame
Copy link

Hi,

I have some questions about the class InitTranslation used for SMPL refinement, specifically regarding the check for valid keypoints –
https://github.com/zju3dv/EasyMocap/blob/206c95065f0da64581804528d9e182fd35de5e88/myeasymocap/operations/init.py#L44C1-L45C1

for i in range(kpts1.shape[0]):
  k2d = keypoints[i, :nJoints]
  if k2d[:, -1].sum() < nJoints / 2:
      mywarn('[{}] No valid keypoints in frame {}'.format(self.__class__.__name__, i))
      params['Th'][i] = params['Th'][i-1]
      continue

  1. Why do you use k2d[:, -1].sum()? How do you handle cases where negative and positive values offset each other in the sum?
  2. What is the rationale behind the threshold nJoints / 2?

Thank you for your assistance.

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