search

zc-alexfan / arctic

[CVPR 2023] Official repository for downloading, processing, visualizing, and training models on the ARCTIC dataset.
https://arctic.is.tue.mpg.de
Other
301 stars 18 forks source link

Evaluating the predicted weak perspective camera #20

Closed ap229997 closed 1 year ago

ap229997 commented 1 year ago

The predicted weak perspective camera is converted into the translation term, which is then used to compute the vertices and joints in camera coordinate frame. However, during evaluation, all the 3D locations are shifted to the wrist joint and then metrics are computed. This effectively gets rid of any translation error. Is there any reason why the metrics are not computed in the camera frame?

zc-alexfan commented 1 year ago

Which metric you refer to? The metrics do not evaluate the global translation, but the relative translation between the two hands.

ap229997 commented 1 year ago

I was mainly looking at mpjpe_ra but the same is the case for other metrics as well. I understand that global translation does not matter much for contact and interaction metrics.

zc-alexfan commented 1 year ago

Yes, the global translation does not matter. Also, MPJPE_RA is also root-relative.