Xiaoxuan Ma

Thanks for your prompt reply. `joint_cam` means 3D joint coordinates processed from https://github.com/mks0601/I2L-MeshNet_RELEASE/blob/5d495593fa99e3e44af0289964a7da7284fd9876/data/Human36M/Human36M.py#L93 and the visualization script can be inserted just before https://github.com/mks0601/I2L-MeshNet_RELEASE/blob/5d495593fa99e3e44af0289964a7da7284fd9876/data/Human36M/Human36M.py#L153 ``` if "data/Human36M/images/s_09_act_05_subact_02_ca_02/s_09_act_05_subact_02_ca_02_001201.jpg" in img_path: transform =...

hmm I randomly plot half of the test set, it seems like that there are about 100 samples that have the wrong `joint_cam`, thus with the wrong `mesh_cam`. And most...

Ohhhhhh my god! It's a different image on my side! I should have checked my data now! Thank you so much!

okay! I'm downloading now! Thank you so much!

oh, got it! There is no problem! Thank you again!

Hi, thanks for your attention and sorry for my late reply! Since this work focuses on _relative_ pose estimation, we first align the _root_ before computing MPJPE following the standard...

Hi, thanks for your attention. At this time, our method couldn't inference ANY video without root information (locate back-projected volume) or camera parameter (used when doing back-projection).

@pangyyyyy Hi, have you solved the problem?

Paper name/title: GFPose: Learning 3D Human Pose Prior with Gradient Fields Paper link: https://arxiv.org/pdf/2212.08641.pdf Code link: https://github.com/Embracing/GFPose Thank you!