You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Thank you for a very exciting and interesting research paper as well as sharing the test code.
The code works brilliantly for 3d shape estimation, but is there a way to get skeleton joint positions and rotations with your code?
Are joint names with their respective positions and rotations supposed to be included in SMPL h5 file?
Thank you for your work.
Best regards,
Jurgis
The text was updated successfully, but these errors were encountered:
Thanks for your interest!
Yes, we save the SMPL parameter in the h5 file. which compose of 3-dim camera parameter, 72-dim SMPL 24 joint rotation vector, 10-dim SMPL shape parameter. To derive the 3D joint location, please refer to https://github.com/JDAI-CV/DSD-SATN/blob/master/src/utils/SMPL.py
At its last 2 line, it derived the vertices, 3D joints coordinates and rotation as verts, joint, r
Thank you for a very exciting and interesting research paper as well as sharing the test code.
The code works brilliantly for 3d shape estimation, but is there a way to get skeleton joint positions and rotations with your code?
Are joint names with their respective positions and rotations supposed to be included in SMPL h5 file?
Thank you for your work.
Best regards,
Jurgis
The text was updated successfully, but these errors were encountered: