search

mingyuan-zhang / MotionDiffuse

MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model
https://mingyuan-zhang.github.io/projects/MotionDiffuse.html
Other
828 stars 75 forks source link

SMPL Visualization #20

Open exitudio opened 1 year ago

exitudio commented 1 year ago

Thank you for your work, it's really interesting. I have one question. How can I get SMPL format from pose?

I tried to get SMPL from cont6d_params (data[..., 67:193]) by using smplpytorch but the pose looks different from your visualization based on joint positions

GuGuDaDaDa commented 1 year ago

Thank you for your work, it's really interesting. I have one question. How can I get SMPL format from pose?

I tried to get SMPL from cont6d_params (data[..., 67:193]) by using smplpytorch but the pose looks different from your visualization based on joint positions

Did you solve it? I have the same question.

exitudio commented 1 year ago

Seem like this problem is from the inverse kinematics (and forward kinematics ) format of text-to-motion is different from smplpytorch. However, I still can't solve the problem.