search

mkocabas / VIBE

Official implementation of CVPR2020 paper "VIBE: Video Inference for Human Body Pose and Shape Estimation"
https://arxiv.org/abs/1912.05656
Other
2.85k stars 551 forks source link

Can I use to detected 3D keypoints to control my own mesh model?[FEATURE] #257

Open Holmes-Alan opened 2 years ago

Holmes-Alan commented 2 years ago

I understand that your method uses SMPL to generate the 3D model. I wonder if I can replace it with my own mesh model since I want to use a textured 3D model for animation.

If not, what should I do? Thank you in advance.