search

TimoBolkart / voca

This codebase demonstrates how to synthesize realistic 3D character animations given an arbitrary speech signal and a static character mesh.
https://voca.is.tue.mpg.de/en
1.15k stars 273 forks source link

Is it possible to map facial models to BlendShape? #84

Closed airfri closed 2 years ago

airfri commented 2 years ago

I saw the VOCA model output video and OBJ file sequence, and I was wondering if there are other output forms, such as blendshape, or if it is possible to map the output 3D mesh data into blendshape.

TimoBolkart commented 2 years ago

You can map it to FLAME blendshapes as seen in the compute_FLAME_params.py demo.