Giters

radekd91 / emoca

Official repository accompanying a CVPR 2022 paper EMOCA: Emotion Driven Monocular Face Capture And Animation. EMOCA takes a single image of a face as input and produces a 3D reconstruction. EMOCA sets the new standard on reconstructing highly emotional images in-the-wild

Home Page:https://emoca.is.tue.mpg.de/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Mesh extraction?

oliverban opened this issue · comments

commented

After reconstruction video is there any chance to get the actual mesh out in OBJ/FBX/ALEMBIC or any other 3D format?

commented

Hi @oliverban, you can get multiple meshes from the video's frames by adding the argument --save_mesh when running demos/test_emoca_on_video.py. Check out the script for more details.