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

46
/ 100
Emerging

Built on PyTorch and PyTorch Lightning, EMOCA uses a deep learning architecture combining facial landmark detection with parametric 3D face model regression to capture both coarse geometry and fine expression details. The v2 update integrates MediaPipe landmarks and perceptual lip-reading loss to improve mouth and eye articulation, departing from the original FAN-based approach. The codebase depends on PyTorch3D for 3D operations and provides inference through command-line demos in the dedicated EMOCA subfolder.

828 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

828

Forks

102

Language

Python

License

Last pushed

Dec 06, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/radekd91/emoca"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.