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
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.
Stars
828
Forks
102
Language
Python
License
—
Category
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.
Higher-rated alternatives
petercunha/Emotion
:smile: Recognizes human faces and their corresponding emotions from a video or webcam feed....
Prem-ium/Metahuman-Emotion-Recognition
Emotionally responsive Virtual Metahuman CV with Real-Time User Facial Emotion Detection (Unreal...
genbing99/SoftNet-SpotME
Shallow Optical Flow Three-Stream CNN For Macro and Micro-Expression Spotting From Long Videos
PrudhvirajuChekuri/EmoViz
This is a web application that takes different kind of inputs(real-time, image, video) from the...
DeepPythonist/EmotionTracker
AI-powered real-time emotion detection desktop app using DeepFace. Track emotions via webcam...