patrikhuber/eos
A lightweight 3D Morphable Face Model library in modern C++
This tool helps researchers and developers in computer vision extract 3D face models from 2D images. You input a 2D image of a face and, optionally, a set of facial landmarks. The output is a 3D face shape (an .obj file) and a texture map (.png) that represents the face in a standardized, pose-invariant way. It's designed for computer vision scientists, augmented reality developers, and anyone working with 3D facial analysis.
1,978 stars. No commits in the last 6 months.
Use this if you need to generate a 3D face model, estimate head pose, or analyze facial expressions from standard 2D images.
Not ideal if you need a high-fidelity animation-ready rig or real-time facial performance capture for film and gaming without a programming background.
Stars
1,978
Forks
599
Language
C++
License
Apache-2.0
Category
Last pushed
May 01, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/patrikhuber/eos"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
Uason-Chen/CTR-GCN
[ICCV2021] Official code for "Channel-wise Topology Refinement Graph Convolution for...
PeterL1n/BackgroundMattingV2
Real-Time High-Resolution Background Matting
PeterL1n/RobustVideoMatting
Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!
Zielon/MICA
MICA - Towards Metrical Reconstruction of Human Faces [ECCV2022]
BGU-CS-VIL/DeepMCBM
"A Deep Moving-camera Background Model" [Erez, Shapira Weber, and Freifeld, ECCV 2022]