Zielon/MICA
MICA - Towards Metrical Reconstruction of Human Faces [ECCV2022]
This project helps researchers and developers reconstruct detailed 3D models of human faces from standard 2D images. You input one or more face images, and it outputs a precise 3D mesh, a rendered image of the reconstruction, and the underlying facial parameters. It's designed for computer vision scientists, graphics developers, and academics working with 3D face modeling.
630 stars. No commits in the last 6 months.
Use this if you need to generate accurate, metrical 3D face reconstructions from 2D images for research or application development, particularly within computer vision or 3D graphics domains.
Not ideal if you're looking for an off-the-shelf end-user application for casual photo editing or consumer-facing 3D avatar creation without development.
Stars
630
Forks
91
Language
Python
License
—
Category
Last pushed
Mar 17, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Zielon/MICA"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
patrikhuber/eos
A lightweight 3D Morphable Face Model library in modern C++
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!
BGU-CS-VIL/DeepMCBM
"A Deep Moving-camera Background Model" [Erez, Shapira Weber, and Freifeld, ECCV 2022]