abdallahdib/NextFace

A high-fidelity 3D face reconstruction library from monocular RGB image(s)

46
/ 100
Emerging

Leverages differentiable ray tracing with PyTorch's autograd to jointly optimize a morphable face model, estimating not just geometry but also per-pixel material properties (diffuse/specular/roughness) and spherical harmonics lighting in a three-stage pipeline. Supports multi-image reconstruction with optional identity sharing across frames, and exports reconstructed meshes, texture maps, and environment maps compatible with external rendering engines. Integrates MediaPipe or FAN for facial landmark detection and requires Basel Face Model and AlbedoMM datasets.

813 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

813

Forks

103

Language

Jupyter Notebook

License

GPL-3.0

Last pushed

Oct 18, 2023

Commits (30d)

0

Get this data via API

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

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