abdallahdib/NextFace
A high-fidelity 3D face reconstruction library from monocular RGB image(s)
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.
Stars
813
Forks
103
Language
Jupyter Notebook
License
GPL-3.0
Category
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.
Higher-rated alternatives
vita-epfl/monoloco
A 3D vision library from 2D keypoints: monocular and stereo 3D detection for humans, social...
nburrus/stereodemo
Small Python utility to compare and visualize the output of various stereo depth estimation algorithms
fangchangma/self-supervised-depth-completion
ICRA 2019 "Self-supervised Sparse-to-Dense: Self-supervised Depth Completion from LiDAR and...
wvangansbeke/Sparse-Depth-Completion
Predict dense depth maps from sparse and noisy LiDAR frames guided by RGB images. (Ranked 1st...
JiawangBian/sc_depth_pl
SC-Depth (V1, V2, and V3) for Unsupervised Monocular Depth Estimation ...