sicxu/Deep3DFaceRecon_pytorch

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1907 stars · 340 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A PyTorch implementation of Deep3DFaceReconstruction, a weakly-supervised CNN method for reconstructing 3D face geometry from a single image or image set. It achieves state-of-the-art shape reconstruction accuracy on benchmarks like FaceWarehouse, MICC Florence, and the NoW Challenge.

Use cases

• reconstruct a 3D face model from a single photo
• generate 3D face meshes from image sets
• estimate face pose and shape coefficients for avatars
• research baseline for 3D morphable model fitting
• build face reconstruction into a graphics or AR pipeline
• evaluate 3D face reconstruction accuracy on benchmarks

When to choose

• you need accurate 3D face geometry from single RGB images
• you want a PyTorch implementation for easy integration or fine-tuning
• you need robustness to pose and occlusions
• you want a strong benchmarked baseline for 3DMM research

When to avoid

• you need real-time reconstruction on mobile or CPU-only devices
• you require a maintained production-supported library with an API
• you need full-head or full-body reconstruction rather than faces
• you prefer TensorFlow, where the original Microsoft implementation exists

Facets

library · maturity stable

computer-vision image-processing machine-learning deep-learning computer-vision image-processing artificial-intelligence deep-learning python cross-platform 3d-face-reconstruction pytorch face-mesh 3dmm single-image cvprw-2019 gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="sicxu/Deep3DFaceRecon_pytorch")