cleardusk/3DDFA_V2

Health v2 · maintenance only

Adoption not part of the score

3149 stars · 554 forks observed · 2026-08-28

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

3DDFA_V2 is the official PyTorch implementation of the ECCV 2020 paper 'Towards Fast, Accurate and Stable 3D Dense Face Alignment'. It regresses 3DMM parameters from single images to produce 3D face landmarks, dense reconstructions, pose estimation, and exports to .ply/.obj, with ONNX runtime support for fast inference.

Use cases

• reconstruct a 3d face model from a single photo
• detect 3d facial landmarks in images
• estimate head pose from a webcam feed
• export 3d face meshes to obj or ply files
• run fast face alignment with onnx runtime
• generate uv texture maps of faces
• track facial landmarks in video

When to choose

• you need fast, accurate 3D dense face alignment from single images
• you want 3DMM parameter regression with PyTorch or ONNX inference
• you need head pose, landmarks, or mesh export from face photos
• you want a webcam-based real-time face tracking demo

When to avoid

• you need full-body or multi-person 3D reconstruction
• you need a general-purpose face recognition or identity verification system
• you need a maintained production service - the repo is research code with infrequent updates

Facets

library · maturity stable

computer-vision image-processing machine-learning sdk computer-vision deep-learning artificial-intelligence image-processing python cross-platform 3d-face-alignment 3dmm face-reconstruction pytorch onnx eccv-2020 landmarks head-pose-estimation gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="cleardusk/3DDFA_V2")