microsoft/Deep3DFaceReconstruction

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

2353 stars · 449 forks observed · 2026-08-28

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

A TensorFlow implementation of a weakly-supervised CNN method for reconstructing accurate 3D face models (shape, texture, pose, landmarks) from single images or image sets, published at CVPRW 2019. The repository is no longer maintained; the authors recommend the PyTorch reimplementation instead.

Use cases

• reconstruct a 3d face model from a single photo
• estimate face pose and facial landmarks from images
• extract high-fidelity face textures and albedo from photos
• build 3d avatars from face images
• research baseline for monocular 3d face reconstruction
• handle faces under large pose or occlusion

When to choose

• you need a TensorFlow-based 3D face reconstruction pipeline
• you are reproducing the CVPRW 2019 paper's results
• you need pose estimation and 68 landmarks alongside 3D reconstruction

When to avoid

• you want an actively maintained project - use the official PyTorch reimplementation instead
• your stack is PyTorch-native
• you need real-time performance on modern hardware without legacy TensorFlow 1.x

Facets

library · maturity abandoned

machine-learning computer-vision image-processing computer-vision deep-learning artificial-intelligence python 3d-face-reconstruction tensorflow basel-face-model face-modeling cvprw-2019 deprecated linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="microsoft/Deep3DFaceReconstruction")