# microsoft/Deep3DFaceReconstruction

Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set (CVPRW 2019)

Repository: https://github.com/microsoft/Deep3DFaceReconstruction
Canonical: https://ross.abutalabs.com/products/deep3dfacereconstruction
Language: Python
License: MIT
License Family: permissive
Topics: 3d-face-reconstruction, basel-face-model, faces, tensorflow
Last push: 2024-01-04T16:15:41+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2723, "days_push": 972, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2353, forks 449 (observed 2026-08-28T04:06:40.482784+00:00)

## What it is
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 The repository is no longer maintained; the authors recommend the PyTorch reimplementation instead.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
- artifact type: library
- maturity: abandoned
- function: machine-learning, computer-vision, image-processing
- domain: computer-vision, deep-learning, artificial-intelligence
- platform: python
- tags: 3d-face-reconstruction, tensorflow, basel-face-model, face-modeling, cvprw-2019, deprecated, linux, gpu

## Member repositories
- microsoft/Deep3DFaceReconstruction (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:40.482784+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:36:30.014905+00:00, confidence not recorded.
  - readme: https://github.com/microsoft/Deep3DFaceReconstruction (fetched 2026-08-28T04:06:40.482784+00:00, sha 6e012229f75a)
- Data as of 2026-08-30T08:39:29.467469+00:00.