# sicxu/Deep3DFaceRecon_pytorch

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

Repository: https://github.com/sicxu/Deep3DFaceRecon_pytorch
Canonical: https://ross.abutalabs.com/products/deep3dfacerecon_pytorch
Language: Python
License: MIT
License Family: permissive
Last push: 2024-11-26T07:13:38+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": 1871, "days_push": 645, "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 1907, forks 340 (observed 2026-08-28T04:05:52.562765+00:00)

## What it is
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
- artifact type: library
- maturity: stable
- function: computer-vision, image-processing, machine-learning, deep-learning
- domain: computer-vision, image-processing, artificial-intelligence, deep-learning
- platform: python, cross-platform
- tags: 3d-face-reconstruction, pytorch, face-mesh, 3dmm, single-image, cvprw-2019, gpu, linux

## Member repositories
- sicxu/Deep3DFaceRecon_pytorch (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:52.562765+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 2026-08-30T03:11:16.277484+00:00, confidence not recorded.
  - readme: https://github.com/sicxu/Deep3DFaceRecon_pytorch (fetched 2026-08-28T04:05:52.562765+00:00, sha 7ff0ee26428d)
- Data as of 2026-08-30T08:39:29.467469+00:00.