# vchoutas/smplx

SMPL-X

Repository: https://github.com/vchoutas/smplx
Canonical: https://ross.abutalabs.com/products/smplx
Homepage: https://smpl-x.is.tue.mpg.de/
Language: Python
License: NOASSERTION
License Family: other
Last push: 2024-08-12T05:09:47+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": 2673, "days_push": 751, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2685, forks 395 (observed 2026-08-28T04:07:10.244471+00:00)

## What it is
A PyTorch implementation of SMPL-X, a unified parametric 3D model of the human body with fully articulated hands and an expressive face, also supporting loading of SMPL and SMPL+H models. It provides model loading, parameter fitting utilities, and transfer code between models in the SMPL family.

## Use cases
- load and evaluate the SMPL-X 3D human body model in PyTorch
- fit a 3D body model with hands and face to 2D image features
- convert between SMPL, SMPL+H, and SMPL-X model parameters
- generate 3D human meshes from pose, shape, and expression parameters
- build human pose estimation or body capture research pipelines
- render parametric 3D human avatars for research

## When to choose
- you need a research-grade implementation of SMPL-X, SMPL+H, or SMPL in PyTorch
- your project involves 3D human pose, shape, or expression estimation from images
- you need to transfer parameters between models in the SMPL family
- you are doing non-commercial scientific research on expressive human capture

## When to avoid
- you need a permissively licensed model for commercial products - the license restricts use to non-commercial scientific research
- you need a general-purpose 3D animation or character rigging tool rather than a parametric body model library
- you need ready-made pretrained networks that regress SMPL-X parameters from images - this repo provides the model itself, not full estimation pipelines

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, computer-vision, graphics, simulation
- domain: computer-vision, graphics, machine-learning
- platform: python, windows
- tags: smpl, 3d-human-body-model, pytorch, parametric-body-model, non-commercial-license, computer-graphics, human-pose, research, linux, macos

## Member repositories
- vchoutas/smplx (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:10.244471+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 2026-08-30T02:17:50.804143+00:00, confidence not recorded.
  - readme: https://github.com/vchoutas/smplx (fetched 2026-08-28T04:07:10.244471+00:00, sha 8c16187bc64d)
  - homepage: https://smpl-x.is.tue.mpg.de/ (fetched 2026-08-29T10:00:00.077126+00:00, sha 8f885443046e)
- Data as of 2026-08-30T08:39:29.467469+00:00.