# MotrixLab/SMPLer-X

[NeurIPS 2023] Official Code for "SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation"

Repository: https://github.com/MotrixLab/SMPLer-X
Canonical: https://ross.abutalabs.com/products/smpler-x
Homepage: https://caizhongang.github.io/projects/SMPLer-X/
Language: Python
License: NOASSERTION
License Family: other
Last push: 2026-02-12T08:55:28+00:00

## Health v2 (maintenance only)
Score: 59/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 67, release rhythm 35, longevity 84
- inputs: {"age_days": 1183, "days_push": 202, "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 1220, forks 83 (observed 2026-08-28T04:04:01.850618+00:00)

## What it is
Official code for SMPLer-X, a family of foundation models for expressive human pose and shape estimation (EHPS) that unifies body, hand, and face motion capture from images and video. It provides training, testing, inference, visualization, and a HuggingFace demo built on PyTorch and mmpose.

## Use cases
- estimate 3d human body hands and face pose from video
- recover smpl-x mesh from monocular images
- fit human body shape and pose from rgb video
- run motion capture without markers using a single camera
- benchmark expressive human pose and shape estimation models
- fine-tune a foundation model for 3d human mesh recovery

## When to choose
- you need state-of-the-art SMPL-X body, hand, and face estimation from RGB input
- you want pretrained EHPS foundation models with scaling-law-backed performance
- you need a research codebase for training and evaluating EHPS models

## When to avoid
- you need real-time pose estimation on CPU or edge devices
- you only need lightweight 2D keypoints rather than full 3D SMPL-X meshes
- you require a permissively licensed model for commercial use (license is non-standard)

## Facets
- artifact type: library
- maturity: stable
- function: machine-learning, deep-learning, computer-vision, image-processing, video-processing
- domain: computer-vision, machine-learning, deep-learning, artificial-intelligence
- platform: python
- tags: human-pose-estimation, smpl-x, ehps, 3d-human-mesh, foundation-model, neurips-2023, body-hands-face, motion-capture, gpu, docker, linux

## Member repositories
- MotrixLab/SMPLer-X (main) score 59

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:01.850618+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 2026-08-30T06:15:55.843998+00:00, confidence not recorded.
  - readme: https://github.com/MotrixLab/SMPLer-X (fetched 2026-08-28T04:04:01.850618+00:00, sha 02f1c6f5e995)
  - homepage: https://caizhongang.github.io/projects/SMPLer-X/ (fetched 2026-08-29T12:24:32.989922+00:00, sha 998cfba7bab9)
- Data as of 2026-08-30T08:39:29.467469+00:00.