vchoutas/smplify-x

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

2163 stars · 374 forks observed · 2026-08-28

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

SMPLify-X is the official PyTorch implementation of the CVPR 2019 paper 'Expressive Body Capture: 3D Hands, Face, and Body from a Single Image'. It fits the SMPL-X unified 3D body model (with articulated hands and expressive face) to 2D keypoints extracted from a single monocular image via optimization.

Use cases

• estimate 3d body, hand, and face pose from a single image
• fit the smpl-x body model to openpose keypoints
• recover 3d human mesh from monocular rgb photos
• run smplify-x fitting pipeline on a folder of images
• fit smpl or smpl+h body models to 2d keypoints
• generate 3d human body meshes for research on human motion and interaction

When to choose

• you need research-grade 3d expressive body fitting from single images
• you already have OpenPose keypoints and registered SMPL-X model files
• you want the reference implementation of the SMPLify-X optimization method

When to avoid

• you need a commercial license - the code and models are restricted to non-commercial scientific research
• you want a fast real-time pose estimator rather than a slow per-image optimization
• you need a maintained production tool - the repo is primarily research code with limited upkeep

Facets

library · maturity maintenance

computer-vision machine-learning image-processing computer-vision machine-learning python 3d-human-pose body-model smpl-x pose-fitting pytorch non-commercial-license research-code optimization research linux macos

Member repositories

For agents

markdown · JSON · MCP: product_card(name="vchoutas/smplify-x")