# jeffffffli/HybrIK

Official code of "HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation", CVPR 2021

Repository: https://github.com/jeffffffli/HybrIK
Canonical: https://ross.abutalabs.com/products/hybrik
Language: Python
License: MIT
License Family: permissive
Topics: 3d-pose-estimation, smpl, inverse-kinematics, pose-estimation, pytorch, cvpr, cvpr21
Last push: 2025-01-08T10:01:45+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2102, "days_push": 602, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1618, forks 190 (observed 2026-08-28T04:05:12.157198+00:00)

## What it is
HybrIK is the official PyTorch implementation of a hybrid analytical-neural inverse kinematics method for 3D human pose and shape estimation from images. It recovers SMPL body meshes (and whole-body meshes in HybrIK-X) and includes pretrained models, training code, demos, and a Blender add-on.

## Use cases
- estimate 3d human pose and shape from a single image
- recover smpl body mesh from photos or video
- run whole-body mesh recovery including hands and face
- reconstruct human motion for animation in blender
- benchmark 3d pose estimation on datasets like agora

## When to avoid
- you need real-time pose estimation on edge devices with limited compute
- you only need simple 2d keypoint detection without body shape
- you require a production-ready api rather than research code

## Facets
- artifact type: library
- maturity: stable
- function: machine-learning, computer-vision, image-processing
- domain: computer-vision, machine-learning, deep-learning
- platform: python
- tags: 3d-pose-estimation, inverse-kinematics, smpl, human-mesh-recovery, pytorch, cvpr, body-mesh, linux, gpu

## Member repositories
- jeffffffli/HybrIK (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:12.157198+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 2026-08-30T03:49:38.782222+00:00, confidence not recorded.
  - readme: https://github.com/jeffffffli/HybrIK (fetched 2026-08-28T04:05:12.157198+00:00, sha 5bc213d3b80b)
- Data as of 2026-08-30T08:39:29.467469+00:00.