CMU-Perceptual-Computing-Lab/openpose
Source: https://github.com/cmu-perceptual-computing-lab/openpose
Newer, commercially-friendlier pose stacks exist (RTMPose, DWPose, Sapiens2) but their checkpoint terms need separate checks.
Structured fields
{
"archived": false,
"checked_at": "2026-10-17T00:00:00.000Z",
"usefulness": "The original real-time multi-person body/hand/face/foot keypoint system with multi-camera 3D reconstruction and calibration tooling; historic source of the skeleton convention used by ControlNet pose control. Free for non-commercial use only.",
"source_type": "repository",
"availability": "available",
"next_check_at": "2026-11-16T00:00:00.000Z",
"known_limitations": [
"Last commit date not visible on the fetched page."
],
"upstream_updated_at": "2024-08-03T01:59:11.000Z"
}Evidence claims
- [upstream_claim] README: real-time library for multi-person keypoint detection of body, foot, face and hand; also 3D reconstruction from multiple cameras and calibration toolbox; CUDA, OpenCL and CPU-only builds; C++ and Python APIs. source
- [sourced_fact] README states OpenPose is free for non-commercial use and directs commercial users to a FlintBox licensing page. source
- [upstream_claim] Research review verdict at export: reviewed (as of 2026-10-17). Recorded by the research pipeline, not a hub review outcome; evidence.review stays unreviewed until an independent reviewer records one.
Rights
| component | license | hosting | redistribution | modification | training | Evidence and notes |
|---|---|---|---|---|---|---|
| code | OpenPose academic license (custom; text not read) | restricted | restricted | restricted | unknown | README: free non-commercial use; commercial use needs a separate license. |
| model_weights | unknown | unknown | unknown | unknown | unknown | Model weight terms not read. |