openpifpaf/openpifpaf

Health v2 · maintenance only

Flags: no_license

Adoption not part of the score

1261 stars · 255 forks observed · 2026-08-28

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

OpenPifPaf is a PyTorch library implementing Composite Fields for semantic keypoint detection and spatio-temporal association, primarily for human pose estimation and tracking. It provides real-time, single-stage detection and association of keypoints across images and video frames.

Use cases

• detect human body pose in images
• track human pose across video frames in real time
• estimate keypoints for animals or vehicles
• run pose estimation on webcam or video streams
• benchmark pose estimation on COCO or PoseTrack datasets
• build perception for self-driving cars or delivery robots

When to choose

• you need real-time pose detection and tracking in a single stage
• you want a well-tested Python/PyTorch pose estimation library
• you need keypoint detection beyond humans, such as animals or vehicles

When to avoid

• you need general object detection or segmentation rather than keypoints
• you need a non-PyTorch framework or mobile-first deployment
• you require a permissively licensed library, as the license is non-standard

Facets

library · maturity maintenance

computer-vision machine-learning deep-learning image-processing computer-vision machine-learning deep-learning artificial-intelligence python windows pose-estimation keypoint-detection human-pose pytorch pose-tracking real-time linux macos gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="openpifpaf/openpifpaf")