ViTAE-Transformer/ViTPose

The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation" and [TPAMI'23] "ViTPose++: Vision Transformer for Generic Body Pose Estimation"

53
/ 100
Established

This tool helps researchers and engineers accurately identify and track human body keypoints in images and videos. You input visual media, and it outputs precise coordinates for body joints, enabling detailed analysis of human movement and posture. It's designed for professionals working in fields like sports science, animation, security, and healthcare.

1,957 stars.

Use this if you need to precisely locate and analyze human body poses from visual data for research, development, or application building.

Not ideal if your primary need is object detection or facial recognition, as this tool focuses specifically on human pose estimation.

human-pose-estimation motion-analysis computer-vision biomechanics video-surveillance
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

1,957

Forks

243

Language

Python

License

Apache-2.0

Last pushed

Dec 25, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ViTAE-Transformer/ViTPose"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.