leoxiaobin/deep-high-resolution-net.pytorch

The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"

51
/ 100
Established

This project helps pinpoint key anatomical locations on people in images or video, often called human pose estimation. It takes an image or video frame as input and outputs precise coordinates for body joints like elbows, wrists, and ankles. Professionals in sports analytics, animation, robotics, or augmented reality would find this useful for analyzing or replicating human motion.

4,466 stars. No commits in the last 6 months.

Use this if you need highly accurate and spatially precise mapping of human body keypoints from visual data.

Not ideal if you need a lightweight model for real-time inference on low-power devices, or if your primary goal is general object detection rather than detailed pose analysis.

human-pose-estimation sports-analytics animation robotics augmented-reality
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

4,466

Forks

926

Language

Cuda

License

MIT

Last pushed

Aug 30, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/leoxiaobin/deep-high-resolution-net.pytorch"

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