HowieMa/PPT

[ECCV 2022] "PPT: token-Pruned Pose Transformer for monocular and multi-view human pose estimation"

21
/ 100
Experimental

This project helps efficiently determine human body poses from video or images. It takes single or multiple camera views of people as input and outputs the precise 2D or 3D positions of their body joints. It's ideal for researchers and practitioners in computer vision, robotics, or biomechanics who need to analyze human movement.

No commits in the last 6 months.

Use this if you need an efficient way to track human pose from video or images, especially when processing many frames or analyzing complex multi-view scenarios.

Not ideal if your primary goal is object detection or tracking other elements besides human body poses.

human-pose-estimation gait-analysis motion-capture sports-science robotics
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 5 / 25

How are scores calculated?

Stars

63

Forks

2

Language

Python

License

Last pushed

Oct 27, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/HowieMa/PPT"

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