GONGJIA0208/Diffpose

[CVPR 2023] DiffPose: Toward More Reliable 3D Pose Estimation

37
/ 100
Emerging

This project helps analyze human movement by converting 2D video footage into detailed 3D skeletal poses. It takes standard video data or 2D pose estimations and outputs precise 3D coordinates for human joints, providing a robust understanding of motion. Researchers and practitioners in fields like biomechanics, animation, or sports science would find this useful for analyzing human actions.

187 stars. No commits in the last 6 months.

Use this if you need to transform 2D video recordings of human movement into accurate and reliable 3D pose data for analysis or simulation.

Not ideal if you are looking for a ready-to-use application with a graphical interface, as this project is a code-based solution for researchers and developers.

human-motion-analysis 3D-pose-estimation video-analysis biomechanics computer-vision
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

187

Forks

13

Language

Python

License

MIT

Last pushed

Dec 28, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/GONGJIA0208/Diffpose"

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