XunshanMan/MVGFormer

This is the official implementation of the work presented at CVPR 2024, titled Multiple View Geometry Transformers for 3D Human Pose Estimation (MVGFormer).

32
/ 100
Emerging

This project helps researchers and engineers working with human motion capture to accurately estimate 3D human poses from multiple camera views. You provide 2D video feeds from different angles, and it outputs precise 3D joint locations and body poses, even when camera setups change. This is ideal for those analyzing human movement in research, sports science, or robotics.

No commits in the last 6 months.

Use this if you need robust and generalizable 3D human pose estimations from multi-camera video footage, particularly in varied or changing camera environments.

Not ideal if you only have single-camera video input or are not working with human pose estimation.

human-motion-capture 3D-pose-estimation multi-camera-systems computer-vision biomechanics-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

68

Forks

4

Language

Python

License

Apache-2.0

Last pushed

Mar 22, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/XunshanMan/MVGFormer"

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