kristijanbartol/general-3d-humans

[CVPR 2022 Oral] Generalizable Human Pose Triangulation

29
/ 100
Experimental

This tool helps researchers and computer vision practitioners accurately estimate 3D human poses from multiple camera views, even with new camera setups. You provide 2D keypoint detections of a person from different camera angles, and it outputs their estimated 3D pose, robustly handling varied camera placements. It's ideal for anyone analyzing human movement across different recording environments.

No commits in the last 6 months.

Use this if you need to determine the 3D pose of a person from video footage captured by multiple cameras, especially when those cameras have different or changing arrangements.

Not ideal if you only have a single camera view or do not have pre-extracted 2D human keypoints from your images.

3D-human-pose-estimation motion-capture biomechanics-analysis computer-vision-research multi-view-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 5 / 25

How are scores calculated?

Stars

62

Forks

2

Language

Python

License

MIT

Last pushed

Feb 14, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/kristijanbartol/general-3d-humans"

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