sanweiliti/LEMO

Official Pytorch implementation for 2021 ICCV paper "Learning Motion Priors for 4D Human Body Capture in 3D Scenes" and trained models / data

40
/ 100
Emerging

This project helps researchers and engineers accurately capture and model human motion within 3D scenes over time. It takes raw motion capture data or video recordings as input and produces high-fidelity, temporally consistent 4D human body models. Robotics engineers, animation studios, and biomechanics researchers would use this for precise human movement analysis.

202 stars. No commits in the last 6 months.

Use this if you need to create realistic, smooth, and complete 4D human body movements from potentially noisy or incomplete motion capture data in complex 3D environments.

Not ideal if you are looking for a simple, out-of-the-box solution for casual video processing or if your primary focus is on static 3D body models without considering temporal dynamics.

human-motion-capture 3d-animation biomechanics robotics computer-vision
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

202

Forks

21

Language

Python

License

MIT

Last pushed

May 01, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/sanweiliti/LEMO"

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