sanweiliti/LEMO
Official Pytorch implementation for 2021 ICCV paper "Learning Motion Priors for 4D Human Body Capture in 3D Scenes" and trained models / data
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.
Stars
202
Forks
21
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
DeepLabCut/DeepLabCut
Official implementation of DeepLabCut: Markerless pose estimation of user-defined features with...
openpifpaf/openpifpaf
Official implementation of "OpenPifPaf: Composite Fields for Semantic Keypoint Detection and...
lambdaloop/anipose
🐜🐀🐒🚶 A toolkit for robust markerless 3D pose estimation
DIYer22/bpycv
Computer vision utils for Blender (generate instance annoatation, depth and 6D pose by one line code)
NeLy-EPFL/DeepFly3D
Motion capture (markerless 3D pose estimation) pipeline and helper GUI for tethered Drosophila.