dluvizon/scene-aware-3d-multi-human
Source code of the paper Scene-Aware 3D Multi-Human Motion Capture, EUROGRAPHICS 2023
This project helps capture the realistic 3D movement and shape of multiple people in a scene using just a standard video camera. You input a single video clip, and it outputs detailed 3D positions, body shapes, and articulated poses for each person, along with a 3D reconstruction of the static background. This tool is ideal for researchers or animators who need affordable and easy-to-set-up 3D motion capture.
131 stars. No commits in the last 6 months.
Use this if you need to analyze the complex 3D motion of multiple people in a scene from a single video source, without specialized multi-camera setups or markers.
Not ideal if you require real-time motion capture or need to track subjects across different camera views without pre-processing.
Stars
131
Forks
18
Language
Python
License
—
Category
Last pushed
Aug 02, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/dluvizon/scene-aware-3d-multi-human"
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.