KevinLTT/video2bvh
Extracts human motion in video and save it as bvh mocap file.
This tool helps animators and motion designers turn standard video footage of human movement into reusable 3D motion capture files. You input a video showing a person moving, and it outputs a BVH (Biovision Hierarchy) file. This BVH file can then be applied to 3D character models in animation software, saving significant time compared to manual keyframe animation.
639 stars. No commits in the last 6 months.
Use this if you need to quickly extract human motion from video for animation, game development, or visual effects projects.
Not ideal if you require extremely precise, professional-grade motion capture that typically comes from dedicated studio setups with specialized hardware.
Stars
639
Forks
99
Language
Python
License
MIT
Category
Last pushed
Nov 09, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/KevinLTT/video2bvh"
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.