#177 · Primary category： Computer Vision
MocapNET
Real-time 3D human pose estimation from monocular images, directly outputting BVH format for animation and mocap workflows.
Project last updated：08/13/26
GitHub Stars
949
Forks
144
Contributors
2
License
Other
Why we included this project
MocapNET is worth a look if you want motion capture without a suit or a studio. Point a webcam at someone, run a 2D pose detector like MediaPipe, and MocapNET lifts those joints into a full 3D skeleton written out as BVH, the format animation tools such as Blender import natively. The v4 codebase is a fresh Python rewrite and ships with a Colab notebook, so animators and game modders with more asset-side than ML experience can get something moving quickly. Real research backs it up, a defended PhD thesis and an ICCV workshop paper, not just a half-finished script. Treat it as a solid prototype-grade starting point rather than plug-and-play software; the repo is the work of a researcher and occasionally shows it.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
opencv
Open Source Computer Vision Library
RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
tesseract
Tesseract Open Source OCR Engine (main repository)