#559 · Primary category： Computer Vision
EpipolarPose
Self-Supervised Learning of 3D Human Pose using Multi-view Geometry (CVPR2019)
Project last updated：06/26/19
GitHub Stars
608
Forks
92
Contributors
2
License
Other
Why we included this project
EpipolarPose is a PyTorch implementation of a CVPR 2019 paper on 3D human pose estimation. The method trains a 3D pose estimator without 3D ground-truth labels or camera extrinsics, using epipolar geometry across multi-view images to generate supervision, and at inference time it only needs a single RGB image. The repo is organized for someone who wants to dig in: training and validation scripts, model definitions, a refinement unit, and YAML configs for experiments, plus a demo notebook that runs the whole pipeline. It is a good reference if you want to reproduce the paper's results or build on the self-supervised training idea, though it is research code from 2019 rather than a maintained library.
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)