#528 · Primary category： Computer Vision
pyflow
Fast, accurate and easy to run dense optical flow with python wrapper
Project last updated：05/31/19
GitHub Stars
660
Forks
141
Contributors
2
License
MIT
Why we included this project
pyflow wraps Ce Liu's Coarse2Fine optical flow algorithm behind a small Python interface, so you can get a dense per-pixel motion field from a pair of images without compiling C++ or installing the full OpenCV stack. The wrapper was built for a CVPR 2017 paper on unsupervised learning from unlabeled video, so it has been exercised on real research problems rather than just demos. If you work with video frames and need motion between frames for things like frame interpolation or motion segmentation, it is a solid starting point. One caveat: the project has been quiet since 2019, so treat it as a focused utility rather than an actively maintained framework.
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)