#313 · Primary category： Computer Vision
PixelLib
Visit PixelLib's official documentation https://pixellib.readthedocs.io/en/latest/
Project last updated：10/06/23
GitHub Stars
1.1K
Forks
268
Contributors
7
License
MIT
Why we included this project
PixelLib gets object segmentation working in a few lines of Python, covering both semantic and instance segmentation for images and videos without forcing you to assemble Mask R-CNN or PointRend by hand. It runs on both TensorFlow and PyTorch, which matters when a team is split across the two frameworks or in the middle of a migration. The PyTorch path uses PointRend for instance segmentation, which produces cleaner object boundaries and runs faster than the classic Mask R-CNN route; the author also adapted Detectron2's PointRend so it works on Windows, something the upstream code does not offer. Teams that mainly want accurate pixel-level masks without fighting the underlying model code will find it a practical shortcut.
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)