#16 · Primary category： Computer Vision
Real-ESRGAN
Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
Project last updated：08/06/24
GitHub Stars
36.6K
Forks
4.5K
Contributors
11
License
BSD-3-Clause
Why we included this project
Real-ESRGAN is a widely used blind super-resolution library that turns low-quality images into clean 2x to 4x upscales. It includes dedicated models for anime illustrations and a lighter one for general scenes, and the same codebase extends to video restoration, so you can upscale old footage or animation frame by frame. Face enhancement via GFPGAN is built in, and portable ncnn-vulkan executables for Windows, Linux, and macOS make batch jobs on modest hardware straightforward. Developers adding photo enhancement, media archiving, or anime upscaling to their products will find a documented model zoo, training and finetuning scripts, and a simple inference entry point.
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)