#98 · Primary category: Computer Vision
nunif
Misc; latest version of waifu2x; 2D video to stereo 3D video conversion
Project last updated:08/22/26
GitHub Stars
3.4K
Forks
282
Contributors
18
License
MIT
Why we included this project
Anyone who upscales anime art or heavily compressed images has run into waifu2x, and this repo is where its author keeps the current PyTorch implementation and pretrained models, including GAN-based photo models. It doubles as a personal toolbox of side projects: iw3 converts ordinary 2D footage into side-by-side stereo video for VR headsets, stlizer is a fast conservative video stabilizer, and cliqa predicts JPEG quality and grain noise so you can filter out low-quality frames when assembling image datasets. The author calls it a playground and warns that APIs can change without notice, so it fits developers comfortable pinning a version or forking better than teams that need a stable dependency. If you want to run the modern waifu2x or poke at depth-based 3D conversion on your own hardware, this is about as direct a path as you will find.
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)