#329 · Primary category： Computer Vision
MUNIT
Multimodal Unsupervised Image-to-Image Translation
Project last updated：09/20/22
GitHub Stars
2.7K
Forks
487
Contributors
5
License
Other
Why we included this project
MUNIT is worth a look if you are working on unsupervised image-to-image translation and want to reproduce the ECCV 2018 paper behind it. Even though NVIDIA no longer maintains this repository, it still ships working setups for classic tasks like turning edge sketches into shoes or handbags, translating between animal species, and converting summer Yosemite scenes to winter ones. The authors point to their newer imaginaire library for continued development, so treat this code as a research baseline and educational reference rather than production software. The shared latent space idea and the ability to generate multiple output styles from one input remain a useful benchmark for teams exploring multimodal translation.
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)