#204 · Primary category： Computer Vision
HYPIR
Official implementation of HYPIR: Harnessing Diffusion-Yielded Score Priors for Image Restoration (SIGGRAPH 2025)
Project last updated：10/16/25
GitHub Stars
1.2K
Forks
102
Contributors
2
License
Other
Why we included this project
HYPIR is the official implementation of a SIGGRAPH 2025 method that cleans up and upscales degraded photos by borrowing score priors from a pretrained diffusion model. You hand it a blurry, low-resolution, or compressed image and get back a sharper, higher-resolution version, with a text prompt available to steer the result. The repository includes pretrained LoRA weights, a Gradio interface, and Colab and Replicate demos, so you can test it without assembling the pipeline yourself. If you work on photo enhancement, super-resolution, or restoring old scans, the training and inference scripts make it straightforward to adapt the approach to your own data. One thing to check before adopting it: the code is under a custom non-commercial license, so read the terms if you plan to use it in a product.
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)