wyhuai/DDNM
[ICLR 2023 Oral] Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model
This project helps photographers, archivists, or anyone with old or degraded photos to restore their images to a higher quality. It takes a damaged image—whether it's blurry, noisy, colorless, compressed, or even a low-resolution scan—and produces a clear, enhanced, and often colorized version. This is ideal for those looking to breathe new life into old family photos or improve the clarity of suboptimal digital images without complex software or prior training.
1,331 stars. No commits in the last 6 months.
Use this if you need to quickly and effectively repair common flaws in photos like blur, noise, compression artifacts, or if you want to upscale low-resolution images or colorize old black and white pictures.
Not ideal if you need fine-grained, artistic control over every aspect of the restoration process or if your images require highly specialized editing beyond typical degradation issues.
Stars
1,331
Forks
104
Language
Python
License
MIT
Category
Last pushed
Apr 25, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/wyhuai/DDNM"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
devzhk/InverseBench
InverseBench (ICLR 2025 spotlight)
guyyariv/DyPE
Official implementation for "DyPE: Dynamic Position Extrapolation for Ultra High Resolution Diffusion".
bahjat-kawar/ddrm
[NeurIPS 2022] Denoising Diffusion Restoration Models -- Official Code Repository
yuanzhi-zhu/DiffPIR
"Denoising Diffusion Models for Plug-and-Play Image Restoration", Yuanzhi Zhu, Kai Zhang,...
Algolzw/image-restoration-sde
Image Restoration with Mean-Reverting Stochastic Differential Equations, ICML 2023. Winning...