wyhuai/DDNM

[ICLR 2023 Oral] Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model

44
/ 100
Emerging

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.

photo-restoration image-enhancement digital-archiving historical-photo-preservation media-quality-improvement
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

1,331

Forks

104

Language

Python

License

MIT

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.