sanghviyashiitb/kernel-diff-eccv24

Official Code for "Kernel Diffusion: An Alternate Approach to Blind Deconvolution", Accepted at ECCV2024

28
/ 100
Experimental

This project helps image processing specialists and researchers improve the clarity of blurry images where the cause of the blur is unknown. It takes a blurry image as input and outputs a significantly sharper, deblurred image by estimating the blur pattern. Image analysts, forensic specialists, or anyone needing to recover detail from images affected by unknown blur would use this.

No commits in the last 6 months.

Use this if you need to restore clear details from images that are degraded by blur, and you don't know what caused the blur.

Not ideal if you already know the exact blur pattern (kernel) affecting your image, as specialized non-blind deconvolution tools might be more efficient.

image-restoration image-analysis deblurring digital-photography computational-imaging
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 7 / 25

How are scores calculated?

Stars

10

Forks

1

Language

Python

License

MIT

Last pushed

Oct 09, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/sanghviyashiitb/kernel-diff-eccv24"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.