sanghviyashiitb/kernel-diff-eccv24
Official Code for "Kernel Diffusion: An Alternate Approach to Blind Deconvolution", Accepted at ECCV2024
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.
Stars
10
Forks
1
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
cswry/SeeSR
[CVPR2024] SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution
JJLibra/SALAD-Pan
🤗 Official implementation for "SALAD-Pan: Sensor-Agnostic Latent Adaptive Diffusion for...
open-mmlab/mmgeneration
MMGeneration is a powerful toolkit for generative models, based on PyTorch and MMCV.
Janspiry/Image-Super-Resolution-via-Iterative-Refinement
Unofficial implementation of Image Super-Resolution via Iterative Refinement by Pytorch
hanjq17/Spectrum
[CVPR 2026] Adaptive Spectral Feature Forecasting for Diffusion Sampling Acceleration