FouierL/EquS
Official Code of the paper “Equivariant Sampling for Improving Diffusion Model-based Image Restoration“
This project helps image processing specialists and researchers enhance degraded images. It takes a corrupted image (e.g., blurry, noisy, or low-resolution) and produces a significantly clearer, higher-quality version. The ideal users are those working on image restoration tasks like super-resolution or removing compression artifacts.
Use this if you need to reliably restore degraded images across various levels of corruption and transformations, consistently achieving superior visual and quantitative results.
Not ideal if you require real-time image processing or are working with image types that do not benefit from diffusion model-based restoration.
Stars
19
Forks
—
Language
Python
License
—
Category
Last pushed
Jan 29, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/FouierL/EquS"
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