zhangyi-3/IDR
Self-Supervised Image Denoising via Iterative Data Refinement (CVPR2022)
This project helps remove unwanted noise from digital images, making them clearer and more usable for analysis or presentation. You input noisy images, and it outputs cleaned, denoised versions. It's designed for researchers, photographers, or image analysts who work with noisy image data and need to improve its quality without requiring clean reference images.
131 stars.
Use this if you have images with various types of noise (e.g., Gaussian, impulse) and need an automated way to enhance their quality without access to perfectly clean examples for comparison.
Not ideal if you need to restore severely corrupted images or are looking for tools to enhance image resolution rather than just remove noise.
Stars
131
Forks
15
Language
Python
License
MIT
Category
Last pushed
Jan 16, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/zhangyi-3/IDR"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
yinboc/liif
Learning Continuous Image Representation with Local Implicit Image Function, in CVPR 2021 (Oral)
XingangPan/deep-generative-prior
Code for deep generative prior (ECCV2020 oral)
mv-lab/swin2sr
[ECCV] Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration. ...
eliahuhorwitz/DeepSIM
Official PyTorch implementation of the paper: "DeepSIM: Image Shape Manipulation from a Single...
cszn/FFDNet
FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising (TIP, 2018)