Home Projects KAIR
KAIR
Python

KAIR

Image Restoration Toolbox (PyTorch). Training and testing codes for DPIR, USRNet, DnCNN, FFDNet, SRMD, DPSR, BSRGAN, SwinIR

by cszn · GitHub
Stars
Forks
License
Created
Last commit
Category
Language
bsrgandeep-learningdenoisingMITPython
View on GitHub
In plain words

Restore and enhance images with a toolbox that includes various algorithms for denoising and improving picture quality.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
KAIR — GitHub preview card
📈 Star history
3 5083 505
2026-07-072026-08-31
📈 Track KAIR

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

Image Restoration Toolbox (PyTorch). Training and testing codes for DPIR, USRNet, DnCNN, FFDNet, SRMD, DPSR, BSRGAN, SwinIR

KAIR has 3.5k stars on GitHub. It has been forked 702 times. KAIR is written mainly in Python. It has been in active development since 2019. KAIR is available under the MIT license. Its main topics are bsrgan, deep-learning, denoising, dncnn.

Frequently asked questions

What is KAIR?

Image Restoration Toolbox (PyTorch). Training and testing codes for DPIR, USRNet, DnCNN, FFDNet, SRMD, DPSR, BSRGAN, SwinIR

Is KAIR open source?

KAIR is an open-source project. It is released under the MIT license.

Is KAIR free?

Yes. KAIR is free and open source — you can use, modify and self-host it.

What license does KAIR use?

KAIR is available under the MIT license.

What language is KAIR written in?

KAIR is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — KAIR

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=cszn-kair)](https://olud.ai/project/cszn-kair.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.