File Exchange

image thumbnail

Learning Deep CNN Denoiser Prior for Image Restoration

version 1.0.0.1 (201 MB) by Kai Zhang
Learning Deep CNN Denoiser Prior for Image Restoration, CVPR, 2017

16 Downloads

Updated 27 Nov 2020

From GitHub

View Version History

View license on GitHub

We plug the CNN denoisers into the half quadratic splitting (HQS) algorithm to solve the following image restoration tasks:
- Image Deblurring
- Image Inpainting
- Single Image Super-Resolution
- Color Image Demosaicking
No task-specific training is done for the above tasks.

Paper Link: http://openaccess.thecvf.com/content_cvpr_2017/papers/Zhang_Learning_Deep_CNN_CVPR_2017_paper.pdf
Code Link: https://github.com/cszn/IRCNN

@inproceedings{zhang2017learning,
title={Learning Deep CNN Denoiser Prior for Image Restoration},
author={Zhang, Kai and Zuo, Wangmeng and Gu, Shuhang and Zhang, Lei},
booktitle={IEEE Conference on Computer Vision and Pattern Recognition},
pages={3929--3938},
year={2017},
}

Cite As

Kai Zhang (2021). Learning Deep CNN Denoiser Prior for Image Restoration (https://github.com/cszn/IRCNN), GitHub. Retrieved .

Comments and Ratings (5)

Kai Zhang

PyTorch version: https://github.com/cszn/DPIR

cui

Is there any one that does not rely on third-party matconv?

Kenta

moahaimen talib

hi sir i need to use cnn (deep neural network) in classification of binary images
please
could you help me

MATLAB Release Compatibility
Created with R2015b
Compatible with any release
Platform Compatibility
Windows macOS Linux

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!