All Projects → HanbumKo → DnCNN-JPEG

HanbumKo / DnCNN-JPEG

Licence: other
A tensorflow implementation of 'Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising' only for JPEG deblokcing

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to DnCNN-JPEG

CResMD
(ECCV 2020) Interactive Multi-Dimension Modulation with Dynamic Controllable Residual Learning for Image Restoration
Stars: ✭ 92 (+441.18%)
Mutual labels:  jpeg-deblocking
DnCNN-Denoise-Gaussian-noise-TensorFlow
Simple implementation of the paper (DnCNN)'Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising'
Stars: ✭ 53 (+211.76%)
Mutual labels:  dncnn
Image-Denoising-with-Deep-CNNs
Use deep Convolutional Neural Networks (CNNs) with PyTorch, including investigating DnCNN and U-net architectures
Stars: ✭ 54 (+217.65%)
Mutual labels:  dncnn

Description

A Tensorflow implementation of DnCNN, 'Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising' TIP2017, paper. Original code is here but this code covers only a Gaussian denoiser. So I fixed it for JPEG deblocking(only for quality factor : 10).

Model architecture

Alt text

Usage

Train

$ python generate_patches.py
$ python main.py

Test

$ python main.py --phase test

Result

input : Alt text output : Alt text

Reference

https://github.com/crisb-DUT/DnCNN-tensorflow

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].