Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/mingtaoguo/dncnn-denoise-gaussian-noise-tensorflow
Simple implementation of the paper (DnCNN)'Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising'
https://github.com/mingtaoguo/dncnn-denoise-gaussian-noise-tensorflow
denoise-images dncnn tensorflow
Last synced: about 2 months ago
JSON representation
Simple implementation of the paper (DnCNN)'Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising'
- Host: GitHub
- URL: https://github.com/mingtaoguo/dncnn-denoise-gaussian-noise-tensorflow
- Owner: MingtaoGuo
- License: mit
- Created: 2018-08-31T13:43:57.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2019-03-02T02:14:19.000Z (almost 6 years ago)
- Last Synced: 2024-06-05T19:28:20.813Z (7 months ago)
- Topics: denoise-images, dncnn, tensorflow
- Language: Python
- Size: 1.36 MB
- Stars: 59
- Watchers: 4
- Forks: 13
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# DnCNN-TensorFlow
Simple implementation of the paper (DnCNN)'Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising'
## Introduction
This code just simplely implement the paper [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](http://cn.arxiv.org/pdf/1608.03981), but there are some details of the code are different from the paper.
## DataSets
The datasets include 400 gray images, but i have croped them into 40x40 patches. the croped datasets can be downloaded from my [BaiduYun](https://pan.baidu.com/s/1Uiq29K2WLvOyeGlnRu8j_A)
Examples of TrainingSet
|||||||||
|-|-|-|-|-|-|-|-|
|||||||||
## Python packages
====================
1. python3.5
2. tensorflow1.4.0
3. pillow
4. numpy
5. scipy
====================
## Results of the code
Trained about 1 epoch
|Raw|Noised|Denoised|
|-|-|-|
||||
||||
||||
||||
||||
||||
||||