Giter Club home page Giter Club logo

cnn_denoise_pytorch's Introduction

CNN_Denoiser_pytorch

Pytorch框架下采用CNN去除高斯噪声(盲去噪,未像DnCNN事先给出相对固定的信噪比),尝试采用类似FPN+残差网络的结构。

具体模型结构的搭建:

1.模型输入大小设定主要是由于此模型最初为了应对一个小型比赛,因此输入大小采用了竞赛中的图像大小。

2.网络结构靠感觉居多,未进行对比实验。

3.网络的部分卷积层的设定有意背离目前一些分类网络的设定上:

(1)S2的Conv或者Pooling放在了靠后位置,并采用大kernel,希望能够尽可能保留一些细节;

(2)另外也是处于验证的目的采用了Pixel Shuffle————发现貌似比bilinear显存占用少一些;

(3)Batchsize较小,尝试GroupNorm;

(3)数据集为超分辨率数据集经过多次缩放和裁剪得到————多尺度训练;

(4)去噪PSNR范围限定在在10-40;

4.整体思路参照Beyond A Gaussian Denoiser论文(DnCNN)————具体网络结构尝试大换血。

5.数据集采用DIV2K数据集。

6.个人GPU算力及显存大小的限制,实际条件不允许尝试更深的网络。

7.Result(————目前估计如果详细测试,和DnCNN相比应该差别没有很明显,但盲去噪效果应该会好一些):

(1)第一个epoch后测试集平均PSNR就有26.85,平均SSIM为0.833;

部分去噪效果:

image image image

或者您发现了一些问题或建议,请留言,谢谢。

cnn_denoise_pytorch's People

Contributors

m0redr1nk avatar

Watchers

James Cloos avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.