Code Monkey home page Code Monkey logo

fastderain's Introduction

FastDeRain

The Matlab implementation and video results of FastDeRain

Author Tai-Xiang Jiang
E-mail [email protected]

Brief description

This folder contains the implementation of the algorithm for video rain streaks removal named FastDeRain.

Main files:

File name Description
Demo_FastDerain.m Demo of FastDeRain, implemented on CPU
Demo_FastDerain_GPU_version.m Demo of FastDeRain, implemented on GPU
Demo_FastDerain_Oblique.m Demo of FastDeRain for oblique rain streaks, implemented on GPU

Refference

An early material of the this menthod is:
Tai-Xiang Jiang, Ting-Zhu Huang, Xi-Le Zhao, Liang-Jian Deng, Yao Wang; ''A Novel Tensor-Based Video Rain Streaks Removal Approach via Utilizing Discriminatively Intrinsic Priors'' The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 4057-4066. [PDF]

The preprint of the extended journal version:
Tai-Xiang Jiang, Ting-Zhu Huang, Xi-Le Zhao, Liang-Jian Deng, Yao Wang; “Fastderain: A novel video rain streak removal method using directional gradient priors,” ArXiv e-prints, 2018. [arXiv] [PDF]

If you use this code, please cite

  @InProceedings{Jiang_2017_CVPR,
     author    = {Jiang, Tai-Xiang and Huang, Ting-Zhu and Zhao, Xi-Le and Deng, Liang-Jian and Wang, Yao},
     title     = {A Novel Tensor-Based Video Rain Streaks Removal Approach via Utilizing Discriminatively Intrinsic Priors},
     booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
     month     = {July},
     pages     = {2818-2827},
     doi       = {10.1109/CVPR.2017.301},
     year      = {2017}}

  @article{Jiang2018FastDeRain,
     author    = {Jiang, Tai-Xiang and Huang, Ting-Zhu and Zhao, Xi-Le and Deng, Liang-Jian and Wang, Yao},
     title     = {FastDeRain: A Novel Video Rain Streak Removal Method Using Directional Gradient Priors},
     journal   = {ArXiv e-prints},
     eprint    = {1803.07487},
     year      = {2018},
     url       = {https://arxiv.org/pdf/1803.07487.pdf}}

Meanwhile, our method for single image rain streaks removal are detailed in this article:
Liang-Jian Deng, Ting-Zhu Huang, Xi-Le Zhao, and Tai-Xiang Jiang; "A directional global sparse model for single image rain removal." Applied Mathematical Modelling (2018).
Corresponding codes are compressed in the file "UGSM_v3.0.zip".

  @article{deng2018directional,
     title     = {A directional global sparse model for single image rain removal},
     author    = {Deng, Liang-Jian and Huang, Ting-Zhu and Zhao, Xi-Le and Jiang, Tai-Xiang},
     journal   = {Applied Mathematical Modelling},
     volume    = {59},
     pages     = {662 -- 679},
     year      = {2018},
     publisher = {Elsevier}
     doi       = {10.1016/j.apm.2018.03.001}}

Other

(The .p files will be replaced by .m files as soon as possible.)
Date: 03/03/2018

fastderain's People

Contributors

taixiangjiang avatar uestctensorgroup avatar

Watchers

James Cloos avatar superchao 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.