Skip to content
C++ Implementation of Image Super-Resolution using Convolutional Neural Network
C C++ Shell MATLAB
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
Pictures changes log Dec 31, 2015
Result Delete LumaCubic.bmp Dec 31, 2015
_Old_Version Update README.md Jan 16, 2016
LICENSE Initial commit Dec 31, 2015
README.md Update README.md Dec 31, 2015
SRCNN changes log Dec 31, 2015
SRCNN.cpp changes log Dec 31, 2015
SRCNN.o changes log Dec 31, 2015
convdata.h changes log Dec 31, 2015
opencv.sh Update opencv.sh Dec 31, 2015
srcnn.sh Update srcnn.sh Dec 31, 2015

README.md

SRCNN_Cpp

C++ Implementation of Image Super-Resolution using Convolutional Neural Network

Introduction

SRCNN_Cpp is a C++ Implementation of Image Super-Resolution using SRCNN which is proposed by Chao Dong in 2014.

  • If you want to find the details of SRCNN algorithm, please read the paper:

    Chao Dong, Chen Change Loy, Kaiming He, Xiaoou Tang. Learning a Deep Convolutional Network for Image Super-Resolution, in Proceedings of European Conference on Computer Vision (ECCV), 2014

  • If you want to download the training code(caffe) or test code(Matlab) for SRCNN, please open your browse and visit http://mmlab.ie.cuhk.edu.hk/projects/SRCNN.html for more details.

  • And thank you very much for Chao's work in SRCNN.

License

SRCNN_Cpp is released under the GPL v2 License (refer to the LICENSE file for details).

Contents

  1. Requirements
  2. Compile
  3. Demo

Requirements

  1. You need to install OpenCV2+ or OpenCV3+ in your computer.

    OpenCV download site: http://opencv.org/

  2. You also need to install pkg-config.

  3. And we really need g++ which is already installed in almost all Linux systems.

Note: we do not need Caffe in your system!

Our SRCNN_Cpp is developed in fc22 x64_86 system with g++-5.3 and OpenCV 3.0.0.

Compile

You can compile the C/C++ files on the command line in your Linux system.

$ ./opencv.sh SRCNN

If the compile is successful, you will see the information below:

  [Compile] Complete -- SRCNN.o has created!
  [Linking] Complete -- SRCNN has created!

Demo

You can run the following command to test the demo program.

./srcnn.sh Pictures/butterfly_GT.bmp

And the output images is save in the path: ./Output/

If you want to test your own images, please run the following command:

./srcnn.sh Path_To_Your_Own_Image

Enjoy yourself~

You can’t perform that action at this time.