Giter Club home page Giter Club logo

2015-jmiv-texture-synthesis's Introduction

2015-JMIV-texture-synthesis

Source code of the article

G. Tartavel, Y. Gousseau, G. Peyré. Variational Texture Synthesis with Sparsity and Spectrum Constraints. Journal of Mathematical Imaging and Vision, 52(1), pp. 124–144, 2015.

Examples of syntheses

Description

This is an implementation of our texture synthesis algorithm. It is an exemplar-base approach: the goal is to generate a new texture from a sample image.

More details about the algorithm, the variational approach and the sparsity constraints are available in our publications.

This implementation is in Matlab and is composed of a set of *.m files. Documentation is available in Matlab for each function "FCN" by typing:

help FCN

Usage

Compile the MEX functions. You can use the Makefile provided in 'mex/':

$ cd mex/ && make

Launch Matlab and execute the editable script or the interactive script:

LaunchExample; LaunchInteractive;

You can use the matlab 'help' command to explore the files:

help Synthesis

Note about the Image Processing toolbox in Matlab. If you don't have it, replacement functions can be found in 'improc_toolbox/'. You can for example add this directory to Matlab's search path:

addpath('improc_toolbox');

Note about the SPAMS toolbox. The SPAMS toolbox provide a more efficient dictionary learning step. It is available here:

File descriptions

  • README.txt : this information file

  • *.png : some images to try the algorithm and the toolboxes

  • *.mat : some dictionary already learned (to save time)

  • LaunchCopymap.m : editable script to analyze the innovation capacity

  • LaunchExample.m : editable script to launch a synthesis

  • LaunchInteractive.m : interactive script to launch a synthesis

  • Synthesis.m : implements our synthesis algorithm

  • Patches.m : interface for patches in an image

  • Histogram.m : provides histogram tools (histogram transfer)

  • Sparsity.m : provides sparse decomposition functions

  • Spectrum.m : provides Fourier spectrum tools (spectrum transfer)

  • mex/ : contains the C++ implementation of some MEX functions

  • mex/Makefile : useful to compile/generate the MEX files

  • improc_toolbox/ : contains a basic implementation of some function provided in Matlab's Image Processing toolbox

Copyright (c) 2015 Guillaume Tartavel

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.