Giter VIP home page Giter VIP logo

kasertim / imagespirit Goto Github PK

View Code? Open in Web Editor NEW

This project forked from bittnt/imagespirit

0.0 2.0 0.0 3.66 MB

ImageSpirit Project for SIGGRAPH 2015 demo, ACM TOG 2014 "ImageSpirit: Verbal Guided Image Parsing". CVPR 2014 "Dense Semantic Image Segmentation with Objects and Attributes"

Home Page: http://mmcheng.net/imagespirit/

C++ 80.93% C 1.17% MATLAB 0.26% HTML 15.04% JavaScript 1.97% CSS 0.62% Batchfile 0.01%

imagespirit's Introduction

ImageSpirit Source code

This is the software bundle "ImageSpirit", created and maintained by: Shuia Zheng [email protected] Ming Ming Cheng [email protected]

  1. Dependencies

This code is tested under Windows 8.1 system with Visual Studio 2010 and Visual Studio 2012. You are required to have OpenCV 2.4 and Qt 4.8 installed. For Qt 4.8, you may find BlueGo will be useful to help installing Qt4.8. The code may not work well with Qt 5.0+ at the moment.

https://bitbucket.org/Vertexwahn/bluego

  1. Build Process

You open the sln file with visual studio, then compile it, if you set up all the paths.

  1. Functions

This software contains the implementation of using factorial DenseCRF in the application of semantic image segmentation. Further image editing application can be done with the CmmCode library.

  1. Reference

If you found the software is useful, please refer to:

@article{cheng2014imagespirit,
	author = {Cheng, Ming-Ming and Zheng, Shuai and Lin, Wen-Yan and Vineet, Vibhav and Sturgess, Paul and Crook, Nigel and Mitra, Niloy J. and Torr, Philip},
	title = {ImageSpirit: Verbal Guided Image Parsing},
	journal = {ACM Trans. Graph.},
	issue_date = {November 2014},
	volume = {34},
	number = {1},
	month = dec,
	year = {2014},
	issn = {0730-0301},
	pages = {3:1--3:11},
	articleno = {3},
	numpages = {11},
	doi = {10.1145/2682628},
	acmid = {2682628},
}
@inproceedings{DenseObjAtt_CVPR2014,
author = {Shuai Zheng and Ming-Ming Cheng and Jonathan Warrell and Paul Sturgess and Vibhav Vineet and Carsten Rother and Philip H. S. Torr},
title = {Dense Semantic Image Segmentation with Objects and Attributes},
booktitle = { IEEE International Conference on Computer Vision and Pattern Recognition (CVPR)},
address = {Columbus, Ohio, United States},
year = {2014}
}
  1. License

This software is free for non-commercial use. Any commercial use is strictly prohibited.

This software has used DenseCRF software from Philipp Krähenbühl et al. and Permutohedral lattice software from Andrew Adams et al. Please also refer to their publications if this software is in use. http://www.philkr.net/ http://people.csail.mit.edu/abadams/

Some part of the higher order potential implementation has also related to the implementation from Vibhav Vineet et al. Please refer to http://www.robots.ox.ac.uk/~tvg/publications.php

You can use the unary potential from ALE. Stable version: http://www.robots.ox.ac.uk/~phst/ale.htm Latest version: http://www.inf.ethz.ch/personal/ladickyl/ALE.zip

imagespirit's People

Contributors

bittnt avatar mingmingcheng avatar

Watchers

James Cloos avatar Yi-Ting Chen 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.