Coder Social home page Coder Social logo

tingmanyan / sdr Goto Github PK

View Code? Open in Web Editor NEW
110.0 3.0 37.0 3.71 MB

Code for 'Segment-based Disparity Refinement with Occlusion Handling for Stereo Matching'

License: GNU General Public License v3.0

CMake 0.62% Batchfile 1.02% Shell 0.99% C++ 95.44% C 1.93%
stereo-matching disparity-map disparity-refinement depth

sdr's Introduction

Segment-based Disparity Refinement with Occlusion Handling for Stereo Matching

Please cite the [paper] if you find it useful

@ARTICLE{8661596, 
author={T. {Yan} and Y. {Gan} and Z. {Xia} and Q. {Zhao}}, 
journal={IEEE Transactions on Image Processing}, 
title={Segment-Based Disparity Refinement With Occlusion Handling for Stereo Matching}, 
year={2019}, 
volume={28}, 
number={8}, 
pages={3885-3897}, 
doi={10.1109/TIP.2019.2903318}, 
ISSN={1057-7149}, 
month={Aug},}

Workflow

SDR

Dependency

-OpenCV 3
-Eigen

Usage

mkdir build
cd build
- on Windows:
  cmake .. -G "Visual Studio 15 2017 Win64" -T host=x64
  open and compile fdr.sln using Visual Studio 2017
- on Mac & Ubuntu:
  cmake ..
  make -j4

To run the demo

  • on Windows:
    double-click demo.bat
  • on Mac & Ubuntu:
    ./demo.sh

You will obtain the same results as in our paper on Windows. Results on Mac is silghtly different due to the graph-based segmentation generates different number of superpixels on Mac and Windows.

sdr's People

Contributors

tingmanyan avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar

sdr's Issues

How to draw the superpixels?

It seems that one of the difference if this paper with localexp is that you use superpixels. But I wonder how to draw out the superpixels edge? Or you just use the mean value of the superpixel so the segmentation accuraccy do not affect too much?

Reference Papers and Parameters explanations

Hi,

I'm interested in understanding your work.

Can you provide some references to the papers that it is implemented from?

It would be nice to have some explanation of the parameters in the parameters file.

Hello,when I run main.cpp with vs2017,I get a exception in FastDR.cpp

I can run demo.bat with no error,but when I run main.cpp with my own image,I get a exception in FastDR.cpp 186 line.the wrong code is the last line:
for (int i = 0; i < height; i++)
for (int j = 0; j < width; j++) {
tl = spx.at(i, j);
int disp = D.at(i, j);
data_term[tl][disp / bins_width] += 1;
}
Wish you can give me some helps.

how can I code for vs2017

I look for your codes(fdr/main.cpp),which is for KITTI dataset.
Now i want to refine my own disparity(CV_8U),how to modify this ?

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.