Git Product home page Git Product logo

realtimespecularhighlightremoval's Introduction

Real-Time High-Quality Specular Highlight Removal Using Efficient Pixel Clustering

by Antonio Souza, Márcio Macedo, Verônica Nascimento and Bruno Oliveira.

Introduction

This is a C++/OpenCV/CUDA application for real-time specular highlight removal in still images. Technical details are provided in our SIBGRAPI 2018 paper.

To enable real-time specular highlight removal using GPU, uncomment the line #define REMOVE_SPECULAR_HIGHLIGHT_USING_CUDA in include/SpecularHighlightRemoval/useCUDA.h.

Citation

The provided source codes are in public domain and can be downloaded for free. If this work is useful for your research, please consider citing:

@inproceedings{Macedo2018,
author={Souza, Antonio and Macedo, Marcio and Nascimento, Veronica and Oliveira, Bruno},
title={Real-Time High-Quality Specular Highlight Removal Using Efficient Pixel Clustering},
booktitle={Proceedings of the 31st Conference on Graphics, Patterns and Images (SIBGRAPI)},
year={2018},
pages={56-63},
doi={10.1109/SIBGRAPI.2018.00014},
publisher={IEEE}
}

realtimespecularhighlightremoval's People

Contributors

marciocerqueira 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

Watchers

 avatar  avatar  avatar

realtimespecularhighlightremoval's Issues

Corrupted output

Thank you for sharing your great work!
I am trying to run it but the output seems to be corrupted as shown in the attached screenshot. Do you have any recommendation?
Thanks!

rm

It seems difficult to process white region.

Thank you very much for your paper and code. It can process well on the images which are showed in your paper. However, I use it to process my images which has much white region, such as white wall, white desk, white car and so on. It always turn white into black or color like black. I try to change the parameters but nothing. Could you give me some advice?

Update ReadMe.txt

Hi Márcio,

SIBGRAPI proceedings have been published. Could you add the full citation to the ReadMe.txt so people can find and cite your work easier?

A. Carlos dos Santos Souza, M. Cerqueira de Farias Macedo, V. Paixao do Nascimento, and B. Santos Oliveira, “Real-Time High-Quality Specular Highlight Removal Using Efficient Pixel Clustering,” in 2018 31st SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), 2018 [Online]. Available: http://dx.doi.org/10.1109/SIBGRAPI.2018.00014

Also here it is in IEEE Xplore.

https://ieeexplore.ieee.org/document/8614311

how to obtain a good result?

Thank you for sharing your code. I think the shadow removal is one of the most challenge works in vision field.

Based on your code, I am trying to solve my problems

input image
image

output image
image

As you can see, the road area is gone and the shadow still exists. How can I improve the result? Could you advise me?

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.