/SemanticSoftSegmentation

Spectral segmentation described in Aksoy et al., "Semantic Soft Segmentation", ACM TOG (Proc. SIGGRAPH), 2018

Primary LanguageMATLABOtherNOASSERTION

Semantic Soft Segmentation

This repository includes the spectral segmentation approach presented in

Yagiz Aksoy, Tae-Hyun Oh, Sylvain Paris, Marc Pollefeys and Wojciech Matusik, "Semantic Soft Segmentation", ACM Transactions on Graphics (Proc. SIGGRAPH), 2018 

The network for semantic feature generation can be found [here].

Please refer to the [project page] for more information and example data.

The Superpixels class requires [ImageGraphs].

License and citation

This toolbox is provided for academic use only. If you use this code, please cite our paper:

@ARTICLE{sss,
author={Ya\u{g}{\i}z Aksoy and Tae-Hyun Oh and Sylvain Paris and Marc Pollefeys and Wojciech Matusik},
title={Semantic Soft Segmentation},
journal={ACM Transactions on Graphics (Proc. SIGGRAPH)},
year={2018},
pages = {72:1-72:13},
volume = {37},
number = {4}
}

Credit

Parts of this implementation are taken from

Anat Levin, Alex Rav-Acha, Dani Lischinski, "Spectral Matting", IEEE TPAMI, 2008

The original source code for Spectral Matting can be found [here].