Real-Time Coarse-to-Fine Topologically Preserving Segmentation

Jian Yao, Marko Boben, Sanja Fidler, Raquel Urtasun; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 2947-2955

Abstract


In this paper, we tackle the problem of unsupervised segmentation in the form of superpixels. Our main emphasis is on speed and accuracy. We build on [31] to define the problem as a boundary and topology preserving Markov random field. We propose a coarse to fine optimization technique that speeds up inference in terms of the number of updates by an order of magnitude. Our approach is shown to outperform [31] while employing a single iteration. We evaluate and compare our approach to state-of-the-art superpixel algorithms on the BSD and KITTI benchmarks. Our approach significantly outperforms the baselines in the segmentation metrics and achieves the lowest error on the stereo task.

Related Material


[pdf]
[bibtex]
@InProceedings{Yao_2015_CVPR,
author = {Yao, Jian and Boben, Marko and Fidler, Sanja and Urtasun, Raquel},
title = {Real-Time Coarse-to-Fine Topologically Preserving Segmentation},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2015}
}