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 defifine the problem as a boundary and topology preserving Markov random fifield. We propose a coarse to fifine 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 signifificantly outperforms the baselines in the segmentation metrics and achieves the lowest error on the stereo task.