Bilateral Space Video Segmentation

Nicolas Maerki, Federico Perazzi, Oliver Wang, Alexander Sorkine-Hornung; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 743-751

Abstract


In this work, we propose a novel approach to video segmentation that operates in bilateral space. We design a new energy on the vertices of a regularly sampled spatio-temporal bilateral grid, which can be solved efficiently using a standard graph cut label assignment. Using a bilateral formulation, the energy that we minimize implicitly approximates long-range, spatio-temporal connections between pixels while still containing only a small number of variables and only local graph edges. We compare to a number of recent methods, and show that our approach achieves state-of-the-art results on multiple benchmarks in a fraction of the runtime. Furthermore, our method scales linearly with image size, allowing for interactive feedback on real-world high resolution video.

Related Material


[pdf]
[bibtex]
@InProceedings{Maerki_2016_CVPR,
author = {Maerki, Nicolas and Perazzi, Federico and Wang, Oliver and Sorkine-Hornung, Alexander},
title = {Bilateral Space Video Segmentation},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2016}
}