Tighter Relaxations for Higher-Order Models Based on Generalized Roof Duality
Many problems in computer vision can be turned into a large-scale boolean optimization problem, which is in general NP-hard. In this paper, we further develop one of the most successful approaches, namely roof duality, for approximately solving such problems for higher-order models. Two new methods that can be applied independently or in combination are investigated. The first one is based on constructing relaxations using generators of the submodular function cone. In the second method, it is shown that the roof dual bound can be applied in an iterated way in order to obtain a tighter relaxation. We also provide experimental results that demonstrate better performance with respect to the state-of-the-art, both in terms of improved bounds and the number of optimally assigned variables.
Unable to display preview. Download preview PDF.
- 2.Boykov, Y., Kolmogorov, V.: Computing geodesics and minimal surfaces via graph cuts. In: Int. Conf. Computer Vision, Nice, France (2003)Google Scholar
- 4.Schoenemann, T., Kahl, F., Cremers, D.: Curvature regularity for region-based image segmentation and inpainting: A linear programming relaxation. In: Int. Conf. Computer Vision, Kyoto, Japan (2009)Google Scholar
- 10.Kolmogorov, V.: Generalized roof duality and bisubmodular functions. In: Neural Information Processing Systems (2010)Google Scholar
- 11.Kahl, F., Strandmark, P.: Generalized roof duality for pseudo-boolean optimization. In: Int. Conf. Computer Vision, Barcelona, Spain (2011)Google Scholar
- 12.Kahl, F., Strandmark, P.: Generalized roof duality. Discrete Appl. Math. (to appear, 2012)Google Scholar
- 15.Komodakis, N., Paragios, N.: Beyond pairwise energies: Efficient optimization for higher-order MRFs. In: Conf. Computer Vision and Pattern Recognition, Miami, USA (2009)Google Scholar
- 16.Strandmark, P., Kahl, F.: Parallel and distributed graph cuts by dual decomposition. In: Conf. Computer Vision and Pattern Recognition, San Francisco, USA (2010)Google Scholar
- 19.Werner, T.: High-arity interactions, polyhedral relaxations, and cutting plane algorithm for MAP-MRF. In: Conf. Computer Vision and Pattern Recognition, Anchorage, USA (2008)Google Scholar
- 21.Freedman, D., Drineas, P.: Energy minimization via graph cuts: Settling what is possible. In: Conf. Computer Vision and Pattern Recognition, San Diego, USA (2005)Google Scholar
- 25.Fix, A., Grubner, A., Boros, E., Zabih, R.: A graph cut algorithm for higher-order markov random fields. In: Int. Conf. Computer Vision, Barcelona, Spain (2011)Google Scholar