Convex Relaxation for Multilabel Problems with Product Label Spaces
Convex relaxations for continuous multilabel problems have attracted a lot of interest recently [1,2,3,4,5]. Unfortunately, in previous methods, the runtime and memory requirements scale linearly in the total number of labels, making them very inefficient and often unapplicable for problems with higher dimensional label spaces. In this paper, we propose a reduction technique for the case that the label space is a product space, and introduce proper regularizers. The resulting convex relaxation requires orders of magnitude less memory and computation time than previously, which enables us to apply it to large-scale problems like optic flow, stereo with occlusion detection, and segmentation into a very large number of regions. Despite the drastic gain in performance, we do not arrive at less accurate solutions than the original relaxation. Using the novel method, we can for the first time efficiently compute solutions to the optic flow functional which are within provable bounds of typically 5% of the global optimum.
KeywordsConvex Relaxation Convex Envelope Label Space Occlusion Detection Occlude Pixel
Unable to display preview. Download preview PDF.
- 1.Lellmann, J., Becker, F., Schnörr, C.: Convex optimization for multi-class image labeling with a novel family of total variation based regularizers. In: IEEE International Conference on Computer Vision (ICCV) (2009)Google Scholar
- 4.Pock, T., Chambolle, A., Bischof, H., Cremers, D.: A convex relaxation approach for computing minimal partitions. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 810–817 (2009)Google Scholar
- 5.Zach, C., Gallup, D., Frahm, J., Niethammer, M.: Fast global labeling for real-time stereo using multiple plane sweeps. In: Vision, Modeling and Visualization, pp. 243–252 (2009)Google Scholar
- 7.Kindermann, R., Snell, J.: Markov Random Fields and Their Applications. American Mathematical Society, Providence (1980)Google Scholar
- 8.Boykov, Y., Kolmogorov, V.: Computing geodesics and minimal surfaces via graph cuts. In: IEEE International Conference on Computer Vision (ICCV), pp. 26–33 (2003)Google Scholar
- 9.Greig, D., Porteous, B., Seheult, A.: Exact maximum a posteriori estimation for binary images. J. Royal Statistics Soc. 51, 271–279 (1989)Google Scholar
- 12.Schlesinger, D., Flach, B.: Transforming an arbitrary min-sum problem into a binary one. Technical report, Dresden University of Technology (2006)Google Scholar
- 16.Popov, L.: A modification of the arrow-hurwicz method for search of saddle points. Math. Notes 28, 845–848 (1980)Google Scholar