--- res: bibo_abstract: - "Energies with high-order non-submodular interactions have been shown to be very useful in vision due to their high modeling power. Optimization of such energies, however, is generally NP-hard. A naive approach that works for small problem instances is exhaustive search, that is, enumeration of all possible labelings of the underlying graph. We propose a general minimization approach for large graphs based on enumeration of labelings of certain small patches. \r\nThis partial enumeration technique reduces complex high-order energy formulations to pairwise Constraint Satisfaction Problems with unary costs (uCSP), which can be efficiently solved using standard methods like TRW-S. Our approach outperforms a number of existing state-of-the-art algorithms on well known difficult problems (e.g. curvature regularization, stereo, deconvolution); it gives near global minimum and better speed. \r\nOur main application of interest is curvature regularization. In the context of segmentation, our partial enumeration technique allows to evaluate curvature directly on small patches using a novel integral geometry approach.\r\n@eng" bibo_authorlist: - foaf_Person: foaf_givenName: Carl foaf_name: Olsson, Carl foaf_surname: Olsson - foaf_Person: foaf_givenName: Johannes foaf_name: Ulen, Johannes foaf_surname: Ulen - foaf_Person: foaf_givenName: Yuri foaf_name: Boykov, Yuri foaf_surname: Boykov - foaf_Person: foaf_givenName: Vladimir foaf_name: Kolmogorov, Vladimir foaf_surname: Kolmogorov foaf_workInfoHomepage: http://www.librecat.org/personId=3D50B0BA-F248-11E8-B48F-1D18A9856A87 bibo_doi: 10.1109/ICCV.2013.365 dct_date: 2014^xs_gYear dct_language: eng dct_publisher: IEEE@ dct_title: Partial enumeration and curvature regularization@ ...