Partial Enumeration and Curvature Regularization

Carl Olsson, Johannes Ulen, Yuri Boykov, Vladimir Kolmogorov

In International Conference on Computer Vision (ICCV), Sydney, Australia, December, 2013.

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. This 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.

Our 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.


WHOLE PAPER: pdf file (0.4Mb)
- more details can be found in tech. report arXiv:1303.1749v2

[an error occurred while processing this directive]