Exact inference in multi-label CRFs with higher order cliques

This paper addresses the problem of exactly inferring the maximum a posteriori solutions of discrete multi-label MRFs or CRFs with higher order cliques. We present a framework to transform special classes of multi-label higher order functions to submodular second order boolean functions (referred to as F2 s ), which can be minimized exactly using graph cuts and we characterize those classes. The basic idea is to use two or more boolean variables to encode the states of a single multi-label variable. There are many ways in which this can be done and much interesting research lies in finding ways which are optimal or minimal in some sense. We study the space of possible encodings and find the ones that can transform the most general class of functions to F2 s . Our main contributions are two-fold. First, we extend the subclass of submodular energy functions that can be minimized exactly using graph cuts. Second, we show how higher order potentials can be used to improve single view 3D r...

• Type: Conference
• Year: 2008
• Where: CVPR
• Authors: Srikumar Ramalingam, Pushmeet Kohli, Karteek Alahari, Philip H. S. Torr
• Keywords: Boolean Variables, Computer Vision, CVPR 2008, Graph Cuts, Order Boolean Functions, Order Energy Functions, Submodular Energy Functions