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 Fs 2), 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 Fs 2. 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 reconstruction results. We believe that our work on exact minimization of higher order energy functions will lead to similar improvements in solutions of other labelling problems.

[1]  P. L. Ivanescu Some Network Flow Problems Solved with Pseudo-Boolean Programming , 1965 .

[2]  Alain Billionnet,et al.  Maximizing a supermodular pseudoboolean function: A polynomial algorithm for supermodular cubic functions , 1985, Discret. Appl. Math..

[3]  Giorgio Gallo,et al.  On the supermodular knapsack problem , 1989, Math. Program..

[4]  Olga Veksler,et al.  Fast approximate energy minimization via graph cuts , 2001, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[5]  W. Freeman,et al.  Generalized Belief Propagation , 2000, NIPS.

[6]  Martin J. Wainwright,et al.  Tree-based reparameterization for approximate inference on loopy graphs , 2001, NIPS.

[7]  Endre Boros,et al.  Pseudo-Boolean optimization , 2002, Discret. Appl. Math..

[8]  Hiroshi Ishikawa,et al.  Exact Optimization for Markov Random Fields with Convex Priors , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Dale Purves,et al.  Image/source statistics of surfaces in natural scenes , 2003, Network.

[10]  B. Zalesky Efficient Determination of Gibbs Estimators with Submodular Energy Functions , 2003, math/0304041.

[11]  D. Schlesinger,et al.  Best Labeling Search for a Class of Higher Order Gibbs Models 1 , 2004 .

[12]  Vladimir Kolmogorov,et al.  What energy functions can be minimized via graph cuts? , 2002, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Daniel P. Huttenlocher,et al.  Efficient Belief Propagation for Early Vision , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[14]  Shmuel Peleg,et al.  Seamless Image Stitching in the Gradient Domain , 2004, ECCV.

[15]  Richard Szeliski,et al.  A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms , 2001, International Journal of Computer Vision.

[16]  Michael J. Black,et al.  Fields of Experts: a framework for learning image priors , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[17]  Andrew Blake,et al.  Digital tapestry [automatic image synthesis] , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[18]  William T. Freeman,et al.  Constructing free-energy approximations and generalized belief propagation algorithms , 2005, IEEE Transactions on Information Theory.

[19]  Daniel Freedman,et al.  Energy minimization via graph cuts: settling what is possible , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[20]  D. Schlesinger,et al.  TRANSFORMING AN ARBITRARY MINSUM PROBLEM INTO A BINARY ONE , 2006 .

[21]  Alexei A. Efros,et al.  Recovering Surface Layout from an Image , 2007, International Journal of Computer Vision.

[22]  Michael J. Black,et al.  Efficient Belief Propagation with Learned Higher-Order Markov Random Fields , 2006, ECCV.

[23]  Brian Potetz,et al.  Efficient Belief Propagation for Vision Using Linear Constraint Nodes , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[24]  Dmitrij Schlesinger,et al.  Exact Solution of Permuted Submodular MinSum Problems , 2007, EMMCVPR.

[25]  Olga Veksler Graph Cut Based Optimization for MRFs with Truncated Convex Priors , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[26]  Vladimir Kolmogorov,et al.  Optimizing Binary MRFs via Extended Roof Duality , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[27]  Pushmeet Kohli,et al.  Robust Higher Order Potentials for Enforcing Label Consistency , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[28]  Pushmeet Kohli,et al.  Graph Cuts for Minimizing Robust Higher Order Potentials , 2008 .

[29]  James B. Orlin,et al.  A faster strongly polynomial time algorithm for submodular function minimization , 2007, Math. Program..