What energy functions can be minimized via graph cuts?

In the last few years, several new algorithms based on graph cuts have been developed to solve energy minimization problems in computer vision. Each of these techniques constructs a graph such that the minimum cut on the graph also minimizes the energy. Yet, because these graph constructions are complex and highly specific to a particular energy function, graph cuts have seen limited application to date. In this paper, we give a characterization of the energy functions that can be minimized by graph cuts. Our results are restricted to functions of binary variables. However, our work generalizes many previous constructions and is easily applicable to vision problems that involve large numbers of labels, such as stereo, motion, image restoration, and scene reconstruction. We give a precise characterization of what energy functions can be minimized using graph cuts, among the energy functions that can be written as a sum of terms containing three or fewer binary variables. We also provide a general-purpose construction to minimize such an energy function. Finally, we give a necessary condition for any energy function of binary variables to be minimized by graph cuts. Researchers who are considering the use of graph cuts to optimize a particular energy function can use our results to determine if this is possible and then follow our construction to create the appropriate graph. A software implementation is freely available.

[1]  Harold S. Stone,et al.  Multiprocessor Scheduling with the Aid of Network Flow Algorithms , 1977, IEEE Transactions on Software Engineering.

[2]  L. Lovász,et al.  Geometric Algorithms and Combinatorial Optimization , 1981 .

[3]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Tomaso Poggio,et al.  Computational vision and regularization theory , 1985, Nature.

[5]  William H. Cunningham,et al.  Minimum cuts, modular functions, and matroid polyhedra , 1985, Networks.

[6]  Andrew V. Goldberg,et al.  A new approach to the maximum flow problem , 1986, STOC '86.

[7]  G. B. Smith,et al.  Preface to S. Geman and D. Geman, “Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images” , 1987 .

[8]  J. G. Pierce,et al.  Geometric Algorithms and Combinatorial Optimization , 2016 .

[9]  D. Greig,et al.  Exact Maximum A Posteriori Estimation for Binary Images , 1989 .

[10]  Ramesh C. Jain,et al.  Using Dynamic Programming for Solving Variational Problems in Vision , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  藤重 悟.  Submodular functions and optimization , 1991 .

[12]  Myunghwan Kim,et al.  Optimal Task Assignment in Linear Array Networks , 1992, IEEE Trans. Computers.

[13]  Mihalis Yannakakis,et al.  The complexity of multiway cuts (extended abstract) , 1992, STOC '92.

[14]  Ravindra K. Ahuja,et al.  Network Flows: Theory, Algorithms, and Applications , 1993 .

[15]  Stan Z. Li,et al.  Markov Random Field Modeling in Computer Vision , 1995, Computer Science Workbench.

[16]  Ioannis Milis.  Task Assignment in Distributed Systems Using Network Flow Methods , 1995, Combinatorics and Computer Science.

[17]  Ingemar J. Cox,et al.  A maximum-flow formulation of the N-camera stereo correspondence problem , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[18]  Davi Geiger,et al.  Occlusions, Discontinuities, and Epipolar Lines in Stereo , 1998, ECCV.

[19]  Davi Geiger,et al.  Segmentation by grouping junctions , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[20]  Olga Veksler,et al.  Markov random fields with efficient approximations , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

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

[22]  Richard Szeliski,et al.  An Experimental Comparison of Stereo Algorithms , 1999, Workshop on Vision Algorithms.

[23]  Carlo Tomasi,et al.  Multiway cut for stereo and motion with slanted surfaces , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[24]  Alexander Schrijver,et al.  A Combinatorial Algorithm Minimizing Submodular Functions in Strongly Polynomial Time , 2000, J. Comb. Theory, Ser. B.

[25]  John W. Fisher,et al.  Incorporating Spatial Priors into an Information Theoretic Approach for fMRI Data Analysis , 2000, MICCAI.

[26]  Marie-Pierre Jolly,et al.  Interactive Organ Segmentation Using Graph Cuts , 2000, MICCAI.

[27]  Satoru Iwata,et al.  A combinatorial, strongly polynomial-time algorithm for minimizing submodular functions , 2000, STOC '00.

[28]  R. Zabih,et al.  Exact voxel occupancy with graph cuts , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[29]  Satoru Iwata,et al.  A combinatorial strongly polynomial algorithm for minimizing submodular functions , 2001, JACM.

[30]  Marie-Pierre Jolly,et al.  Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[31]  Marie-Pierre Jolly,et al.  Interactive Graph Cuts for Optimal Boundary and Region Segmentation of Objects in N-D Images , 2001, ICCV.

[32]  Vladimir Kolmogorov,et al.  Computing visual correspondence with occlusions using graph cuts , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[33]  Nikos Paragios,et al.  A MRF-based approach for real-time subway monitoring , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[34]  Christoph Schnörr,et al.  Image Labeling and Grouping by Minimizing Linear Functionals over Cones , 2001, EMMCVPR.

[35]  D. Scharstein,et al.  A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms , 2001, Proceedings IEEE Workshop on Stereo and Multi-Baseline Vision (SMBV 2001).

[36]  Vladimir Kolmogorov,et al.  Multi-camera Scene Reconstruction via Graph Cuts , 2002, ECCV.

[37]  José M. N. Leitão,et al.  The ZπM algorithm: a method for interferometric image reconstruction in SAR/SAS , 2002, IEEE Trans. Image Process..

[38]  Vladimir Kolmogorov,et al.  Visual correspondence using energy minimization and mutual information , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[39]  Vladimir Kolmogorov,et al.  Computing geodesics and minimal surfaces via graph cuts , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[40]  Irfan A. Essa,et al.  Graphcut textures: image and video synthesis using graph cuts , 2003, ACM Trans. Graph..

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

[42]  Carlo Tomasi,et al.  Surfaces with occlusions from layered stereo , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[43]  Vladimir Kolmogorov,et al.  An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision , 2004, IEEE Trans. Pattern Anal. Mach. Intell..

[44]  R. Zabih,et al.  What energy functions can be minimized via graph cuts , 2004 .

[45]  Sébastien Roy,et al.  Stereo Without Epipolar Lines: A Maximum-Flow Formulation , 1999, International Journal of Computer Vision.

[46]  Stephen T. Barnard,et al.  Stochastic stereo matching over scale , 1989, International Journal of Computer Vision.

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