Markov random fields with efficient approximations
Yuri Y. Boykov, Olga Veksler, Ramin Zabih A · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2002
Markov Random Fields (MRFs) can be used for a wide variety of vision problems. In this paper we focus on MRFs with two-valued clique potentials, which form a generalized Potts model. We show that the maximum a posteriori estimate of such an MRF can be obtained by solving a multiway minimum cut problem on a graph. We develop efficient algorithms for computing good approximations to the minimum multiway, cut. The visual correspondence problem can be formulated as an MRF in our framework; this yields quite promising results on real data with ground truth. We also apply our techniques to MRFs with linear clique potentials.
Cited by 422 works. doi:10.1109/cvpr.1998.698673
Authors
References
- Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images
- Visual Reconstruction
- Some generalized order-disorder transformations
- Exact Maximum A Posteriori Estimation for Binary Images
- Markov Random Field Modeling in Computer Vision
- A maximum-flow formulation of the N-camera stereo correspondence problem
- Segmentation by grouping junctions
- A Maximum Likelihood Stereo Algorithm
- The complexity of multiway cuts (extended abstract)
- Parallel Integration of Vision Modules