Markov random fields with efficient approximations
Top Cited Papers
- 27 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 57 (10636919) , 648-655
- https://doi.org/10.1109/cvpr.1998.698673
Abstract
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.Keywords
This publication has 9 references indexed in Scilit:
- A maximum-flow formulation of the N-camera stereo correspondence problemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Segmentation by grouping junctionsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- A Maximum Likelihood Stereo AlgorithmComputer Vision and Image Understanding, 1996
- Markov Random Field Modeling in Computer VisionPublished by Springer Nature ,1995
- The complexity of multiway cuts (extended abstract)Published by Association for Computing Machinery (ACM) ,1992
- Parallel Integration of Vision ModulesScience, 1988
- Visual ReconstructionPublished by MIT Press ,1987
- Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of ImagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1984
- Some generalized order-disorder transformationsMathematical Proceedings of the Cambridge Philosophical Society, 1952