ML Anthology

Markov Random Fields with Efficient Approximations

Yuri Boykov, Olga Veksler, Ramin Zabih
CVPR 1998 pp. 648-655
doi:10.1109/CVPR.1998.698673 /cvpr/1998/boykov1998cvpr-markov/

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.

PDF CVPR Semantic Scholar

Cite

Text

Boykov et al. "Markov Random Fields with Efficient Approximations." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1998. doi:10.1109/CVPR.1998.698673

Markdown

[Boykov et al. "Markov Random Fields with Efficient Approximations." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1998.](https://mlanthology.org/cvpr/1998/boykov1998cvpr-markov/) doi:10.1109/CVPR.1998.698673

BibTeX

@inproceedings{boykov1998cvpr-markov,
  title     = {{Markov Random Fields with Efficient Approximations}},
  author    = {Boykov, Yuri and Veksler, Olga and Zabih, Ramin},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1998},
  pages     = {648-655},
  doi       = {10.1109/CVPR.1998.698673},
  url       = {https://mlanthology.org/cvpr/1998/boykov1998cvpr-markov/}
}