Markov random fields with efficient approximations

Markov random fields with efficient approximations (1998)

by Yuri Boykov , Olga Veksler , Ramin Zabih

Venue:	In IEEE Conference on Computer Vision and Pattern Recognition
Citations:	123 - 21 self

Datum	Value	Source
TITLE	Markov random fields with efficient approximations	INFERENCE
AUTHOR NAME	Yuri Boykov	SVM HeaderParse 0.2
AUTHOR AFFIL	Computer Science Department; Cornell University	SVM HeaderParse 0.2
AUTHOR ADDR	Ithaca, NY 14853	SVM HeaderParse 0.2
AUTHOR NAME	Olga Veksler	SVM HeaderParse 0.2
AUTHOR AFFIL	Computer Science Department; Cornell University	SVM HeaderParse 0.2
AUTHOR ADDR	Ithaca, NY 14853	SVM HeaderParse 0.2
AUTHOR NAME	Ramin Zabih	SVM HeaderParse 0.2
AUTHOR AFFIL	Computer Science Department; Cornell University	SVM HeaderParse 0.2
AUTHOR ADDR	Ithaca, NY 14853	SVM HeaderParse 0.2
ABSTRACT	Markov Random Fields (MRF’s) can be used for a wide variety of vision problems. In this paper we focus on MRF’s 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 MRF’s with linear clique potentials. 1	SVM HeaderParse 0.2
YEAR	1998	INFERENCE
VENUE	In IEEE Conference on Computer Vision and Pattern Recognition	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	648--655	INFERENCE
CITATIONS	12 found	ParsCit 1.0