DocumentCode :
3014895
Title :
Efficient Belief Propagation for Vision Using Linear Constraint Nodes
Author :
Potetz, Brian
Author_Institution :
Carnegie Mellon Univ., Pittsburgh
fYear :
2007
fDate :
17-22 June 2007
Firstpage :
1
Lastpage :
8
Abstract :
Belief propagation over pairwise connected Markov random fields has become a widely used approach, and has been successfully applied to several important computer vision problems. However, pairwise interactions are often insufficient to capture the full statistics of the problem. Higher-order interactions are sometimes required. Unfortunately, the complexity of belief propagation is exponential in the size of the largest clique. In this paper, we introduce a new technique to compute belief propagation messages in time linear with respect to clique size for a large class of potential functions over real-valued variables. We demonstrate this technique in two applications. First, we perform efficient inference in graphical models where the spatial prior of natural images is captured by 2 times 2 cliques. This approach shows significant improvement over the commonly used pairwise-connected models, and may benefit a variety of applications using belief propagation to infer images or range images. Finally, we apply these techniques to shape-from-shading and demonstrate significant improvement over previous methods, both in quality and in flexibility.
Keywords :
Markov processes; belief networks; computer vision; user interfaces; computer vision problems; higher-order interactions; linear constraint nodes; pairwise connected Markov random fields; pairwise interactions; real-valued variables; shape-from-shading techniques; vision belief propagation; Application software; Belief propagation; Computer vision; Graphical models; Higher order statistics; Markov random fields; Probability distribution; Reflectivity; Statistical distributions; Stereo vision;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Vision and Pattern Recognition, 2007. CVPR '07. IEEE Conference on
Conference_Location :
Minneapolis, MN
ISSN :
1063-6919
Print_ISBN :
1-4244-1179-3
Electronic_ISBN :
1063-6919
Type :
conf
DOI :
10.1109/CVPR.2007.383094
Filename :
4270119
Link To Document :
بازگشت