Belief Propagation on the GPU for Stereo Vision

Download	View accepted manuscript: Belief Propagation on the GPU for Stereo Vision (PDF, 301 KiB)
Author	Search for: Brunton, Alan; Search for: Shu, Chang; Search for: Roth, Gerhard
Format	Text, Article
Conference	Third Canadian Conference on Computer and Robot Vision, June 7-9, 2006, Québec City, Québec, Canada
Subject	stereo vision; image-based rendering; belief propagation; graphics processing unit
Abstract	The power of Markov random field formulations of lowlevel vision problems, such as stereo, has been known for some time. However, recent advances, both algorithmic and in processing power, have made their application practical. This paper presents a novel implementation of Bayesian belief propagation for graphics processing units found in most modern desktop and notebook computers, and applies it to the stereo problem. The stereo problem is used for comparison to other BP algorithms.
Publication date	2006
In	Third Canadian Conference on Computer and Robot Vision [Proceedings].
Language	English
NRC number	NRCC 48491
NPARC number	8913572
Export citation	Export as RIS
Report a correction	Report a correction (opens in a new tab)
Record identifier	3cbf670b-b832-49db-9485-13367d29ea1b
Record created	2009-04-22
Record modified	2020-10-09