The 3rd Canadian Conference on Computer and Robot Vision (CRV'06)
Belief Propagation on the GPU for Stereo Vision
Quebec City, Quebec, Canada
June 07-June 09
ISBN: 0-7695-2542-3
DOI Bookmark:
http://doi.ieeecomputersociety.org/10.1109/CRV.2006.19
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.
Index Terms:
stereo vision, image-based rendering, belief propagation, graphics processing unit.
Citation:
Alan Brunton, Chang Shu, Gerhard Roth, "Belief Propagation on the GPU for Stereo Vision," crv, pp.76, The 3rd Canadian Conference on Computer and Robot Vision (CRV'06), 2006
Usage of this product signifies your acceptance of the
Terms of Use.
|
|||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||