Belief Propagation on the GPU for Stereo Vision
National Research, Council Canada, Institute for Information Technology
Computer and Robot Vision, 2006. The 3rd Canadian Conference on In Computer and Robot Vision, 2006. The 3rd Canadian Conference on (2006), pp. 76-76
@conference{brunton2006belief,
title={Belief propagation on the GPU for stereo vision},
author={Brunton, A. and Shu, C. and Roth, G.},
booktitle={Computer and Robot Vision, 2006. The 3rd Canadian Conference on},
pages={76},
isbn={0769525423},
year={2006},
organization={IEEE}
}
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.
December 3, 2010 by hgpu
