Third Canadian Conference on Computer and Robot Vision, June 7-9, 2006, Québec City, Québec, Canada
stereo vision; image-based rendering; belief propagation; graphics processing unit
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.
Third Canadian Conference on Computer and Robot Vision [Proceedings].