Belief Propagation on the GPU for Stereo Vision

From National Research Council Canada

Download
  1. (PDF, 598 KB)
AuthorSearch for: ; Search for: ; Search for:
FormatText, Article
ConferenceThird Canadian Conference on Computer and Robot Vision, June 7-9, 2006., Québec City, Québec, Canada
Subjectstereo 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
LanguageEnglish
NRC numberNRCC 48491
NPARC number8913572
Export citationExport as RIS
Report a correctionReport a correction
Record identifier3cbf670b-b832-49db-9485-13367d29ea1b
Record created2009-04-22
Record modified2020-04-22
Report a problem on this page
Date modified: