• DocumentCode
    2072789
  • Title

    Belief Propagation on the GPU for Stereo Vision

  • Author

    Brunton, Alan ; Shu, Chang ; Roth, Gerhard

  • Author_Institution
    University of Ottawa, Canada
  • fYear
    2006
  • fDate
    07-09 June 2006
  • Firstpage
    76
  • Lastpage
    76
  • 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.
  • Keywords
    belief; graphics processing unit.; image-based rendering; propagation; stereo vision; Belief propagation; Computer graphics; Computer vision; Councils; Information technology; Layout; Markov random fields; Pixel; Random variables; Stereo vision; belief; graphics processing unit.; image-based rendering; propagation; stereo vision;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computer and Robot Vision, 2006. The 3rd Canadian Conference on
  • Print_ISBN
    0-7695-2542-3
  • Type

    conf

  • DOI
    10.1109/CRV.2006.19
  • Filename
    1640431