• DocumentCode
    3549055
  • Title

    Real-time connectivity constrained depth map computation using programmable graphics hardware

  • Author

    Cornells, N. ; Van Gool, Luc

  • Author_Institution
    Katholieke Univ. Leuven, Belgium
  • Volume
    1
  • fYear
    2005
  • fDate
    20-25 June 2005
  • Firstpage
    1099
  • Abstract
    This paper presents a passive depth map computation algorithm which runs entirely on programmable 3D graphics hardware at real-time speed. Previous implementations relied on the use of either mipmapping or correlation windows to increase the robustness of the calculated depth map. These methods, however, are inherently unable to compute the depths for fine 3D structures. To overcome this obstacle we introduce a pixel-based method which incorporates connectivity information between neighboring pixels, while maintaining the performance boost gained by implementing the algorithm on a highly parallelized architecture such as graphics hardware.
  • Keywords
    image reconstruction; parallel architectures; real-time systems; 3D structures; highly parallelized architecture; pixel-based method; programmable 3D graphics hardware; real-time connectivity constrained depth map computation; Cameras; Computer architecture; Computer graphics; Frequency estimation; Hardware; Iterative algorithms; Moore´s Law; Robustness; Software performance; Supercomputers;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on
  • ISSN
    1063-6919
  • Print_ISBN
    0-7695-2372-2
  • Type

    conf

  • DOI
    10.1109/CVPR.2005.291
  • Filename
    1467389