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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

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


    Contributors:
    Cornells, N. (author) / Van Gool, L. (author)


    Publication date :

    2005-01-01


    Size :

    309488 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Real-time virtual environment signal extraction and denoising using programmable graphics hardware

    Su, Y. / Xu, Z. J. / Jiang, X. Q. | British Library Online Contents | 2009



    Feature tracking and matching in video using programmable graphics hardware

    Sinha, S. N. / Frahm, J. M. / Pollefeys, M. et al. | British Library Online Contents | 2011


    Real-Time Image-Based Stylistic Rendering Using Graphics Hardware Acceleration

    Chiang, Chun-Chung / Hsueh, Yu-Hung / Liu, Damon Shing-Min | IEEE | 2007