Several new algorithms for visual correspondence based on graph cuts have recently been developed. While these methods give very strong results in practice, they do not handle occlusions properly. Specifically, they treat the two input images asymmetrically, and they do not ensure that a pixel corresponds to at most one pixel in the other image. In this paper, we present a new method which properly addresses occlusions, while preserving the advantages of graph cut algorithms. We give experimental results for stereo as well as motion, which demonstrate that our method performs well both at detecting occlusions and computing disparities.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Computing visual correspondence with occlusions using graph cuts


    Beteiligte:
    Kolmogorov, V. (Autor:in) / Zabih, R. (Autor:in)


    Erscheinungsdatum :

    01.01.2001


    Format / Umfang :

    1138759 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Computing Visual Correspondence with Occlusions via Graph Cuts

    Kolmogorov, V. / Zabih, R. / IEEE | British Library Conference Proceedings | 2001



    Extracting Dense Features for Visual Correspondence with Graph Cuts

    Veksler, O. / IEEE | British Library Conference Proceedings | 2003


    Computing Geodesics and Minimal Surfaces via Graph Cuts

    Boykov, Y. / Kolmogorov, V. / IEEE | British Library Conference Proceedings | 2003