This paper presents a novel approach for estimating parameters for MRF-based stereo algorithms. This approach is based on a new formulation of stereo as a maximum a posterior (MAP) problem, in which both a disparity map and MRF parameters are estimated from the stereo pair itself. We present an iterative algorithm for the MAP estimation that alternates between estimating the parameters while fixing the disparity map and estimating the disparity map while fixing the parameters. The estimated parameters include robust truncation thresholds, for both data and neighborhood terms, as well as a regularization weight. The regularization weight can be either a constant for the whole image, or spatially-varying, depending on local intensity gradients. In the latter case, the weights for intensity gradients are also estimated. Experiments indicate that our approach, as a wrapper for existing stereo algorithms, moves a baseline belief propagation stereo algorithm up six slots in the middlebury rankings.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Parameter estimation for MRF stereo


    Beteiligte:
    Zhang, L. (Autor:in) / Seitz, S.M. (Autor:in)


    Erscheinungsdatum :

    2005-01-01


    Format / Umfang :

    702840 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Building facade detection, segmentation, and parameter estimation for mobile robot stereo vision

    Delmerico, J. A. / David, P. / Corso, J. J. | British Library Online Contents | 2013


    Pushing the limits of stereo using variational stereo estimation

    Ranftl, Rene / Gehrig, Stefan / Pock, Thomas et al. | IEEE | 2012


    Pushing the Limits of Stereo Using Variational Stereo Estimation

    Ranftl, R. / Gehrig, S. / Pock, T. et al. | British Library Conference Proceedings | 2012


    Motion and inertial parameter estimation of non-cooperative target on orbit using stereo vision

    Ge, Dongming / Wang, Dayi / Zou, Yuanjie et al. | Elsevier | 2020


    Estimation of depth and 3D motion parameter of moving object with multiple stereo images

    Yi, J.-W. / Oh, J.-H. | British Library Online Contents | 1996