Develops a Bayesian feedback method for incorporating global structure into prior models for binocular stereopsis. Since most stereo scenes contain either background continuation (large background surfaces continuing behind smaller fore-ground surfaces) or transparency continuation (small opaque patches on a transparent surface), highly nonlocal interactions are often present in the scene geometry. The commonly used local prior models which impose piecewise smoothness constraints on the reconstructions do not capture the probabilistic subtleties of global 3D structures. Therefore, the authors develop a hybridized prior which balances the local properties of the scene geometry with the global properties. Experimental results demonstrating the potential of this technique are provided.<>


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Global priors for binocular stereopsis


    Contributors:


    Publication date :

    1994-01-01


    Size :

    487661 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Global Priors for Binocular Stereopsis

    Belhumeur, P. N. / IEEE; Signal Processing Society | British Library Conference Proceedings | 1994


    Binocular Helmholtz stereopsis

    Zickler, / Ho, / Kriegman, et al. | IEEE | 2003


    Binocular Helmholtz Stereopsis

    Kriegman, D. / Zickler, T. / Ho, J. et al. | British Library Conference Proceedings | 2003


    A Bayesian Approach to Binocular Stereopsis

    Belhumeur, P. N. | British Library Online Contents | 1996