All non-trivial stereo problems need model priors to deal with ambiguities and noise perturbations. To meet requirements of increasingly demanding tasks such as modeling for rendering, a proper model prior should impose preference on the true scene structure, while avoiding artificial bias such as fronto-parallel. We introduce a geometric model prior based on a novel technique we call kernel correlation. Maximizing kernel correlation is shown to be equal to distance minimization in the M-estimator sense. As a model prior, kernel correlation is demonstrated to have good properties that can result in renderable, very smooth and accurate depth map. The results are evaluated both qualitatively by view synthesis and quantitatively by error analysis.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    A correlation-based model prior for stereo


    Contributors:
    Yanghai Tsin, (author) / Kanade, T. (author)


    Publication date :

    2004-01-01


    Size :

    765239 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    A Correlation-Based Model Prior for Stereo

    Tsin, Y. / Kanade, T. / IEEE Computer Society | British Library Conference Proceedings | 2004


    Rethinking the Prior Model for Stereo

    Ishikawa, H. / Geiger, D. | British Library Conference Proceedings | 2006


    Rethinking the Prior Model for Stereo

    Ishikawa, Hiroshi / Geiger, Davi | Springer Verlag | 2006

    Free access

    Total Absolute Gaussian Curvature for Stereo Prior

    Ishikawa, Hiroshi | Springer Verlag | 2007


    Improvements in Real-Time Correlation-Based Stereo Vision

    Hirschmuller, H. / IEEE Computer Society | British Library Conference Proceedings | 2001