We cast the problem of multiframe stereo reconstruction of a smooth shape as the global region segmentation of a collection of images of the scene. Dually, the problem of segmenting multiple calibrated images of an object becomes that of estimating the solid shape that gives rise to such images. We assume that the radiance has smooth statistics. This assumption covers Lambertian scenes with smooth or constant albedo as well as fine homogeneous textures, which are known challenges to stereo algorithms based on local correspondence. We pose the segmentation problem within a variational framework, and use fast level set methods to approximate the optimal solution numerically. Our algorithm does nor work in the presence of strong textures, where traditional reconstruction algorithms do. It enjoys significant robustness to noise under the assumptions it is designed for.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Stereoscopic segmentation


    Contributors:
    Yezzi, A.J. (author) / Soatto, S. (author)


    Publication date :

    2001-01-01


    Size :

    1338225 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Stereoscopic Segmentation

    Yezzi, A. / Soatto, S. / IEEE | British Library Conference Proceedings | 2001


    Stereoscopic Segmentation

    Yezzi, A. / Soatto, S. | British Library Online Contents | 2003


    Shedding light on stereoscopic segmentation

    Hailin Jin, / Cremers, D. / Yezzi, A.J. et al. | IEEE | 2004


    Shedding Light on Stereoscopic Segmentation

    Jin, H. / Cremers, D. / Yezzi, A. et al. | British Library Conference Proceedings | 2004


    Image segmentation for binocular stereoscopic dual-energy x-ray imaging

    Yong, Y. S. / Evans, J. P. O. / Chan, J. W. | British Library Online Contents | 2005