We present a common variational framework for dense depth recovery and dense three-dimensional motion field estimation from multiple video sequences, which is robust to camera spectral sensitivity differences and illumination changes. For this purpose, we first show that both problems reduce to a generic image matching problem after backprojecting the input images onto suitable surfaces. We then solve this matching problem in the case of statistical similarity criteria that can handle frequently occurring nonaffine image intensities dependencies. Our method leads to an efficient and elegant implementation based on fast recursive filters. We obtain good results on real images.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Variational stereovision and 3D scene flow estimation with statistical similarity measures


    Contributors:
    Pons, (author) / Keriven, (author) / Faugeras, (author) / Hermosillo, (author)


    Publication date :

    2003-01-01


    Size :

    1020872 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Variational Stereovision and 3D Scene Flow Estimation with Statistical Similarity Measures

    Pons, J. / Keriven, R. / Faugeras, O. et al. | British Library Conference Proceedings | 2003


    3D scene analysis by real-time stereovision

    Garibotto, G. / Cibei, C. | IEEE | 2005


    3D Scene Analysis by Real-Time Stereovision

    Garibotto, G. / Cibei, C. | British Library Conference Proceedings | 2005


    Statistical estimation of multiple measures of similarity

    Semkin, B. I. / Gorshkov, M. V. | British Library Online Contents | 2014