Nonrigid 3D structure-from-motion and 2D optical flow can both be formulated as tensor factorization problems. The two problems can be made equivalent through a noisy affine transform, yielding a combined nonrigid structure-from-intensities problem that we solve via structured matrix decompositions. Often the preconditions for this factorization are violated by image noise and deficiencies of the data visa-vis the sample complexity of the problem. Both issues are remediated with careful use of rank constraints, norm constraints, and integration over uncertainty in the intensity values, yielding novel solutions for SVD under uncertainty, factorization under uncertainty, nonrigid factorization, and subspace optical flow. The resulting integrated algorithm can track and reconstruct in 3D nonrigid surfaces having very little texture, for example the smooth parts of the face. Working with low-resolution low-texture "found video," these methods produce good tracking and 3D reconstruction results where prior algorithms fail.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Morphable 3D models from video


    Contributors:
    Brand, W. (author)


    Publication date :

    2001-01-01


    Size :

    1110925 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Morphable 3D Models from Video

    Brand, M. / IEEE | British Library Conference Proceedings | 2001


    Morphable Surface Models

    Shelton, C. R. | British Library Online Contents | 2000


    Multidimensional Morphable Models

    Jones, M. J. / Poggio, T. / IEEE; Computer Society | British Library Conference Proceedings | 1998


    Morphable structure

    PARSONS LAURA / WOODS BENJAMIN / FRISWELL MICHAEL | European Patent Office | 2016

    Free access

    Component-based face recognition with 3D morphable models

    Huang, Jennifer, 1980- | DSpace@MIT | 2003

    Free access