To what extent can three-dimensional shape and radiance be inferred from a collection of images? Can the two be estimated separately while retaining optimality? How should the optimality criterion be computed? When is it necessary to employ an explicit model of the reflectance properties of a scene? In this paper we introduce a separation principle for shape and radiance estimation that applies to Lambertian scenes and holds for any choice of norm. When the scene is not Lambertian, however, shape cannot be decoupled from radiance, and therefore matching image-to-image is not possible directly. We employ a rank constraint on the radiance tensor, which is commonly used in computer graphics, and construct a novel cost functional whose minimization leads to an estimate of both shape and radiance for nonLambertian objects, which we validate experimentally.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Tales of shape and radiance in multiview stereo


    Contributors:
    Soatto, (author) / Yezzi, (author) / Hailin Jin, (author)


    Publication date :

    2003-01-01


    Size :

    686400 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Tales of Shape and Radiance in Multi-view Stereo

    Soatto, S. / Yezzi, A. / Jin, H. et al. | British Library Conference Proceedings | 2003



    Multiview stereo and silhouette fusion via minimizing generalized reprojection error

    Li, Z. / Wang, K. / Jia, W. et al. | British Library Online Contents | 2015


    A multiview 3D modeling system based on stereo vision techniques

    Park, S. Y. / Subbarao, M. | British Library Online Contents | 2005


    Multiview stereo object reconstruction with a one-line search method

    Zhang, J. / Chesi, G. | British Library Online Contents | 2013