We consider the problem of estimating the shape and radiance of an object from a calibrated set of views under the assumption that the reflectance of the object is non-Lambertian. Unlike traditional stereo, we do not solve the correspondence problem by comparing image-to-image. Instead, we exploit a rank constraint on the radiance tensor field of the surface in space, and use it to define a discrepancy measure between each image and the underlying model. Our approach automatically returns an estimate of the radiance of the scene, along with its shape, represented by a dense surface. The former can be used to generate novel views that capture the non-Lambertian appearance of the scene.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Multi-view stereo beyond Lambert


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


    Publication date :

    2003-01-01


    Size :

    1061866 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Multi-view Stereo beyond Lambert

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


    Beyond Lambert: reconstructing surfaces with arbitrary BRDFs

    Magda, S. / Kriegman, D.J. / Zickler, T. et al. | IEEE | 2001


    Beyond Lambert: Reconstructing Surfaces with Arbitrary BRDFs

    Magda, S. / Kriegman, D. / Zickler, T. et al. | British Library Conference Proceedings | 2001


    Beyond Lambert: reconstructing specular surfaces using color

    Mallick, S.P. / Zickler, T.E. / Kriegman, D.J. et al. | IEEE | 2005


    OPTIMAL MULTI-TARGET LAMBERT RENDEZVOUS

    Bang, Jun / Ahn, Jaemyung | British Library Conference Proceedings | 2016