The recovery of 3D models from multiple reference images involves not only the extraction of 3D shape, but also of texture. Assuming that all surfaces are Lambertian, the resulting final texture is typically computed as a linear combination of reference textures. This is, however, not the optimal means for reconstructing textures, since this does not model the anisotropy in the texture projection. Furthermore, the spatial image sampling may be quite variable within a fore-shortened surface. This also has important implications for computer vision techniques that involve analysis by synthesis and the image-based rendering (IBR) technique of view-dependent texture mapping (VDTM). Starting with sampling theory, we show how weights should be spatially distributed for optimal texture construction. The local weights take into consideration the effects of anisotropy and variable spatial image sampling. We also present experimental results to verify our analysis.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Optimal texture map reconstruction from multiple views


    Contributors:


    Publication date :

    2001-01-01


    Size :

    1621903 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Optimal Texture Map Reconstruction from Multiple Views

    Wang, L. / Kang, S. B. / Szeliski, R. et al. | British Library Conference Proceedings | 2001


    Reconstruction of topographies from multiple SEM views

    Janssen,R. / Hersener,J. / Daimler-Benz,Ulm,DE | Automotive engineering | 1991


    Adaptive reconstruction using multiple views

    Ulvklo, M. / Knutsson, H. / Granlund, G. | IEEE | 1998



    Multiple Motion Scene Reconstruction from Uncalibrated Views

    Han, M. / Kanade, T. / IEEE | British Library Conference Proceedings | 2001