Lighting condition is an important factor in face analysis and synthesis, which has received extensive study in both computer vision and computer graphics. Motivated by the work on multilinear model, we propose a learning-based algorithm for relighting based on tensor framework, which explicitly accounts for the interaction of the identity factor and the lighting factor. The major contribution of our work is that we develop a novel algorithm based on a two-stage decomposition scheme to simultaneously and robustly solve for the identity parameter and the lighting parameter which are both unknown. Equipped with the decomposition algorithm, the capability of the tensor model is significantly extended. Experiment results illustrate the effectiveness of our algorithm.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Tensor-based factor decomposition for relighting


    Contributors:
    Dahua Lin, (author) / Yingqing Xu, (author) / Xiaoou Tang, (author) / Shuicheng Yan, (author)


    Publication date :

    2005-01-01


    Size :

    153854 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Tensor-based Factor Decomposition for Relighting

    Lin, D. / Xu, Y. / Tang, X. et al. | British Library Conference Proceedings | 2005


    Relighting an airport runway

    Roell, F.G. | Tema Archive | 1978


    EDITORIAL - Relighting the fire.

    Online Contents | 2005


    Face relighting with radiance environment maps

    Zhen Wen, / Zicheng Liu, / Huang, T.S. | IEEE | 2003


    Face Relighting with Radiance Environment Maps

    Wen, Z. / Liu, Z. / Huang, T. et al. | British Library Conference Proceedings | 2003