This paper proposes a new Bayesian framework for solving the matting problem, i.e. extracting a foreground element from a background image by estimating an opacity for each pixel of the foreground element. Our approach models both the foreground and background color distributions with spatially-varying sets of Gaussians, and assumes a fractional blending of the foreground and background colors to produce the final output. It then uses a maximum-likelihood criterion to estimate the optimal opacity, foreground and background simultaneously. In addition to providing a principled approach to the matting problem, our algorithm effectively handles objects with intricate boundaries, such as hair strands and fur, and provides an improvement over existing techniques for these difficult cases.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    A Bayesian approach to digital matting


    Beteiligte:
    Yung-Yu Chuang, (Autor:in) / Curless, B. (Autor:in) / Salesin, D.H. (Autor:in) / Szeliski, R. (Autor:in)


    Erscheinungsdatum :

    2001-01-01


    Format / Umfang :

    1129635 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    A Bayesian Approach to Digital Matting

    Chuang, Y.-Y. / Curless, B. / Salesin, D. H. et al. | British Library Conference Proceedings | 2001


    Bayesian Video Matting Using Learnt Image Priors

    Apostoloff, N. / Fitzgibbon, A. / IEEE Computer Society | British Library Conference Proceedings | 2004


    Bayesian video matting using learnt image priors

    Apostoloff, N. / Fitzgibbon, A. | IEEE | 2004


    Oriented Poisson matting

    Zhenlong Du, / Hai Lin, / Xueying Qin, et al. | IEEE | 2005


    Oriented Poisson Matting

    Du, Z. / Lin, H. / Qin, X. et al. | British Library Conference Proceedings | 2005