Dynamic textures are sequences of images of moving scenes that exhibit certain stationarity properties in time; these include sea-waves, smoke, foliage, whirlwind but also talking faces, traffic scenes etc. We present a novel characterization of dynamic textures that poses the problems of modelling, learning, recognizing and synthesizing dynamic textures on a firm analytical footing. We borrow tools from system identification to capture the "essence" of dynamic textures; we do so by learning (i.e. identifying) models that are optimal in the sense of maximum likelihood or minimum prediction error variance. For the special case of second-order stationary processes we identify the model in closed form. Once learned, a model has predictive power and can be used for extrapolating synthetic sequences to infinite length with negligible computational cost. We present experimental evidence that, within our framework, even low dimensional models can capture very complex visual phenomena.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Dynamic textures


    Contributors:
    Soatto, S. (author) / Doretto, G. (author) / Ying Nian Wu, (author)


    Publication date :

    2001-01-01


    Size :

    1160169 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Dynamic Textures

    Soatto, S. / Doretto, G. / Wu, Y. et al. | British Library Conference Proceedings | 2001


    Dynamic Textures

    Doretto, G. / Chiuso, A. / Wu, Y. N. et al. | British Library Online Contents | 2003


    Editable dynamic textures

    Doretto, G. / Soatto, S. | IEEE | 2003


    Editable Dynamic Textures

    Doretto, G. / Soatto, S. / IEEE | British Library Conference Proceedings | 2003


    Mixtures of Dynamic Textures

    Chan, A. / Vasconcelos, N. / IEEE | British Library Conference Proceedings | 2005