Abstract
We address the problem of modeling the spatial and temporal second-order statistics of video sequences that exhibit both spatial and temporal regularity, intended in a statistical sense. We model such sequences as dynamic multiscale autoregressive models, and introduce an efficient algorithm to learn the model parameters. We then show how the model can be used to synthesize novel sequences that extend the original ones in both space and time, and illustrate the power, and limitations, of the models we propose with a number of real image sequences.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Huang, J., Mumford, D.: Statistics of natural images and models. In: Proc. CVPR, pp. 541–547 (1999)
Srivastava, A., Lee, A., Simoncelli, E., Zhu, S.: On advances in statistical modeling of natural images. J. of Math. Imaging and Vision 18, 17–33 (2003)
Soatto, S., Doretto, G., Wu, Y.: Dynamic textures. In: Proc. ICCV, Vancouver, pp. 439–446 (2001)
Doretto, G., Chiuso, A., Wu, Y., Soatto, S.: Dynamic textures. Int. J. Computer Vision 51, 91–109 (2003)
Nelson, R., Polana, R.: Qualitative recognition of motion using temporal texture. CVGIP Image Und. 56, 78–89 (1992)
Szummer, M., Picard, R.: Temporal texture modeling. In: Proc. ICIP, vol. 3, pp. 823–826 (1996)
Bar-Joseph, Z., El-Yaniv, R., Lischinski, D., Werman, M.: Texture mixing and texture movie synthesis using statistical learning. IEEE Trans. Vis. Comp. Graphics 7, 120–135 (2001)
Schödl, A., Szeliski, R., Salesin, D., Essa, I.: Video textures. In: Proc. SIGGRAPH, pp. 489–498 (2000)
Wei, L., Levoy, M.: Texture synthesis over arbitrary manifold surfaces. In: Proc. SIGGRAPH, pp. 355–360 (2001)
Fitzgibbon, A.: Stochastic rigidity: Image registration for nowhere-static scenes. In: Proc. ICCV, Vancouver, pp. 662–670 (2001)
Kwatra, V., Schödl, A., Essa, I., Turk, G., Bobick, A.: Graphcut textures: Image and video synthesis using graph cuts. In: Proc. SIGGRAPH, pp. 277–286 (2003)
Wang, Y., Zhu, S.: A generative method for textured motion: Analysis and synthesis. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 583–598. Springer, Heidelberg (2002)
Daniel, M., Willsky, A.: The modeling and estimation of statistically self-similar processes in a multiresolution framework. IEEE Trans. Inf. T. 45, 955–970 (1999)
Luettgen, M., Karl, W., Willsky, A., Tenney, R.: Multiscale representations of markov random fields. IEEE Trans. Sig. Proc. 41 (1993)
Chou, K., Willsky, A., Beveniste, A.: Multiscale recursive estimation, data fusion, and regularization. IEEE Trans. Automat. Contr., 464–478 (1994)
Geman, S., Geman, D.: Stochastic relaxation, gibbs distributions, and the bayesian restoration of images. IEEE Trans. PAMI 6, 721–741 (1984)
Ljung, L.: System Identification - Theory for the User. Prentice Hall, Englewood Cliffs (1987)
Dempster, A., Laird, N., Rubin, D.: Maximum likelihood from incomplete data via the em algorithm. J. R. Stat. Soc. B 39, 185–197 (1977)
Golub, G., Van Loan, C.: Matrix Computations, 3rd edn. Johns Hopkins Univ. Press, Baltimore (1996)
Lütkepohl, H.: Introduction to Time Series Analysis, 2nd edn. Springer, Berlin (1993)
Rissanen, J.: Modeling by shortest data description. Automatica 14, 465–471 (1978)
Arun, K., Kung, S.: Balanced approximation of stochastic systems. SIAM J. on Matrix Analysis and Apps. 11, 42–68 (1990)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Doretto, G., Jones, E., Soatto, S. (2004). Spatially Homogeneous Dynamic Textures. In: Pajdla, T., Matas, J. (eds) Computer Vision - ECCV 2004. ECCV 2004. Lecture Notes in Computer Science, vol 3022. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24671-8_47
Download citation
DOI: https://doi.org/10.1007/978-3-540-24671-8_47
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-21983-5
Online ISBN: 978-3-540-24671-8
eBook Packages: Springer Book Archive