Dynamic Texture Analysis and Synthesis Using Tensor Decomposition

  • Roberto Costantini
  • Luciano Sbaiz
  • Sabine Süsstrunk
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4292)


Dynamic textures are sequences of images showing temporal regularity, such as smoke, flames, flowing water, or moving grass. Despite being a multidimensional signal, existing models reshape the dynamic texture into a 2D signal for analysis. In this article, we propose to directly decompose the multidimensional (tensor) signal, free from reshaping operations. We show that decomposition techniques originally applied to study psychometric or chemometric data can be used for this purpose. Since spatial, time, and color information are analyzed at the same time, such techniques permit to obtain more compact models. Only one third or less model coefficients are needed for the same quality and synthesis cost of 2D based models, as illustrated by experiments on real dynamic textures.


Singular Value Decomposition Texture Synthesis Dynamic Texture Tensor Decomposition Multidimensional Signal 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Xu, Y., Guo, B., Shum, H.: Chaos mosaic: Fast and memory efficient texture synthesis. Technical Report, Microsoft Research 22 (2000)Google Scholar
  2. 2.
    Wei, L.Y., Levoy, M.: Fast texture synthesis using tree-structured vector quantization. In: Proceedings of SIGGRAPH 2000, pp. 479–488 (2000)Google Scholar
  3. 3.
    Efros, A.A., Freeman, W.T.: Image quilting for texture synthesis and transfer. In: Proceedings of SIGGRAPH 2001, pp. 341–346 (2001)Google Scholar
  4. 4.
    Schödl, A., Szeliski, R., Salesin, D.H., Essa, I.: Video textures. In: Proc. of SIGGRAPH 2000, pp. 489–498 (2000)Google Scholar
  5. 5.
    Kwatra, V., Schödl, A., Essa, I., Turk, G., Bobick, A.: Graphcut textures: Image and video synthesis using graph cuts. In: Proc. of SIGGRAPH 2003, pp. 277–286 (2003)Google Scholar
  6. 6.
    Heeger, D.J., Bergen, J.R.: Pyramid-based texture analysis/synthesis. In: ACM Transactions on Graphics, SIGGRAPH 1995, pp. 229–238 (1995)Google Scholar
  7. 7.
    Zhu, S.C., Wu, Y., Mumford, D.: Filters, random fields and maximum entropy (frame): Towards a unified theory for texture modeling. Int. Journal of Comp. Vis. 27, 107–126 (1998)CrossRefGoogle Scholar
  8. 8.
    Portilla, J., Simoncelli, E.: A parametric model based on joint statistics of complex wavelet coefficients. International Journal of Computer Vision 40, 49–71 (2000)MATHCrossRefGoogle Scholar
  9. 9.
    Alata, O., Olivier, C.: Choice of a 2-d causal autoregressive texture model using information criteria. Pattern Recognition Letters 29, 1191–1201 (2003)CrossRefGoogle Scholar
  10. 10.
    Szummer, M., Picard, R.: Temporal texture modeling. In: IEEE Int. Conf. on Image Process, pp. 823–826 (1996)Google Scholar
  11. 11.
    Bar-Joseph, Z., El-Yaniv, R., Lischinski, D., Werman, M.: Texture mixing and texture movie synthesis using statistical learning. IEEE Trans. on Visualization and Computer Graphics 7, 120 (1993)CrossRefGoogle Scholar
  12. 12.
    Zhu, S.-C., Wang, Y.: 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)Google Scholar
  13. 13.
    Doretto, G., Chiuso, A., Wu, Y., Soatto, S.: Dynamic textures. Int. Journal of Computer Vision 51, 91–109 (2003)MATHCrossRefGoogle Scholar
  14. 14.
    Doretto, G., Soatto, S.: Editable dynamic textures. In: CVPR 2003, vol. 2, pp. 137–142 (2003)Google Scholar
  15. 15.
    Saisan, P., Doretto, G., Wu, Y.N., Soatto, S.: Dynamic texture recognition. In: CVPR 2001, vol. 2, pp. 58–63 (2001)Google Scholar
  16. 16.
    Yuan, L., Wen, F., Liu, C., Shum, H.Y.: Synthesizing dynamic texture with closed-loop linear dynamic system. In: European Conf. on Comp. Vision (2004)Google Scholar
  17. 17.
    Liu, C.B., Lin, R.S., Ahuja, N.: Modeling dynamical textures using subspace mixtures. In: ICIME 2005 (2005)Google Scholar
  18. 18.
    Abraham, B., Camps, O.I., Sznaier, M.: Dynamic texture with fourier descriptors. In: Proc. of the 4th Int. Workshop on Texture Analysis ans Synthesis, pp. 53–58 (2005)Google Scholar
  19. 19.
    Costantini, R., Sbaiz, L., Süsstrunk, S.: Dynamic texture synthesis: Compact models based on luminance-chrominance color representation. To appear in Proc. ICIP 2006, Atlanta, GA, USA (2006)Google Scholar
  20. 20.
    Lathauwen, L.D., Moor, B.D., Vandewalle, J.: A multilinear singular value decomposition. Siam J. Matrix Anal. Appl. 21, 1253–1278 (2000)CrossRefMathSciNetGoogle Scholar
  21. 21.
    Lathauwen, L.D., Moor, B.D., Vandewalle, J.: On the best rank-1 and rank-(r 1,r 2, ..., r 1) approximation of higher-order tensors. Siam J. Matrix Anal. Appl. 21, 1324–1342 (2000)CrossRefMathSciNetGoogle Scholar
  22. 22.
    Tucker, L.: Some mathematical notes on three-mode factor analysis. Psychometrika 31, 279–311 (1966)CrossRefMathSciNetGoogle Scholar
  23. 23.
    Tucker, L.: Relations between multidimensional scaling and three-mode factor analysis. Psychometrika 37, 3–27 (1972)MATHCrossRefMathSciNetGoogle Scholar
  24. 24.
    Mahoney, M.W., Maggioni, M., Drineas, P.: Tensor-cur decompositions for tensor-based data. In: Proc. 12th Annual SIGKDD 2006 (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Roberto Costantini
    • 1
  • Luciano Sbaiz
    • 1
  • Sabine Süsstrunk
    • 1
  1. 1.School of Computer and Communication SciencesEcole Polytechnique Fédérale de Lausanne (EPFL)LausanneSwitzerland

Personalised recommendations