Non Linear Temporal Textures Synthesis: A Monte Carlo Approach

  • Andrea Masiero
  • Alessandro Chiuso
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3952)


In this paper we consider the problem of temporal texture modeling and synthesis. A temporal texture (or dynamic texture) is seen as the output of a dynamical system driven by white noise. Experimental evidence shows that linear models such as those introduced in earlier work are sometimes inadequate to fully describe the time evolution of the dynamic scene. Extending upon recent work which is available in the literature, we tackle the synthesis using non-linear dynamical models. The non-linear model is never given explicitly but rather we describe a methodology to generate samples from the model. The method requires estimating the “state” distribution and a linear dynamical model from the original clip which are then used respectively as target distribution and proposal mechanism in a rejection sampling step. We also report extensive experimental results comparing the proposed approach with the results obtained using linear models (Doretto et al.) and the “closed-loop” approach presented at ECCV 2004 by Yuan et al.


Nonnegative Matrix Factorization Gaussian Density Transition Kernel Texture Synthesis Kernel Density Estimator 
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.
    Bissacco, A., Saisan, P., Soatto, S.: Dynamic modeling of human gaits. In: Proc. of the IFAC Symposium on System Identification (2003)Google Scholar
  2. 2.
    Doretto, G., Chiuso, A., Soatto, S., Wu, Y.: Dynamic textures. International Journal of Computer Vision 51(2), 91–109 (2003)CrossRefMATHGoogle Scholar
  3. 3.
    Doretto, G., Cremers, D., Favaro, P., Soatto, S.: Dynamic texture segmentation. In: Proceedings of the International Conference on Computer Vision, Nice, France, October 2003, vol. 2, pp. 1236–1242 (2003)Google Scholar
  4. 4.
    Finesso, L., Spreij, P.: Approximate nonnegative matrix factorization via alternating minimization. In: Proc. of the 16th International Symposium on MTNS, Leuven, July 2004, pp. 223–252 (2004)Google Scholar
  5. 5.
    Fitzgibbon, A.: Stochastic rigidity: Image registration for nowhere-static scenes. In: Proc. IEEE International Conf. Computer Vision (ICCV), Vancouver, Canada, vol. 1, pp. 662–670 (2001)Google Scholar
  6. 6.
    Heeger, D., Bergen, J.: Pyramid-based texture analysis/synthesis. In: SIGGRAPH 1995 Conf. Proc. (1995)Google Scholar
  7. 7.
    Julesz, B.: Visual pattern discrimination. IRE Trans. on Information Theory 8, 84–92 (1962)CrossRefGoogle Scholar
  8. 8.
    Kwatra, V., Schödl, A., Essa, I., Turk, G., Bobick, A.: Graphcut textures: Image and video synthesis using graph cuts. In: Proc. ACM Transactions on Graphics, SIGGRAPH 2003 (2003)Google Scholar
  9. 9.
    Lee, D., Seung, H.S.: Algorithms for non-negative matrix factorization. In: Leen, T.K., Dietterich, T.G., Tresp, V. (eds.) Advances in Neural and Information Processing Systems 13, pp. 556–562. MIT Press, Cambridge (2001)Google Scholar
  10. 10.
    Scholkopf, B., Smola, A., Muller, K.-R.: Nonlinear component analysis as a kernel eigenvalue problem. Neural Computation, 1299–1319 (1998)Google Scholar
  11. 11.
    Scott, D.W.: Multivariate Density Estimation, Theory, Practice, and Visualization. John Wiley and Sons, Chichester (1992)CrossRefMATHGoogle Scholar
  12. 12.
    Shawe-Taylor, J., Cristianini, N.: Kernel Methods for Pattern Analysis. Cambridge University Press, Cambridge (2004)CrossRefMATHGoogle Scholar
  13. 13.
    Silverman, B.W.: Density estimation for Statistics and Data Analysis. Chapman and Hall, Boca Raton (1986)CrossRefMATHGoogle Scholar
  14. 14.
    Sznaier, M., Camps, O., Mazzaro, C.: Finite horizon model reduction of a class of neutrally stable systems with applications to texture synthesis and recognition. In: CDC 2004 (2004)Google Scholar
  15. 15.
    Szummer, M., Picard, R.: Temporal texture modeling. In: IEEE International Conference on Image Processing (ICIP), Lausanne, Switzerland, vol. 3, pp. 823–826 (1996)Google Scholar
  16. 16.
    Tanizaki, H.: Nonlinear Filters: Estimation and Applications, 2nd edn. Springer, Heidelberg (1996)CrossRefMATHGoogle Scholar
  17. 17.
    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)CrossRefGoogle Scholar
  18. 18.
    Wang, Y., Zhu, S.: Analysis and synthesis of textured motion: Particles and waves. IEEE Trans. on Patt. Anal. and Mach. Intell. 26(10), 1348–1363 (2004)CrossRefGoogle Scholar
  19. 19.
    Wu, Y., Zhu, S., Liu, X.: Equivalence of julesz ensembles and frame models. Int’l Journal of Computer Vision 38(3), 247–267 (2000)CrossRefMATHGoogle Scholar
  20. 20.
    Yuan, L., Wen, F., Liu, C., Shum, H.-Y.: Synthesizing dynamic texture with closed-loop linear dynamic system. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3022, pp. 603–616. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  21. 21.
    Zhu, S., Liu, X., Wu, Y.: Exploring texture ensembles by efficient markov chain monte carlo. IEEE Trans. on Patt. Anal. and Mach. Intell. 22(6), 554–569 (2000)CrossRefGoogle Scholar
  22. 22.
    Zhu, S., Wu, Y., Mumford, D.: Minimax entropy principle and its application to texture modeling. Neural Computation 9(8) (1997)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Andrea Masiero
    • 1
  • Alessandro Chiuso
    • 1
  1. 1.Department of Information EngineeringUniversity of PadovaPadovaItaly

Personalised recommendations