Abstract
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.
This work has been supported in part by RECSYS project of the European Community and by the national project New methods and algorithms for identification and adaptive control of technological systems funded by MIUR.
Chapter PDF
Similar content being viewed by others
Keywords
- 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.
References
Bissacco, A., Saisan, P., Soatto, S.: Dynamic modeling of human gaits. In: Proc. of the IFAC Symposium on System Identification (2003)
Doretto, G., Chiuso, A., Soatto, S., Wu, Y.: Dynamic textures. International Journal of Computer Vision 51(2), 91–109 (2003)
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)
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)
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)
Heeger, D., Bergen, J.: Pyramid-based texture analysis/synthesis. In: SIGGRAPH 1995 Conf. Proc. (1995)
Julesz, B.: Visual pattern discrimination. IRE Trans. on Information Theory 8, 84–92 (1962)
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)
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)
Scholkopf, B., Smola, A., Muller, K.-R.: Nonlinear component analysis as a kernel eigenvalue problem. Neural Computation, 1299–1319 (1998)
Scott, D.W.: Multivariate Density Estimation, Theory, Practice, and Visualization. John Wiley and Sons, Chichester (1992)
Shawe-Taylor, J., Cristianini, N.: Kernel Methods for Pattern Analysis. Cambridge University Press, Cambridge (2004)
Silverman, B.W.: Density estimation for Statistics and Data Analysis. Chapman and Hall, Boca Raton (1986)
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)
Szummer, M., Picard, R.: Temporal texture modeling. In: IEEE International Conference on Image Processing (ICIP), Lausanne, Switzerland, vol. 3, pp. 823–826 (1996)
Tanizaki, H.: Nonlinear Filters: Estimation and Applications, 2nd edn. Springer, Heidelberg (1996)
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)
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)
Wu, Y., Zhu, S., Liu, X.: Equivalence of julesz ensembles and frame models. Int’l Journal of Computer Vision 38(3), 247–267 (2000)
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)
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)
Zhu, S., Wu, Y., Mumford, D.: Minimax entropy principle and its application to texture modeling. Neural Computation 9(8) (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Masiero, A., Chiuso, A. (2006). Non Linear Temporal Textures Synthesis: A Monte Carlo Approach. In: Leonardis, A., Bischof, H., Pinz, A. (eds) Computer Vision – ECCV 2006. ECCV 2006. Lecture Notes in Computer Science, vol 3952. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11744047_22
Download citation
DOI: https://doi.org/10.1007/11744047_22
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-33834-5
Online ISBN: 978-3-540-33835-2
eBook Packages: Computer ScienceComputer Science (R0)