Abstract
Dynamic textures are sequences of images of moving scenes that show stationarity properties in time. Eg: waves, flame, fountain, etc. Recent attempts at generating, potentially, infinitely long sequences model the dynamic texture as a Linear Dynamic System. This assumes a linear correlation in the input sequence. Most real world sequences however, exhibit nonlinear correlation between frames. In this paper, we propose a technique of generating dynamic textures using a low dimension model that preserves the non-linear correlation. We use nonlinear dimensionality reduction to create an embedding of the input sequence. Using this embedding, a nonlinear mapping is learnt from the embedded space into the image input space. Any input is represented by a linear combination of nonlinear bases functions centered along the manifold in the embedded space. A spline is used to move along the input manifold in this embedded space as a similar manifold is created for the output. The nonlinear mapping learnt on the input is used to map this new manifold into a sequence in the image space. Output sequences, thus created, contain images never present in the original sequence and are very realistic.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Stam, J., Fiume, E.: Depicting fire and other gaseous phenomena using diffusion processes. In: Proc. SIGGRAPH 1995, pp. 129–136 (August 1995)
Hodgins, J.K., Wooten, W.L.: Animating human athletes. In: Robotics Research: The Eighth International Symposium, pp. 356–367 (1998)
Popovićć, J., Seitz, S.M., Erdmann, M., Popović, Z., Witkin, A.: Interactive manipulation of rigid body simulations. In: Proc. of SIGGRAPH 2000, pp. 209–218 (July 2000)
Perry, C.H., Picard, R.W.: Synthesizing Flames and Their Spreading. In: Proc. of the 5th Eurographics Workshop on Animation and Simulation, Oslo, Norway (September 1994)
Schödl, A., Szeliski, R., Salesin, D.H., Essa, I.: Video textures, In: Akeley, K. (ed.) Siggraph 2000 Computer Graphics Proceedings, ACMPress/ACM SIGGRAPH /Addison Wesley/Longman, 2000, pp. 489–498 (2000)
Fitzgibbon, A.W.: Stochastic rigidity: image registration for nowherestatic scenes. In: Proceedings of the Eighth International Conference On Computer Vision, pp. 662–669 (2001)
Soatto, S., Doretto, G., Wu, Y.N.: Dynamic textures. In: International Conference on Computer Vision, pp. 439–446 (2001)
Kwatra, V., Schödl, A., Essa, I., Turk, G., Bobick, A.: Graphcut Textures: Image and Video Synthesis Using Graph Cuts. In: Proceedings of Siggraph 2003, pp. 277–286 (2003)
Szummer, M., Picard, R.W.: Temporal Texture Modeling. IEEE International Conference on Image Processing 3, 823–826 (1996)
Yuan, L., Wen, F., Liu, C., shum, H.Y.: Synthesizing Dynamic Texture with Closed-Loop Linear Dynamical System. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3022, pp. 603–616. Springer, Heidelberg (2004)
Roweis, S., Saul, L.: Nonlinear dimensionality reduction by locally linear embedding. Science 290, 2323–2326 (2000)
Tenenbaum, J.B., de Silva, V., Langford, J.C.: A global geometric framework for nonlinear dimensionality reduction. Science 290, 2319–2323 (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Awasthi, I., Elgammal, A. (2007). Learning Nonlinear Manifolds of Dynamic Textures. In: Braz, J., Ranchordas, A., Araújo, H., Jorge, J. (eds) Advances in Computer Graphics and Computer Vision. Communications in Computer and Information Science, vol 4. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-75274-5_28
Download citation
DOI: https://doi.org/10.1007/978-3-540-75274-5_28
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-75272-1
Online ISBN: 978-3-540-75274-5
eBook Packages: Computer ScienceComputer Science (R0)