Higher Order SVD Analysis for Dynamic Texture Synthesis

This is the latest version of this item.

Abstract

Videos representing flames, water, smoke, etc. are often defined as dynamic textures: “textures” because they are characterized by redundant repetition of a pattern and “dynamic” because this repetition is also in time and not only in space. Dynamic textures have been modeled as linear dynamic systems by unfolding the video frames into column vectors and describing their trajectory as time evolves. After the projection of the vectors onto a lower dimensional space by a Singular Value Decomposition (SVD), the trajectory is modeled using system identification techniques. Synthesis is obtained by driving the system with random noise. In this paper, we show that the standard SVD can be replaced by a Higher Order SVD (HOSVD), originally known as Tucker decomposition. HOSVD decomposes the dynamic texture as a multidimensional signal (tensor) without unfolding the video frames on column vectors. This is a more natural and flexible decomposition, since it permits to perform dimension reduction in spatial, temporal, and chromatic domain, while standard SVD allows for temporal reduction only. We show that for a comparable synthesis quality, the HOSVD approach requires on average five times less parameters than the standard SVD approach. The analysis part is more expensive, but the synthesis has the same cost as existing algorithms. Our technique is thus well suited to dynamic texture synthesis on devices limited by memory and computational power, such as PDAs or mobile phones.

Reference

Costantini, Roberto and Sbaiz, Luciano and Süsstrunk, Sabine (2008) Higher Order SVD Analysis for Dynamic Texture Synthesis. IEEE Transactions on Image Processing, 17 (1). pp. 42-52. [BibTeX]

Full Text

Preview

PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader Copyright Notice: Copyright IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE. 3137Kb

Code/Data

Here you can find the code and data to reproduce all images and tables from the paper. If you use this code in your research and publications, please also put a reference to this paper. Thank you!

ZIP License: Creative Commons GNU GPL (Software) 45Mb

Tested Configurations

Matlab R2007b on Windows XP

Further Details