Composite Texture Descriptions

  • Alexey Zalesny
  • Vittorio Ferrari
  • Geert Caenen
  • Dominik Auf der Maur
  • Luc Van Gool
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2352)


Textures can often more easily be described as a composition of subtextures than as a single texture. The paper proposes a way to model and synthesize such “composite textures”, where the layout of the different subtextures is itself modeled as a texture, which can be generated automatically. Examples are shown for building materials with an intricate structure and for the automatic creation of landscape textures. First, a model of the composite texture is generated. This procedure comprises manual or unsupervised texture segmentation to learn the spatial layout of the composite texture and the extraction of models for each of the subtextures. Synthesis of a composite texture includes the generation of a layout texture, which is subsequently filled in with the appropriate subtextures. This scheme is refined further by also including interactions between neighboring subtextures.


Texture Synthesis Texture Model Neighborhood System Verbatim Copying Single Texture 
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.


  1. 1.
    G. Caenen, V. Ferrari, L. Van Gool, and A. Zalesny. Unsupervised Texture Segmentation through Clique Partitioning. Tech. Rep. KUL/ESAT/PSI, Catholic University of Leuven, Belgium, 2002.Google Scholar
  2. 2.
    J.S. De Bonet. Multiresolution Sampling Procedure for Analysis and Synthesis of Texture Images. Proc. Computer Graphics, ACM SIGGRAPH’97, 1997, pp. 361–368.Google Scholar
  3. 3.
    A. Efros and T. Leung. Texture Synthesis by Non-Parametric Sampling. Proc. Int. Conf. Computer Vision (ICCV’99), Vol. 2, 1999, pp. 1033–1038.CrossRefGoogle Scholar
  4. 4.
    V. Ferrari, T. Tuytelaars, and L. Van Gool. Real-Time Affine Region Tracking and Coplanar Grouping. IEEE Computer Soc. Conf. on Computer Vision and Pattern Recognition (CVPR’01), December 2001, Vol. 2, pp. 226–233.Google Scholar
  5. 5.
    A. Gagalowicz and S.D. Ma. Sequential Synthesis of Natural Textures. Computer Vision, Graphics, and Image Processing, Vol. 30, 1985, pp. 289–315.CrossRefGoogle Scholar
  6. 6.
    G. Gimel’farb, Image Textures and Gibbs Random Fields. Kluwer Academic Publishers: Dordrecht, 1999, 250 p.Google Scholar
  7. 7.
    D. Heeger and J. Bergen. Pyramid-Based Texture Analysis/Synthesis, ASM SIGGRAPH’ 95, pp. 239–238, 1995.Google Scholar
  8. 8.
    A. Hertzmann, C. Jacobs, N. Oliver, B. Curless, and D. Salesin. Image analogies. ACM SIGGRAPH2001, pp. 327–340, 2001.Google Scholar
  9. 9.
    B. Julesz and R.A. Schumer. Early Visual Perception. Ann. Rev. Psychol. Vol. 32, 1981, pp. 575–627 (p. 594).CrossRefGoogle Scholar
  10. 10.
    R. Paget. Nonparametric Markov Random Field Models for Natural Texture Images. PhD Thesis, University of Queensland, February 1999.Google Scholar
  11. 11.
    L.-Y. Wei and M. Levoy. Fast Texture Synthesis Using Tree-Structured Vector Quantization. SIGGRAPH 2000, pp. 479–488.Google Scholar
  12. 12.
    Y.N. Wu, S.C. Zhu, and X. Liu. Equivalence of Julesz and Gibbs Texture Ensembles. Proc. Int. Conf. Computer Vision (ICCV’99), 1999, pp. 1025–1032.Google Scholar
  13. 13.
    A. Zalesny and L. Van Gool. A Compact Model for Viewpoint Dependent Texture Synthesis. SMILE 2000, Workshop on 3D Structure from Images, Lecture Notes in Computer Science 2018, M. Pollefeys, L. Van Gool, A. Zisserman, and A. Fitzgibbon (Eds.), 2001, pp. 124–143.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Alexey Zalesny
    • 1
  • Vittorio Ferrari
    • 1
  • Geert Caenen
    • 2
  • Dominik Auf der Maur
    • 1
  • Luc Van Gool
    • 1
    • 2
  1. 1.Swiss Federal Institute of Technology ZurichSwitzerland
  2. 2.Catholic University of LeuvenBelgium

Personalised recommendations