Texture is frequently considered as a repetitive spatial arrangement of texels, the primitive elements of texture. We define the texel as a bunch of image signals that has a particular geometric structure (shape and size). This provides for fast synthesis of a spatially homogeneous texture by bunch sampling. First, the structure of the texels and a placement grid to spatially arrange them are estimated from a training image using a generic Gibbs random field model of the texture. Then at the synthesis stage, the structure serves as a sampling mask to capture the texels from the training image. Random positions for replicating texels to form a synthetic large-size texture are selected according to the placement grid.


Training Image Partial Energy Texture Synthesis Pixel Pair Colour 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.
    Besag, J.E.: On the statistical analysis of dirty pictures. Journal of the Royal Statistical Society B48, 259–302 (1986)zbMATHMathSciNetGoogle Scholar
  2. 2.
    Brodatz, P.: Textures: A Photographic Album for Artists and Designers. Dover, New York (1966)Google Scholar
  3. 3.
    Chellappa, R.: Two dimensional discrete Gaussian Markov random field models for image processing. In: Progress in Pattern Recognition, vol. 2, pp. 79–112. Elsevier Science Publishers B. V, Amsterdam (1985)Google Scholar
  4. 4.
    Cross, G.R., Jain, A.K.: Markov random field texture models. IEEE Trans. Pattern Anal. Machine Intell. 5, 25–39 (1983)CrossRefGoogle Scholar
  5. 5.
    Efros, A.A., Freeman, W.T.: Image quilting for texture synthesis and transfer. In: Proceedings,SIGGRAPH 2001, Computer Graphics, pp. 341–346. ACM Press / ACM SIGGRAPH (2001)Google Scholar
  6. 6.
    Efros, A.A., Leung, T.K.: Texture synthesis by non-parametric sampling. In: Proc. Int. Conf. on Computer Vision (ICCV 1999), Kerkira, Corfu, Greece, September 20–25, vol. 2, pp. 1033–1038 (1999)Google Scholar
  7. 7.
    Gimel’farb, G.L.: Texture modeling with multiple pairwise pixel interactions. IEEE Trans. Pattern Anal. Machine Intell. 18, 1110–1114 (1996)CrossRefGoogle Scholar
  8. 8.
    Gimel’farb, G.L.: Image Textures and Gibbs Random Fields. Kluwer Academic Publishers, Dordrecht (1999)zbMATHGoogle Scholar
  9. 9.
    Gimel’farb, G.L., Zhou, D.: Fast synthesis of large-size textures using bunch sampling. In: Proc. Image and Vision Computing New Zealand (IVCNZ 2002), Auckland, New Zealand, November 26–28, pp. 215–220 (2002)Google Scholar
  10. 10.
    Haralick, R.: Statistical and structural approaches to texture. Proc. IEEE 67(5), 786–804 (1979)CrossRefGoogle Scholar
  11. 11.
    Liang, L., Liu, C., Shum, H.Y.: Real-time texture synthesis by patch-based sampling. Technical Report MSR-TR-2001-40, Micorsoft Research (2001)Google Scholar
  12. 12.
    Neubeck, A., Zalesny, A., van Gool, L.: Cut-primed smart copying. In: Proc. 3rd Int. Workshop “Texture 2003”, Nice, France, October 17, pp. 119–124. Heriot-Watt Univ. (2003)Google Scholar
  13. 13.
    Picard, R., Graszyk, C., Mann, S., et al.: VisTex Database. MIT Media Lab, Cambridge (1995)Google Scholar
  14. 14.
    Rosin, P.L.: Unimodal thresholding. Pattern Recognition 34(11), 2083–2096 (2001)zbMATHCrossRefGoogle Scholar
  15. 15.
    Voss, K., Suesse, H.: Invariant fitting of planar objects with primitives. IEEE Trans. Pattern Anal. Machine Intell. 19, 80–84 (1997)CrossRefGoogle Scholar
  16. 16.
    Zhou, D., Gimel’farb, G.L.: Bunch sampling for fast texutre synthesis. In: Petkov, N., Westenberg, M.A. (eds.) CAIP 2003. LNCS, vol. 2756, pp. 124–131. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  17. 17.
    Zhu, S., Wu, Y., Mumford, D.: Filters, random fields and maximum entropy (FRAME): To a unified theory for texture modeling. International Journal of Computer Vision 27(2), 107–126 (1998)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Dongxiao Zhou
    • 1
  • Georgy Gimel’farb
    • 1
  1. 1.CITR, Tamaki Campus, Department of Computer ScienceThe University of AucklandAucklandNew Zealand

Personalised recommendations