Discovering Texture Regularity as a Higher-Order Correspondence Problem

  • James Hays
  • Marius Leordeanu
  • Alexei A. Efros
  • Yanxi Liu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3952)


Understanding texture regularity in real images is a challenging computer vision task. We propose a higher-order feature matching algorithm to discover the lattices of near-regular textures in real images. The underlying lattice of a near-regular texture identifies all of the texels as well as the global topology among the texels. A key contribution of this paper is to formulate lattice-finding as a correspondence problem. The algorithm finds a plausible lattice by iteratively proposing texels and assigning neighbors between the texels. Our matching algorithm seeks assignments that maximize both pair-wise visual similarity and higher-order geometric consistency. We approximate the optimal assignment using a recently developed spectral method. We successfully discover the lattices of a diverse set of unsegmented, real-world textures with significant geometric warping and large appearance variation among texels.


Texture Element Optimal Assignment Normalize Cross Correlation Pairwise Constraint Correspondence Problem 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Gibson, J.J.: The Perception of the Visual World. Houghton Mifflin, Boston, Massachusetts (1950)Google Scholar
  2. 2.
    Julesz, B.: Visual pattern discrimination. IRE Transactions on Information Theory 8, 84–92 (1962)CrossRefGoogle Scholar
  3. 3.
    Malik, J., Belongie, S., Shi, J., Leung, T.: Textons, contours and regions: Cue integration in image segmentation. In: ICCV, pp. 918–925 (1999)Google Scholar
  4. 4.
    Garding, J.: Surface orientation and curvature from differential texture distortion. In: ICCV, pp. 733–739 (1995)Google Scholar
  5. 5.
    Malik, J., Rosenholtz, R.: Computing local surface orientation and shape from texture for curved surfaces. Int. J. Computer Vision, 149–168 (1997)Google Scholar
  6. 6.
    Forsyth, D.: Shape from texture without boundaries. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2352, pp. 225–239. Springer, Heidelberg (2002)CrossRefGoogle Scholar
  7. 7.
    Puzicha, J., Hofmann, T., Buhmann, J.: Non-parametric similarity measures for unsupervised texture segmentation and image retrieval. In: CVPR, pp. 267–272 (1997)Google Scholar
  8. 8.
    Leung, T., Malik, J.: Recognizing surfaces using three-dimensional textons. In: ICCV (1999)Google Scholar
  9. 9.
    Varma, M., Zisserman, A.: Texture classification: Are filter banks necessary? In: CVPR, pp. 691–698 (2003)Google Scholar
  10. 10.
    Brooks, S., Dodgson, N.: Self-similarity based texture editing. In: SIGGRAPH 2002, pp. 653–656. ACM Press, New York (2002)Google Scholar
  11. 11.
    Cohen, M.F., Shade, J., Hiller, S., Deussen, O.: Wang tiles for image and texture generation. ACM Trans. Graph. 22, 287–294 (2003)CrossRefGoogle Scholar
  12. 12.
    Lobay, A., Forsyth, D.A.: Recovering shape and irradiance maps from rich dense texton fields. In: CVPR, pp. 400–406 (2004)Google Scholar
  13. 13.
    Liu, Y., Lin, W.C., Hays, J.: Near-regular texture analysis and manipulation. In: ACM Transactions on Graphics, SIGGRAPH (2004)Google Scholar
  14. 14.
    Leung, T.K., Malik, J.: Detecting, localizing and grouping repeated scene elements from an image. In: ECCV, London, UK, pp. 546–555. Springer, Heidelberg (1996)Google Scholar
  15. 15.
    Schaffalitzky, F., Zisserman, A.: Geometric grouping of repeated elements within images. In: Shape, Contour and Grouping in Computer Vision, pp. 165–181 (1999)Google Scholar
  16. 16.
    Turina, A., Tuytelaars, T., Gool, L.V.: Efficient grouping under perspective skew. In: CVPR, pp. 247–254 (2001)Google Scholar
  17. 17.
    Grünbaum, B., Shephard, G.C.: Tilings and Patterns. W. H. Freeman and Company, New York (1987)MATHGoogle Scholar
  18. 18.
    Belongie, S., Malik, J., Puzicha, J.: Shape matching and object recognition using shape contexts. PAMI 24, 509–522 (2002)CrossRefGoogle Scholar
  19. 19.
    Berg, A.C., Berg, T.L., Malik, J.: Shape matching and object recognition using low distortion correspondence. In: CVPR (2005)Google Scholar
  20. 20.
    Leordeanu, M., Hebert, M.: A spectral technique for correspondence problems using pairwise constraints. In: ICCV (2005)Google Scholar
  21. 21.
    Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide baseline stereo from maximally stable extremal regions. In: British Machine Vision Conference (2002)Google Scholar
  22. 22.
    Liu, Y., Collins, R., Tsin, Y.: A computational model for periodic pattern perception based on frieze and wallpaper groups. PAMI 26, 354–371 (2004)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • James Hays
    • 1
  • Marius Leordeanu
    • 1
  • Alexei A. Efros
    • 1
  • Yanxi Liu
    • 1
  1. 1.School of Computer ScienceCarnegie Mellon UniversityPittsburghUSA

Personalised recommendations