TILT: Transform Invariant Low-Rank Textures

  • Zhengdong Zhang
  • Xiao Liang
  • Arvind Ganesh
  • Yi Ma
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6494)


In this paper, we show how to efficiently and effectively extract a rich class of low-rank textures in a 3D scene from 2D images despite significant distortion and warping. The low-rank textures capture geometrically meaningful structures in an image, which encompass conventional local features such as edges and corners as well as all kinds of regular, symmetric patterns ubiquitous in urban environments and man-made objects. Our approach to finding these low-rank textures leverages the recent breakthroughs in convex optimization that enable robust recovery of a high-dimensional low-rank matrix despite gross sparse errors. In the case of planar regions with significant projective deformation, our method can accurately recover both the intrinsic low-rank texture and the precise domain transformation. Extensive experimental results demonstrate that this new technique works effectively for many near-regular patterns or objects that are approximately low-rank, such as human faces and text.


Convex Optimization Scale Invariant Feature Transform Projective Transformation Texture Function Salient Region 
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.
    Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. PAMI 27, 1615–1630 (2005)CrossRefGoogle Scholar
  2. 2.
    Winder, S., Brown, M.: Learning local image descriptor. In: Proc. of CVPR (2007)Google Scholar
  3. 3.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV 60, 91–110 (2004)CrossRefGoogle Scholar
  4. 4.
    Mikolajczyk, K., Schmid, C.: Scale and affine invariant interest point descriptors. IJCV 60 (2004)Google Scholar
  5. 5.
    Morel, J.M., Yu, G.: Asift: A new framework for fully affine invariant image comparison. SIAM Journal on Imaging Sciences 2 (2009)Google Scholar
  6. 6.
    Sundaramoorthi, G., Petersen, P., Varadarajan, V.S., Soatto, S.: On the set of images modulo viewpoint and constrast changes. In: Proc. of CVPR (2009)Google Scholar
  7. 7.
    Ma, Y., Soatto, S., Kosecka, J., Sastry, S.: An Invitation to 3D Vision. Springer, Heidelberg (2004)CrossRefzbMATHGoogle Scholar
  8. 8.
    Kosecka, J., Zhang, W.: Extraction, matching, and pose recovery based on dominant rectagular structures. In: CVGIP: Image Understanding, vol. 100, pp. 274–293 (2005)Google Scholar
  9. 9.
    Schindler, G., Krishnamurthy, P., Lublinerman, R., Liu, Y., Dellaert, F.: Detecting and matching repeated patterns for automatic geo-tagging in urban environments. In: Proc. of CVPR (2008)Google Scholar
  10. 10.
    Park, M., Lee, S., Chen, P., Kashyap, S., Butt, A., Liu, Y.: Performance evaluation of state-of-the-art discrete symmetry detection algorithms. In: Proc. of CVPR (2008)Google Scholar
  11. 11.
    Yang, A., Huang, K., Rao, S., Ma, Y.: Symmetry-based 3-D reconstruction from perspective images. In: Computer Vision and Image Understanding, vol. 99, pp. 210–240 (2005)Google Scholar
  12. 12.
    Levina, E., Bickel, P.J.: Texture synthesis and non-parametric resampling of random fields. Annals of Statistics 34, 1751–1773 (2006)MathSciNetCrossRefzbMATHGoogle Scholar
  13. 13.
    Garding, J., Lindeberg, T.: Direct computation of shape cues using scale-adapted spatial derivative operators. IJCV 17, 163–191 (1996)CrossRefGoogle Scholar
  14. 14.
    Peng, Y., Ganesh, A., Wright, J., Xu, W., Ma, Y.: RASL: Robust alignment by sparse and low-rank decomposition for linearly correlated images. In: Proc. of CVPR (2010)Google Scholar
  15. 15.
    Candès, E., Li, X., Ma, Y., Wright, J.: Robust principal component analysis? (2009) (preprint) Google Scholar
  16. 16.
    Bertsekas, D.P.: Nonlinear Programming. Athena Scientific, Belmont (2004)zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Zhengdong Zhang
    • 1
  • Xiao Liang
    • 1
  • Arvind Ganesh
    • 2
  • Yi Ma
    • 1
    • 2
  1. 1.Visual Computing GroupMicrosoft Research AsiaBeijingChina
  2. 2.Coordinated Science LabUniversity of IllinoisUrbana-ChampaignUSA

Personalised recommendations