Abstract
In this paper, we propose a new tool to efficiently extract a class of “low-rank textures” in a 3D scene from user-specified windows in 2D images despite significant corruptions 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 many 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 affine or projective deformation, our method can accurately recover both the intrinsic low-rank texture and the unknown transformation, and hence both the geometry and appearance of the associated planar region in 3D. Extensive experimental results demonstrate that this new technique works effectively for many regular and near-regular patterns or objects that are approximately low-rank, such as symmetrical patterns, building facades, printed text, and human faces.
Similar content being viewed by others
References
Baker, S., & Matthews, I. (2004). Lucas-Kanade 20 years on: A unifying framework. International Journal of Computer Vision, 56(3), 221–255.
Becker, S., Candès, E., & Grant, M. (2011). Templates for convex cone problems with applications to sparse signal recovery. Mathematical Programming Computation, 3(3), 165–218.
Bertsekas, D. P. (2004). Nonlinear programming. Belmont: Athena Scientific.
Cai, J., Candès, E., & Shen, Z. (2010). A singular value thresholding algorithm for matrix completion. SIAM Journal on Optimization, 20(4), 1956–1982.
Candès, E., & Recht, B. (2009). Exact matrix completion via convex optimization. Foundations of Computational Mathematics, 9(6), 717–772.
Candès, E., & Tao, T. (2010). The power of convex relaxation: Near-optimal matrix completion. IEEE Transactions on Information Theory, 56(5), 2053–2080.
Candès, E., Li, X., Ma, Y., & Wright, J. (2011). Robust principal component analysis? Journal of the ACM, 58(3), 11:1–11:37.
Canny, J. (1986). A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 8(6), 679–698.
Chandrasekaran, V., Sanghavi, S., Parrilo, P., & Willsky, A. (2011). Rank-sparsity incoherence for matrix decomposition. SIAM Journal on Optimization, 21(2), 572–596.
Chang, S., Davis, L., Dunn, S., Eklundh, J., & Rosenfeld, A. (1987). Texture discrimination by projective invariants. Pattern Recognition Letters, 5, 337–342.
Chen, J. L., & Kundu, A. (1994). Rotation and gray scale transform invariant texture identification using wavelet decomposition and hidden Markov model. IEEE Transactions on Pattern Analysis and Machine Intelligence, 16(2), 208–214.
Cohen, F., Fan, Z., & Patel, M. (1991). Classification of rotated and scaled texture images using Gaussian Markov random field models. IEEE Transactions on Pattern Analysis and Machine Intelligence, 13, 192–202.
Cromme, L. (1978). Strong uniqueness: A far-reaching criterion for the convergence analysis of iterative procedures. Numerische Mathematik, 29, 179–193.
Do, M., & Vetterli, M (2002). Rotation invariant texture characterization and retrieval using steerable wavelet-domain hidden Markov models. IEEE Transactions on Multimedia, 4(4), 517–527.
Eckstein, J., & Bertsekas, D. (1992). On the Douglas-Rachford splitting method and the proximal point algorithm for maximal monotone operators. Mathematical Programming, 55, 293–318.
Frey, B., & Jojic, N. (1999). Transformed component analysis: Joint estimation of spatial transformations and image components. In Proc. of IEEE international conference on computer vision.
Gabay, D., & Mercier, B. (1976). A dual algorithm for the solution of nonlinear variational problems via finite element approximations. Computers and Mathematics with Applications, 2, 17–40.
Ganesh, A., Lin, Z., Wright, J., Wu, L., Chen, M., & Ma, Y. (2009). Fast algorithms or recovering a corrupted low-rank matrix. In Proceedings of third international workshop on computational advances in multi-sensor adaptive processing.
Garding, J., & Lindeberg, T. (1996). Direct computation of shape cues using scale-adapted spatial derivative operators. International Journal of Computer Vision, 17(2), 163–191.
Glowinski, R., & Marroco, A. (1975). Sur l’approximation, par elements finis d’ordre un, et la resolution, par penalisation-dualite, d’une classe de problemes de Dirichlet non lineares. Revuew Francaise d’Automatique, Informatique et Recherche Operationelle, 9, 41–76.
Greenspan, H., Belongie, S., Goodman, R., & Perona, P. (1994). Rotation invariant texture recognition using a steerable pyramid. In Proc. of international conference on pattern recognition.
Haley, G., & Manjunath, B. (1999). Rotation-invariant texture classification using a complete space-frequency model. IEEE Transactions on Image Processing, 8, 255–269.
Harris, C., & Stephens, M. (1988). A combined corner and edge detector. In Proc. of 4th alvey vision conference.
He, B. (2009). Parallel splitting augmented Lagrangian methods for monotone structured variational inequalities. Computational Optimization and Applications, 42(2).
He, B., Tao, M., & Yuan, X. (2011). Alternating direction method with Gaussian back substitution for separable convex programming. SIAM Journal on Optimization, under-revision.
Jittorntrum, K., & Osborne, M. (1980). Strong uniqueness and second order convergence in nonlinear discrete approximation. Numerische Mathematik, 34, 439–455.
Kondepudy, R., & Healey, G. (1994). Using moment invariants to analyze 3-D color textures. In Proc. of IEEE international conference on image processing.
Kosecka, J., & Zhang, W. (2005). Extraction, matching, and pose recovery based on dominant rectangular structures. CVGIP. Image Understanding, 100(3), 274–293.
Lee, S., & Liu, Y. (2010). Skewed rotation symmetry group detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 32(9), 1659–1672.
Leung, T., & Malik, J. (2001). Representing and recognizing the visual appearance of materials using three-dimensional textons. International Journal of Computer Vision, 43(1), 29–44.
Levina, E., & Bickel, P. J. (2006). Texture synthesis and non-parametric resampling of random fields. Annals of Statistics, 34(4), 1751–1773.
Lin, Z., Chen, M., Wu, L., & Ma, Y. (2009). The augmented Lagrange multiplier method for exact recovery of corrupted low-rank matrices (UIUC Technical Report UILU-ENG-09-2215).
Liu, R., Lin, Z., Wei, S., & Su, Z. (2011). Solving principal component pursuit in linear time via l 1 filtering (Preprint).
Liu, Y., & Collins, R. (2001). Skewed symmetry groups. In Proc. of IEEE conference on computer vision and pattern recognition.
Liu, Y., Collins, R., & Tsin, Y. (2004). A computational model for periodic pattern perception based on Frieze and wallpaper groups. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(3), 354–371.
Liu, Y., Hel-Or, H., Kaplan, C. S., & Gool, L. V. (2010). Computational symmetry in computer vision and computer graphics. Foundations and Trends in Computer Graphics and Vision, 5(1–2), 1–195.
Lowe, D. G. (2004). Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60, 91–110.
Ma, Y., Soatto, S., Kosecka, J., & Sastry, S. (2004). An invitation to 3D vision. Berlin: Springer.
Madiraju, S., & Liu, C. (1994). Rotation invariant texture classification using covariance. In Proc. of IEEE international conference on image processing.
Mikolajczyk, K., & Schmid, C. (2004). Scale and affine invariant interest point descriptors. International Journal of Computer Vision, 60(1), 63–86.
Mikolajczyk, K., & Schmid, C. (2005). A performance evaluation of local descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence, 27, 1615–1630.
Mobahi, H., Zhou, Z., Yang, A., & Ma, Y. (2011). Holistic 3D reconstruction of urban structures from low-rank textures. In Third international IEEE workshop on 3D representation and recognition.
Morel, J. M., & Yu, G. (2009). ASIFT: A new framework for fully affine invariant image comparison. SIAM Journal on Imaging Sciences, 2(2), 438–469.
Park, M., Lee, S., Chen, P., Kashyap, S., Butt, A., & Liu, Y. (2008). Performance evaluation of state-of-the-art discrete symmetry detection algorithms. In Proc. of IEEE conference on computer vision and pattern recognition.
Park, M., Brocklehurst, K., Collins, R., & Liu, Y. (2010). Translation-symmetry-based perceptual grouping with applications to urban scenes. In Asian conference on computer vision.
Peng, Y., Ganesh, A., Wright, J., Xu, W., & Ma, Y. (2010). RASL: Robust alignment by sparse and low-rank decomposition for linearly correlated images. In Proc. of IEEE conference on computer vision and pattern recognition.
Peng, Y., Ganesh, A., Wright, J., Xu, W., & Ma, Y. (2011). RASL: Robust alignment by sparse and low-rank decomposition for linearly correlated images. IEEE Transactions on Pattern Analysis and Machine Intelligence, to appear.
Recht, B., Fazel, M., & Parillo, P. (2010). Guaranteed minimum rank solution of matrix equations via nuclear norm minimization. SIAM Review, 52(3), 471–501.
Schindler, G., Krishnamurthy, P., Lublinerman, R., Liu, Y., & Dellaert, F. (2008). Detecting and matching repeated patterns for automatic geo-tagging in urban environments. In Proc. of IEEE conference on computer vision and pattern recognition.
Sundaramoorthi, G., Petersen, P., Varadarajan, V. S., & Soatto, S. (2009). On the set of images modulo viewpoint and contrast changes. In Proc. of IEEE conference on computer vision and pattern recognition.
Toh, K., & Yun, S. (2010). An accelerated proximal gradient algorithm for nuclear norm regularized least squares problems. Pacific Journal of Optimization, 6, 615–640.
Winder, S., & Brown, M. (2007). Learning local image descriptor. In Proc. of IEEE conference on computer vision and pattern recognition.
Wu, W. R., & Wei, S. C. (1996). Rotation and gray-scale transform-invariant texture classification using spiral resampling, subband decomposition and hidden Markov model. IEEE Transactions on Image Processing, 5, 1423–1434.
Yang, A., Huang, K., Rao, S., & Ma, Y. (2005). Symmetry-based 3-D reconstruction from perspective images. Computer Vision and Image Understanding, 99(2), 210–240.
Yuan, X., & Tao, M. (2011). Recovering low-rank and sparse components of matrices from incomplete and noisy observations. SIAM Journal on Optimization, 21(1), 57–81.
Zhang, Z., Liang, X., & Ma, Y. (2011a). Unwrapping low-rank textures on generalized cylindrical surfaces. In Proc. of IEEE international conference on computer vision.
Zhang, Z., Matsushita, Y., & Ma, Y. (2011b). Camera calibration with lens distortion from low-rank textures. In Proc. of IEEE conference on computer vision and pattern recognition.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Zhang, Z., Ganesh, A., Liang, X. et al. TILT: Transform Invariant Low-Rank Textures. Int J Comput Vis 99, 1–24 (2012). https://doi.org/10.1007/s11263-012-0515-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11263-012-0515-x