Abstract
We propose a novel regularization model for stereo matching that uses large neighborhood windows. The model is based on the observation that in a local neighborhood there exists a linear relationship between pixel values and disparities. Compared to the traditional boundary preserving regularization models that use adjacent pixels, the proposed model is robust to image noise and captures higher level interactions. We develop a globally optimized stereo matching algorithm based on this regularization model. The algorithm alternates between finding a quadratic upper bound of the relaxed energy function and solving the upper bound using iterative reweighted least squares. To reduce the chance of being trapped in local minima, we propose a progressive convex-hull filter to tighten the data cost relaxation. Our evaluation on the Middlebury datasets shows the effectiveness of our method in preserving boundary sharpness while keeping regions smooth. We also evaluate our method on a wide range of challenging real-world videos. Experimental results show that our method outperforms existing methods in temporal consistency.
Chapter PDF
Similar content being viewed by others
Keywords
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.
References
Bobick, A.F., Intille, S.S.: Large occlusion stereo. IJCV 33, 181–200 (1999)
Boykov, Y., Veksler, O., Zabih, R.: Fast approximate energy minimization via graph cuts. TPAMI (2001)
Scharstein, D., Szeliski, R.: A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. IJCV 47, 7–42 (2002)
Freeman, W., Pasztor, E.: Learning low-level vision. In: ICCV (1999)
Smith, B., Zhang, L., Jin, H.: Stereo matching with nonparametric smoothness priors in feature space. In: CVPR (2009)
Jung, H., Lee, K.M., Lee, S.U.: Stereo reconstruction using high order likelihood. In: ICCV (2011)
Sun, J., Shum, H.Y., Zheng, N.N.: Stereo matching using belief propagation. TPAMI 25, 787–800 (2003)
Woodford, O.J., Torr, P.H.S., Reid, I.D., Fitzgibbon, A.W.: Global stereo reconstruction under second order smoothness priors. In: CVPR (2008)
Yang, Q., Wang, L., Yang, R., Stewénius, H., Nister, D.: Stereo matching with color-weighted correlation, hierarchical belief propagation and occlusion handling. TPAMI 31, 492–504 (2009)
Bleyer, M., Rother, C., Kohli, P.: Surface stereo with soft segmentation. In: CVPR (2010)
Bhusnurmath, A., Taylor, C.: Solving stereo matching problems using interior point methods. In: 3DPVT (2008)
Rhemann, C., Hosni, A., Bleyer, M., Rother, C., Gelautz, M.: Fast cost-volume filtering for visual correspondence and beyond. In: CVPR (2011)
Levin, A., Lischinski, D., Weiss, Y.: A closed-form solution to natural image matting. TPAMI (2008)
He, K., Sun, J., Tang, X.: Guided Image Filtering. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part I. LNCS, vol. 6311, pp. 1–14. Springer, Heidelberg (2010)
Yoon, K.J., Kweon, I.S.: Adaptive support-weight approach for correspondence search. TPAMI 28, 650–656 (2006)
Xu, L., Jia, J.: Stereo Matching: An Outlier Confidence Approach. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part IV. LNCS, vol. 5305, pp. 775–787. Springer, Heidelberg (2008)
Mei, X., Sun, X., Zhou, M., Jiao, S., Wang, H., Zhang, X.: On building an accurate stereo matching system on graphics hardware. In: GPUCV (2011)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zhu, S., Zhang, L., Jin, H. (2012). A Locally Linear Regression Model for Boundary Preserving Regularization in Stereo Matching. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds) Computer Vision – ECCV 2012. ECCV 2012. Lecture Notes in Computer Science, vol 7576. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-33715-4_8
Download citation
DOI: https://doi.org/10.1007/978-3-642-33715-4_8
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-33714-7
Online ISBN: 978-3-642-33715-4
eBook Packages: Computer ScienceComputer Science (R0)