iccv iccv2013 iccv2013-304 iccv2013-304-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Philipp Heise, Sebastian Klose, Brian Jensen, Alois Knoll
Abstract: Most stereo correspondence algorithms match support windows at integer-valued disparities and assume a constant disparity value within the support window. The recently proposed PatchMatch stereo algorithm [7] overcomes this limitation of previous algorithms by directly estimating planes. This work presents a method that integrates the PatchMatch stereo algorithm into a variational smoothing formulation using quadratic relaxation. The resulting algorithm allows the explicit regularization of the disparity and normal gradients using the estimated plane parameters. Evaluation of our method in the Middlebury benchmark shows that our method outperforms the traditional integer-valued disparity strategy as well as the original algorithm and its variants in sub-pixel accurate disparity estimation.
[1] Middlebury stereo benchmark. http : / /vi s ion . middlebury . edu / st e reo / . 5
[2] Portal stereo scene. http : / / cmp . fe lk . cvut . c z / ˜ce ch j / GC S / st e re o-image s / . 4
[3] J.-F. Aujol, G. Gilboa, T. Chan, and S. Osher. Structure-texture image decomposition—modeling, algorithms, and parameter selection. Int. J. Comput. Vision, 67(1): 111–136, 2006. 3
[4] C. Barnes, E. Shechtman, A. Finkelstein, and D. Goldman. PatchMatch: a randomized correspondence algorithm for structural image editing. ACM Transactions on Graphics (TOG), 28(3):24, 2009. 1
[5] C. Barnes, E. Shechtman, D. Goldman, and A. Finkelstein. The generalized patchmatch correspondence al22336666 gorithm. Computer Vision–ECCV 2010, pages 29–43, 2010. 1
[18] C. Strecha, R. Fransens, and L. Van Gool. Combined depth and outlier estimation in multi-view stereo.
[6]sFPpM.oB ndeP s: nec,PeaCtFc.iheMRldoatEhcsehtri,mBAae.tlioeFnfi.tzPgrIionbp aPogrnoat,cioeane d ifnoJgr.sKCoa furt hze .[7]
[8]
[9]
[10]
[11]
[12]
[13]
[14]
[15]
[16]
[17] 7C o m p u te r SVoiscioentyaCndonPfaetre nrcneRoenc,o2g:2n3it9o4n–,2 40 16,2I0E 06E. British Machine Vision Conference, pages 132. 1– 132.1 1. BMVA Press, 2012. 1, 5, 6 M. Bleyer, C. Rhemann, and C. Rother. PatchMatch Stereo - Stereo Matching with Slanted Support Windows. Proc. BMVC, pages 1–1 1, July 2011. 1, 2, 4, 5, 6 A. Chambolle and T. Pock. A first-order primal-dual algorithm for convex problems with applications to imaging. Journal of Mathematical Imaging and Vision, 40(1): 120–145, 2011. 3, 4 A. Handa, R. A. Newcombe, A. Angeli, and A. J. Davison. Applications of legendre-fenchel transformation to computer vision problems. Technical Report DTR1 1-7, Imperial College - Department of Computing, September 2011. 4 R. Hartley and A. Zisserman. Multiple View Geometry in Computer Vision. Cambridge University Press, ISBN: 0521540518, second edition, 2004. 2 H. Hirschmuller and D. Scharstein. Evaluation of Cost Functions for Stereo Matching. In Computer Vision and Pattern Recognition, 2007. CVPR ’07. IEEE Conference on, pages 1–8, 2007. 7 Y. Huang, M. K. Ng, and Y.-W. Wen. A Fast Total Variation Minimization Method for Image Restoration. Multiscale Modeling & Simulation, 7(2):774– 795, Jan. 2008. 2, 3 P. Monasse. Quasi-Euclidean Epipolar Rectification. Image Processing On Line, 2011, 2011. 1 R. A. Newcombe, S. J. Lovegrove, and A. J. Davison. DTAM: Dense Tracking and Mapping in RealTime. ICCV ’11: Proceedings of the 2011 International Conference on Computer Vision, pages 1–8, Aug. 2011. 2, 3, 4 D. Scharstein and R. Szeliski. A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms. Int. J. Comput. Vision, 47(1-3):7–42, 2002. 2, 5, 6 D. Scharstein and R. Szeliski. High-accuracy stereo depth maps using structured light. In Computer Vision and Pattern Recognition, 2003. Proceedings. 2003 IEEE Computer Society Conference on, 2003. 7 F. Steinbr u¨cker, T. Pock, and D. Cremers. Large displacement optical flow computation without warping. Computer Vision, 2009 IEEE 12th International Conference on, pages 1609–1614, 2009. 2, 3, 4 22336677