iccv iccv2013 iccv2013-252 iccv2013-252-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Zhan Yu, Xinqing Guo, Haibing Lin, Andrew Lumsdaine, Jingyi Yu
Abstract: Light fields are image-based representations that use densely sampled rays as a scene description. In this paper, we explore geometric structures of 3D lines in ray space for improving light field triangulation and stereo matching. The triangulation problem aims to fill in the ray space with continuous and non-overlapping simplices anchored at sampled points (rays). Such a triangulation provides a piecewise-linear interpolant useful for light field superresolution. We show that the light field space is largely bilinear due to 3D line segments in the scene, and direct triangulation of these bilinear subspaces leads to large errors. We instead present a simple but effective algorithm to first map bilinear subspaces to line constraints and then apply Constrained Delaunay Triangulation (CDT). Based on our analysis, we further develop a novel line-assisted graphcut (LAGC) algorithm that effectively encodes 3D line constraints into light field stereo matching. Experiments on synthetic and real data show that both our triangulation and LAGC algorithms outperform state-of-the-art solutions in accuracy and visual quality.
[1] E. H. Adelson and J. R. Bergen. The plenoptic function and the elements of early vision. In Computational Models of Visual Processing, pages 3–20. MIT Press, 1991.
[2] D. Attali and J.-D. Boissonnat. of points on polyhedral 30(3):437–452,
[3] surfaces. Complexity Discrete of the delaunay triangulation & Computational Geometry, 2003. M. Bleyer, C. Rother, and P. Kohli. Surface stereo with soft segmentation. CVPR 2010. In
[4] E. Boros, P. L. Hammer, and G. Tavares. Preprocessing of unconstrained quadratic binary optimization. Technical report, 2006.
[5] Y. Boykov, O. Veksler, and R. Zabih. Fast approximate energy minimization via graph cuts. IEEE TPAMI, 23:2001, 2001.
[6] M. S. Datasets. http://vision.middlebury.edu/stereo/data/.
[7] A. Davis, M. Levoy, and F. Durand. Unstructured light fields. In Proceedings of Eurographics, 2012.
[8] B. N. Delaunay. Sur la sph e´re vide. In Bulletin of Academy of Sciences of the USSR, pages 793–800, 1934.
[9] S. Gortler, R. Grzeszczuk, R. Szeliski, and M. Cohen. The lumigraph. In Proceedings of ACM SIGGRAPH, pages 43–54, 1996.
[10] W. V. D. Hodge and D. Pedoe. Methods of algebraic geometry, volume i(book ii), 1994.
[11] H. Hoppe. Efficient implementation of progressive meshes. Computers and Graphics, 1998.
[12] V. Kolmogorov and C. Rother. Minimizing nonsubmodular functions with graph cuts-a review. TPAMI, 29(7):1274–1279, 2007.
[13] V. Kolmogorov and R. Zabih. Computing visual correspondence with occlusions using graph cuts. In ICCV 2001.
[14] V. Kolmogorov and R. Zabih. Multi-camera scene reconstruction via graph cuts. In Proceedings of the ECCV, 2002.
[15] V. Kolmogorov and R. Zabin. What energy functions can be minimized via graph cuts? PAMI, IEEE Transactions on, 26(2): 147 –159, feb. 2004.
[16] A. Levin and F. Durand. Linear view synthesis using a dimensionality gap light field prior. In Computer Vision and Pattern Recognition (CVPR), 2010 IEEE Conference on, pages 1831–1838, 2010.
[17] M. Levoy and P. Hanrahan. Light field rendering. In Proceedings of ACM SIGGRAPH, pages 31–42, 1996.
[18] A. Lumsdaine and T. Georgiev. The focused plenoptic camera. In IEEE ICCP, pages 1–8, 2009.
[19] Lytro. www.lytro.com.
[20] R. Ng, M. Levoy, M. Brdif, G. Duval, M. Horowitz, and P. Hanrahan. Light field photography with a hand-held plenoptic camera. Stanford University Computer Science Tech Report, 2: 1–1 1, 2005.
[21] J. Peters and U. Reif. The simplest subdivision scheme for smoothing polyhedra. ACM Trans. Graph., 16(4), Oct. 1997.
[22] J. Ponce. What is a camera? In IEEE Conference on Computer Vision and Pattern Recognition, 2009.
[23] J. Ponce and Y. Genc. Epipolar geometry and linear subspace methods: A new approach to weak calibration. IJCV 1996.
[24] POV-Ray. www.povray.org.
[25] C. Rother, V. Kolmogorov, V. Lempitsky, and M. Szummer. Optimizing binary mrfs via extended roof duality. In CVPR 2007.
[26] B. G. S. Wanner. Globally consistent depth labeling of 4d light fields. In Proceedings of IEEE CVPR, 2012.
[27] J. R. Shewchuk. General-dimensional constrained delaunay and constrained regular triangulations i: Combinatorial properties. In Discrete and Computational Geometry, 2005.
[28] C. Shi, G. Wang, X. Pei, H. Bei, and X. Lin. High-accuracy stereo matching based on adaptive ground control points. Submitted to IEEE TIP, 2012.
[29] H. Si. Tetgen: A 3d delaunay triangulator.
[30] R. W. Sumner and J. Popovi´ c. Deformation transfer for triangle meshes. ACM Trans. Graph., Aug. 2004. [3 1] Y. Taguchi, A. Agrawal, A. Veeraraghavan, S. Ramalingam, and R. Raskar. Axial-cones: modeling spherical catadioptric cameras for wide-angle light field rendering. In ACM SIGGRAPH Asia, 2010.
[32] S. University. Stanford light field.
[33] Videocube. Microsoft.
[34] R. von Gioi, J. Jakubowicz, J.-M. Morel, and G. Randall. Lsd: A fast line segment detector with a false detection control. TPAMI, 2010.
[35] S. Wanner and B. Goldl ¨uecke. Spatial and angular variational super-resolution of 4d light fields. 2012.
[36] S. Wanner and B. Goldl ¨uecke. Variational light field analysis for disparity estimation and super-resolution. 2013.
[37] O. Woodford, P. Torr, I. Reid, and A. Fitzgibbon. Global stereo reconstruction under second order smoothness priors. In CVPR, june 2008.
[38] J. Yu. General linear cameras: theory and applications. PhD thesis, 2005.
[39] J. Yu and L. McMillan. General linear cameras. In ECCV (2), pages 14–27, 2004.
[40] Z. Yu and J. Yu. http://www.eecis.udel.edu/ zyu/iccv2013/. 2798 Reference Image LAGC GCDL ×× × Gantry 9L.F L (17 1vs7. 1C2D80L 960) LanF.d F Amethyst oL bFo (17 1a 7c generated by 7th×e a1u7t×hor1s2 8of0 [26] using tdhe A mmeotdhiyfisetd L GFC (1D7L×. 7 sc68en 2799 1024), ×an1d7 a ×re1a0l 2L4F× captured by Lytro [n1g9 P]. OTVh-eR Lytro e re Ssutaltn was