cvpr cvpr2013 cvpr2013-219 cvpr2013-219-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Carl Olsson, Johannes Ulén, Yuri Boykov
Abstract: It is commonly believed that higher order smoothness should be modeled using higher order interactions. For example, 2nd order derivatives for deformable (active) contours are represented by triple cliques. Similarly, the 2nd order regularization methods in stereo predominantly use MRF models with scalar (1D) disparity labels and triple clique interactions. In this paper we advocate a largely overlooked alternative approach to stereo where 2nd order surface smoothness is represented by pairwise interactions with 3D-labels, e.g. tangent planes. This general paradigm has been criticized due to perceived computational complexity of optimization in higher-dimensional label space. Contrary to popular beliefs, we demonstrate that representing 2nd order surface smoothness with 3D labels leads to simpler optimization problems with (nearly) submodular pairwise interactions. Our theoretical and experimental re- sults demonstrate advantages over state-of-the-art methods for 2nd order smoothness stereo. 1
[1] S. Birchfield and C. Tomasi. Multiway cut for stereo and motion with slanted surfaces. In International Conference on Computer Vision, 1999. 1
[2] M. Bleyer, C. Rother, and P. Kohli. Surface stereo with soft segmentation. In IEEE conf on Computer Vision and Pattern Recognition (CVPR). IEEE, 2010. 1
[3] E. Boros and P.L. Hammer. Pseudo-boolean optimization. Discrete applied mathematics, 123(1): 155–225, 2002. 2 111777333644 (a) (b) Figure 5. (a) - Image, (b) - depth map using only the data term, (c) (c) - depth map computed with regularization. Figure 6. (a) - Image, (b) - depth map using only the data term, (c) - depth map computed with regularization.
[4] Y. Boykov, O. Veksler, and R. Zabih. Fast approximate energy minimization via graph cuts. IEEE Trans. Pattern Anal. Mach. Intell. , 2001. 1, 2, 4
[5] F. Devernay and O. Faugeras. Computing differential properties of 3-d shapes from stereoscopic images without 3d models. In IEEE conf. on Computer Vision and Pattern Recognition, 1994. 1
[6] Pedro F. Felzenszwalb and Daniel P. Huttenlocher. Efficient belief propagation for early vision. Int. J. Comput. Vision, 70(1):41–54, October 2006. 1
[7] V. Kolmogorov and R. Zabih. Multi-camera scene reconstruction via graph cuts. In European conf. on Computer Vision, 2002. 1
[8] V. S. Lempitsky, C. Rother, S. Roth, and A. Blake. Fusion moves for markov random field optimization. IEEE Trans. Pattern Anal. Mach. Intell., 32(8): 1392–1405, 2010. 1, 2, 3
[9] G. Li and S.W. Zucker. Differential geometric inference in surface stereo. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 32(1):72–86, 2010. 1, 2
[10] C. Olsson and Y. Boykov. Curvature-based regularization for surface approximation. In IEEE Conference on Computer Vision and Pattern Recognition, 2012. 1
[11] C. Rother, V. Kolmogorov, V. S. Lempitsky, and M. Szummer. Optimizing binary mrfs via extended roof duality. In IEEE conf. on Computer Vision and Pattern Recognition, 2007. 2, 6
[12] D. Scharstein and R. Szeliski. High-accuracy stereo depth maps using structured light. In IEEE conf on Computer Vision and Pattern Recognition, volume 1, 2003. 6, 7
[13] Steven M. Seitz. The space of all stereo images. In Int. conf. Computer Vision, 2001 . 2
[14] Y. Wei and L. Quan. Asymmetrical occlusion handling using graph cut for multi-view stereo. In IEEE conf. on Computer Vision and Pattern Recognition, 2005. CVPR, 2005. 5
[15] O.J. Woodford, P.H.S. Torr, I.D. Reid, and A.W. Fitzgibbon. Global stereo reconstruction under second order smoothness priors. In IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009. 1, 2, 6 111777333755