nips nips2008 nips2008-157 nips2008-157-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Ijaz Akhter, Yaser Sheikh, Sohaib Khan, Takeo Kanade
Abstract: Existing approaches to nonrigid structure from motion assume that the instantaneous 3D shape of a deforming object is a linear combination of basis shapes, which have to be estimated anew for each video sequence. In contrast, we propose that the evolving 3D structure be described by a linear combination of basis trajectories. The principal advantage of this approach is that we do not need to estimate any basis vectors during computation. We show that generic bases over trajectories, such as the Discrete Cosine Transform (DCT) basis, can be used to compactly describe most real motions. This results in a significant reduction in unknowns, and corresponding stability in estimation. We report empirical performance, quantitatively using motion capture data, and qualitatively on several video sequences exhibiting nonrigid motions including piece-wise rigid motion, partially nonrigid motion (such as a facial expression), and highly nonrigid motion (such as a person dancing). 1
[1] C. Tomasi and T. Kanade. Shape and motion from image streams under orthography: A factorization method. IJCV, 9:137–154, 1992.
[2] C. Bregler, A. Hertzmann, and H. Biermann. Recovering non-rigid 3D shape from image streams. CVPR, 2:690–696, 2000.
[3] L. Torresani, A. Hertzmann, and C. Bregler. Learning non-rigid 3D shape from 2D motion. NIPS, 2005.
[4] J. Xiao, J. Chai, and T. Kanade. A closed form solution to non-rigid shape and motion recovery. IJCV, 67:233–246, 2006.
[5] L. Torresani, A. Hertzmann, and C. Bregler. Nonrigid structure-from motion: Estimating shape and motion with hierarchical priors. PAMI, 30(5):878–892, May 2008.
[6] J.P. Costeira and T. Kanade. A multibody factorization method for independently moving objects. IJCV, 49:159–179, 1998.
[7] M. Han and T. Kanade. Reconstruction of a scene with multiple linearly moving objects. IJCV, 59:285–300, 2004.
[8] A. Gruber and Y. Weiss. Multibody factorization with uncertainity and missing data using the EM algorithm. CVPR, 1:707–714, 2004.
[9] J. Xiao and T. Kanade. Non-rigid shape and motion recovery: Degenerate deformations. CVPR, 1:668–675, 2004. Trajectory Basis Torresani et al.
[5] Xiao et al.
[9] Trajectory Basis Torresani et al.
[5] Xiao et al.
[9] Trajectory Basis Torresani et al.
[5] Xiao et al.
[9] Trajectory Basis Torresani et al.
[5] Xiao et al.
[9] Figure 6: Results on Dinosaur, Matrix, PIE face, and Cubes sequences. k was set to 12, 3, 2, and 2 respectively.
[10] M. Brand. Morphable 3D models from video. CVPR, 2:456, 2001.
[11] A. Del Bue, F.Smeraldi, and L. Agapito. Non-rigid structure from motion using ranklet-based tracking and non-linear optimization. IVC, pages 297–310, 2007.
[12] Amnon Shashua. Trilinear tensor: The fundamental construct of multiple-view geometry and its applications. AFPAC, 1997.
[13] Lihi Zelnik-Manor and Michal Irani. Temporal factorization vs. spatial factorization. ECCV, 2004.
[14] O. Arikan. Compression of motion capture databases. ACM Trans. on Graphics, 2006.
[15] A. Datta, Y. Sheikh, and T. Kanade. Linear motion estimation for systems of articulated planes. CVPR, 2008.