cvpr cvpr2013 cvpr2013-306 cvpr2013-306-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Lili Tao, Bogdan J. Matuszewski
Abstract: In this paper, a novel approach based on a non-linear manifold learning technique is proposed to recover 3D nonrigid structures from 2D image sequences captured by a single camera. Most ofthe existing approaches assume that 3D shapes can be accurately modelled in a linear subspace. These techniques perform well when the deformations are relatively small or simple, but fail when more complex deformations need to be recovered. The non-linear deformations are often observed in highly flexible objects for which the use of the linear model is impractical. A specific type of shape variations might be governed by only a small number of parameters, therefore can be wellrepresented in a low dimensional manifold. We learn a nonlinear shape prior using diffusion maps method. The key contribution in this paper is the introduction of the shape prior that constrain the reconstructed shapes to lie in the learned manifold. The proposed methodology has been validated quantitatively and qualitatively on 2D points sequences projected from the 3D motion capture data and real 2D video sequences. The comparisons oftheproposed man- ifold based method against several state-of-the-art techniques are shown on different types of deformable objects.
[1] I. Akhter, Y. Sheikh, and S. Khan. In defense of orthonormality constraints for nonrigid structure from motion. In CVPR, 2009. 1 2D InputMPPTAKSFMDM Figure 4. Selected 2D frames from the video sequence of a paper bending. Front and top views of the corresponding 3D reconstructed results using our method (DM), MP, PTA and KSFM.
[2] I. Akhter, Y. Sheikh, S. Khan, and T. Kanade. Trajectory space: A dual representation for nonrigid structure from motion. IEEE PAMI, 2011. 1, 2, 5, 6
[3] P. Arias, G. Randall, and G. Sapiro. Connecting the out-of sample and pre-image problems in kernel methods. In ICPR, 2007. 4
[4] A. Bartoli, V. Gay-Bellile, U. Castellani, J. Peyras, S. Olsen, and P. Sayd. Coarse-to-fine low rank structure from motion. In CVPR, 2008. 1
[5] C. Bregler, A. Hertzmann, and H. Biermann. Recovering non-rigid 3d shape from image streams. In CVPR, 2001. 1
[6] R. Coifman and S. Lafon. Diffusion maps. Appl. Comp. Harm. Anal., 21, 2006. 2, 4
[7] R. Coifman, S. Lafon, A. Lee, M. Maggioni, B. Nadler, F. Warner, and S. Zucker. Geometric diffusions as a tool for harmonic analysis and structure definition of data: Diffusion maps. National Academy of Sciences, 102(21), 2005. 4
[8] A. Del Bue. A factorization approach to structure from motion with shape priors. In CVPR, 2008. 1
[9] P. Etyngier, F. Segonne, and R. Keriven. Shape priors using manifold learning techniques. In ICCV, 2007. 2
[10] J. Fayad, L. Agapito, and A. Del Bue. Piecewise quadratic reconstruction of non-rigid surfaces from monocular sequences. In ECCV, 2010. 1 111555333644 above.
[11] P. Gotardo and A. Martinez. Computing smooth timetrajectories for camera and deformable shape in structure from motion with occlusion. IEEE PAMI, 33, 2011. 5
[12] P. Gotardo and A. Martinez. Kernel non-rigid structure from motion. In ICCV, 2011. 5, 6
[13] B. Matuszewski, W. Quan, L.-K. Shark, A. McLoughlin, C. Lightbody, H. Emsley, and C. Watkins. Hi4d–adsip 3d dynamic facial articulation database. Image and Vision Computing, 10:713–727, 2012. 5
[14] L. Mei, J. Liu, A. Hero, and S. Savarese. Robust object pose estimation via statistical manifold modeling. In ICCV, 2011. 2
[15] M. Paladini, A. Bue, J. Xavier, M. Stosic, M. Dodig, and L. Agapito. Factorization for non-rigid and articulated structure using metric projections. In CVPR, 2009. 1, 2, 5
[16] V. Rabaud and S. Belongie. Re-thinking non-rigid structure from motion. In CVPR, 2008. 1
[17] L. Tao, B. Matuszewski, and S. Mein. Non-rigid structure from motion with incremental shape prior. In ICIP, 2012. 3, 5
[18] J. Taylor, A. Jepson, and K. Kutulakos. Non-rigid structure from locally-rigid motion. In CVPR, 2010. 1
[19] C. Tomasi and T. Kanade. Shape and motion from image streams under orthography: A factorization approach. IJCV, 9(2), 1992. 1
[20] L. Torresani, A. Hertzmann, and C. Bregler. Nonrigid structure-from-motion: Estimating shape and motion with hierarchical priors. IEEE PAMI, 30(5), 2008. 1
[21] P. Tresadern and I. Reid. Articulated structure from motion by factorization. In CVPR, 2005. 1
[22] A. Varol, M. Salzmann, P. Fua, and R. Urtasun. A constrained latent variable model. In CVPR, 2012. 4, 5
[23] A. Varol, M. Salzmann, E. Tola, and P. Fua. Template-free monocular reconstruction of deformable surfaces. In ICCV, 2009. 1
[24] R. Wolz, P. Aljabar, J. Hajnal, J. Ltjnen, and D. Rueckert. Manifold learning combining imaging with non-imaging information. In ISBI, 2011. 2
[25] J. Xiao, J. Chai, and T. Kanade. A closed-form solution to non-rigid shape and motion recovery. In ECCV, 2004. 1, 2, 3
[26] J. Yan and M. Pollefeys. A factorization-based approach for articulated nonrigid shape, motion and kinematic chain recovery from video. IEEE PAMI, 2008. 1
[27] L. Yin, X. Wei, Y. Sun, J. Wang, and M. Rosato. A 3d face expression database for facial behavior research. In AFGR, 2006. 5 111555333755