nips nips2012 nips2012-137 nips2012-137-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Soumya Ghosh, Matthew Loper, Erik B. Sudderth, Michael J. Black
Abstract: We develop a method for discovering the parts of an articulated object from aligned meshes of the object in various three-dimensional poses. We adapt the distance dependent Chinese restaurant process (ddCRP) to allow nonparametric discovery of a potentially unbounded number of parts, while simultaneously guaranteeing a spatially connected segmentation. To allow analysis of datasets in which object instances have varying 3D shapes, we model part variability across poses via affine transformations. By placing a matrix normal-inverse-Wishart prior on these affine transformations, we develop a ddCRP Gibbs sampler which tractably marginalizes over transformation uncertainty. Analyzing a dataset of humans captured in dozens of poses, we infer parts which provide quantitatively better deformation predictions than conventional clustering methods.
[1] M. Attene, S. Katz, M. Mortara, G. Patane, M. Spagnuolo, and A. Tal. Mesh segmentation — A comparative study. In SMI, 2006.
[2] Xiaobai Chen, Aleksey Golovinskiy, and Thomas Funkhouser. A benchmark for 3D mesh segmentation. ACM Transactions on Graphics (Proc. SIGGRAPH), 28(3):73:1–73:12, 2009.
[3] Evangelos Kalogerakis, Aaron Hertzmann, and Karan Singh. Learning 3D Mesh Segmentation and Labeling. ACM Transactions on Graphics, 29(4):102:1–102:12, July 2010.
[4] David M. Blei and Peter I. Frazier. Distance dependent Chinese restaurant processes. J. Mach. Learn. Res., 12:2461–2488, November 2011.
[5] S. Ghosh, A. B. Ungureanu, E. B. Sudderth, and D. Blei. Spatial distance dependent Chinese restaurant processes for image segmentation. In NIPS, pages 1476–1484, 2011.
[6] D. Hirshberg, M. Loper, E. Rachlin, and M.J. Black. Coregistration: Simultaneous alignment and modeling of articulated 3D shape. In ECCV, pages 242–255, 2012.
[7] R. M. Neal. Markov chain sampling methods for Dirichlet process mixture models. JCGS, 9(2):249–265, 2000.
[8] D. Anguelov, D. Koller, H. Pang, P. Srinivasan, and S. Thrun. Recovering articulated object models from 3d range data. In UAI, pages 18–26, 2004.
[9] J. Franco and E. Boyer. Learning temporally consistent rigidities. In IEEE CVPR, pages 1241–1248, 2011.
[10] E. B. Fox. Bayesian Nonparametric Learning of Complex Dynamical Phenomena. PhD thesis, Massachusetts Institute of Technology, Cambridge, MA, 2009.
[11] A. K. Gupta and D. K. Nagar. Matrix Variate Distributions. Chapman & Hall/CRC, October 2000.
[12] Tong-Yee Lee, Yu-Shuen Wang, and Tai-Guang Chen. Segmenting a deforming mesh into near-rigid components. The Visual Computer, 22(9):729–739, September 2006.
[13] Guy Rosman, Michael M. Bronstein, Alexander M. Bronstein, Alon Wolf, and Ron Kimmel. Groupvalued regularization framework for motion segmentation of dynamic non-rigid shapes. In SSVM’11, pages 725–736, 2012.
[14] Stefanie Wuhrer and Alan Brunton. Segmenting animated objects into near-rigid components. The Visual Computer, 26:147–155, 2010.
[15] N. Hasler, C. Stoll, M. Sunkel, B. Rosenhahn, and H.-P. Seidel. A statistical model of human pose and body shape. In Computer Graphics Forum (Proc. Eurographics 2009), volume 2, pages 337–346, March 2009.
[16] R. N. Shepard. Multidimensional scaling, tree-fitting, and clustering. Science, 210:390–398, October 1980.
[17] Wen-Yen Chen, Yangqiu Song, Hongjie Bai, Chih-Jen Lin, and Edward Y. Chang. Parallel spectral clustering in distributed systems. IEEE PAMI, 33(3):568–586, 2011.
[18] Rong Liu and Hao Zhang. Segmentation of 3D meshes through spectral clustering. In Pacific Conference on Computer Graphics and Applications, pages 298–305, 2004.
[19] Edilson de Aguiar, Christian Theobalt, Sebastian Thrun, and Hans-Peter Seidel. Automatic conversion of mesh animations into skeleton-based animations. Computer Graphics Forum, 27(2):389–397, 2008.
[20] Alexander Bronstein, Michael Bronstein, and Ron Kimmel. Calculus of nonrigid surfaces for geometry and texture manipulation. IEEE Tran. on Viz. and Computer Graphics, 13:902–913, 2007.
[21] Oren Freifeld and Michael J. Black. Lie bodies: A manifold representation of 3D human shape. In European Conf. on Computer Vision (ECCV), Part I, LNCS 7572, pages 1–14. Springer-Verlag, October 2012. 9