Abstract
This paper presents a novel approach to represent spatio-temporal visual information. We introduce a surface-based shape model whose structure is invariant to surface variations over time to describe 3D dynamic surfaces (e.g., obtained from multiview video capture). The descriptor is defined as a graph lying on object surfaces and anchored to invariant local features (e.g., extremal points). Geodesic-consistency-based priors are used as cues within a probabilistic framework to maintain the graph invariant, even though the surfaces undergo non-rigid deformations. Our contribution brings to 3D geometric data a temporally invariant structure that relies only on intrinsic surface properties, and is independent of surface parameterization (i.e., surface mesh connectivity). The proposed descriptor can therefore be used for efficient dynamic surface encoding, through transformation into 2D (geometry) images, as its structure can provide an invariant representation for 3D mesh models. Various experiments on challenging publicly available datasets are performed to assess invariant property and performance of the descriptor.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Forsyth, D.A., Mundy, J.L., Zisserman, A., Coelho, C., Heller, A., Rothwell, C.: Invariant descriptors for 3d object recognition and pose. IEEE PAMI 13 (1991)
Mundy, J., Zisserman, A.: Geometric invariance in computer vision. MIT Press (1992)
Rothganger, F., Lazebnik, S., Schmid, C., Ponce, J.: 3d object modeling and recognition using local affine-invariant image descriptors and multi-view spatial constraints. IJCV 66, 231–259 (2006)
Matsuyama, T., Wu, X., Takai, T., Nobuhara, S.: Real-time 3d shape reconstruction, dynamic 3d mesh deformation, and high fidelity visualization for 3d video. CVIU 96, 393–434 (2004)
Allard, J., Ménier, C., Raffin, B., Boyer, E., Faure, F.: Grimage: Markerless 3d interactions. ACM SIGGRAPH - Emerging Technologies (2007)
Starck, J., Hilton, A.: Surface capture for performance-based animation. IEEE CGA (2007)
de Aguiar, E., Stoll, C., Theobalt, C., Ahmed, N., Seidel, H.P., Thrun, S.: Performance capture from sparse multi-view video. ACM Trans. Graphics 27 (2008)
Starck, J., Hilton, A.: Spherical matching for temporal correspondence of non-rigid surfaces. In: IEEE ICCV (2005)
Bronstein, A.M., Bronstein, M.M., Kimmel, R.: Calculus of non-rigid surfaces for geometry and texture manipulation. IEEE Trans. VCG, 902–913 (2007)
Vlasic, D., Baran, I., Matusik, W., Popovic, J.: Articulated mesh animation from multi-view silhouettes. ACM Trans. Graphics 27 (2008)
Cagniart, C., Boyer, E., Ilic, S.: Probabilistic Deformable Surface Tracking from Multiple Videos. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 326–339. Springer, Heidelberg (2010)
Gu, X., Gortler, S., Hoppe, H.: Geometry images. ACM SIGGRAPH (2002)
Seitz, S., Curless, B., Diebel, J., Scharstein, D., Szeliski, R.: A comparison and evaluation of multi-view stereo reconstruction algorithms. In: IEEE CVPR (2006)
Alliez, P., Gotsman, C.: Recent advances in compression of 3d meshes. In: Advances in Multiresolution for Geometric Modelling. Springer (2005)
Alexa, M., Müllen, W.: Representing animations by principal components. Computer Graphics Forum 19 (2000)
Briceno, H., Sandler, P., McMillian, L., Gortler, S., Hoppe, H.: Geometry videos: A new representation for 3d animations. In: Eurographics/SIGGRAPH Symp. Computer Animation, pp. 136–146 (2003)
Karni, Z., Gotsman, C.: Compression of soft-body animation sequence. Computers & Graphics 28, 25–34 (2004)
Mamou, K., Zaharia, T., Preteux, F., Stefanoski, N., Ostermann, J.: Frame-based compression of animated meshes in mpeg-4. In: IEEE ICME (2008)
Blum, H.: A transformation for extracting new descriptors of shape. Models for the Perception of Speech and Visual Form (1967)
Cornea, N., Silver, D., Yuan, X., Balasubramanian, R.: Computing hierarchical curve skeletons of 3d objects. The Visual Computer 21, 945–955 (2005)
Hilaga, M., Shinagawa, Y., Kohmura, T., Kunii, T.L.: Topology matching for fully automatic similarity estimation of 3d shapes. ACM SIGGRAPH, 203–212 (2001)
Carranza, J., Theobalt, C., Magnor, M., Seidel, H.-P.: Free-viewpoint video of human actors. ACM Trans. Graphics 22, 569–577 (2003)
Palagyi, K., Kuba, A.: A parallel 3d 12-subiteration thinning algorithm. Graph. Models and Image Proc. 61, 199–221 (1999)
Baran, I., Popovic, J.: Automatic rigging and animation of 3d characters. ACM Trans. Graphics 26, 27 (2007)
Tung, T., Matsuyama, T.: Topology dictionary for 3d video understanding. IEEE Trans. PAMI 34, 1645–1657 (2012)
Habe, H., Katsura, Y., Matsuyama, T.: Skin-off: Representation and compression scheme for 3d video. In: Picture Coding Symposium (2004)
Saboret, L., Alliez, P., Lévy, B.: Planar parameterization of triangulated surface meshes. In: CGAL Reference Manual. CGAL Editorial Board, 4.0 edition (2012)
Mortara, M., Patanè, G.: Affine-invariant skeleton of 3d shapes. Shape Modeling International (2002)
Morse, M.: The calculus of variations in the large. American Mathematical Society, Colloquium Publication 18, New York (1934)
Pascucci, V., Scorzelli, G., Bremer, P.T., Mascarenhas, A.: Robust on-line computation of reeb graphs: Simplicity and speed. ACM Trans. Graphics 26 (2007)
Edelsbrunner, H., Harer, J., Mascarenhas, A., Pascucci, V.: Time-varying reeb graphs for continuous space-time data. In: Symp. Computational Geometry (2004)
Klein, T., Ertl, T.: Scale-space tracking of critical points in 3d vector fields. In: Proc. Topology-Based Methods in Visualization (2005)
Tung, T., Schmitt, F.: The augmented multiresolution reeb graph approach for content-based retrieval of 3d shapes (code on webpage). Int’l J. Shape Modeling 11, 91–120 (2005)
Taubin, G., Rossignac, J.: Geometric compression through topological surgery. ACM Trans. Graphics 17, 84–115 (1998)
Erickson, J., Har-Peled, S.: Optimally cutting a surface into a disk. Discrete & Computational Geometry 31, 37–59 (2004)
Floater, M.: Parametrization and smooth approximation of surface triangulations. CADG 14, 231–250 (1997)
Mémoli, F., Sapiro, G.: A theoretical and computational framework for isometry invariant recognition of point cloud data. Found. Comput. Math. 5, 313–347 (2005)
Cignoni, P., Rocchini, C., Scopigno, R.: Metro: measuring error on simplified surfaces. Computer Graphics Forum 17, 167–174 (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tung, T., Matsuyama, T. (2013). Invariant Surface-Based Shape Descriptor for Dynamic Surface Encoding. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds) Computer Vision – ACCV 2012. ACCV 2012. Lecture Notes in Computer Science, vol 7724. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-37331-2_37
Download citation
DOI: https://doi.org/10.1007/978-3-642-37331-2_37
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-37330-5
Online ISBN: 978-3-642-37331-2
eBook Packages: Computer ScienceComputer Science (R0)