Scale Space Graph Representation and Kernel Matching for Non Rigid and Textured 3D Shape Retrieval

In this paper we introduce a novel framework for 3D object retrieval that relies on tree-based shape representations (TreeSha) derived from the analysis of the scale-space of the Auto Diffusion Function (ADF) and on specialized graph kernels designed for their comparison. By coupling maxima of the Auto Diffusion Function with the related basins of attraction, we can link the information at different scales encoding spatial relationships in a graph description that is isometry invariant and can easily incorporate texture and additional geometrical information as node and edge features. Using custom graph kernels it is then possible to estimate shape dissimilarities adapted to different specific tasks and on different categories of models, making the procedure a powerful and flexible tool for shape recognition and retrieval. Experimental results demonstrate that the method can provide retrieval scores similar or better than state-of-the-art on textured and non textured shape retrieval benchmarks and give interesting insights on effectiveness of different shape descriptors and graph kernels.

[1]  Paul Suetens,et al.  Isometric deformation invariant 3D shape recognition , 2012, Pattern Recognit..

[2]  Paul Suetens,et al.  SHREC '11 Track: Shape Retrieval on Non-rigid 3D Watertight Meshes , 2011, 3DOR@Eurographics.

[3]  Hans-Peter Kriegel,et al.  Shortest-path kernels on graphs , 2005, Fifth IEEE International Conference on Data Mining (ICDM'05).

[4]  A. Ben Hamza,et al.  Reeb graph path dissimilarity for 3D object matching and retrieval , 2011, The Visual Computer.

[5]  Wan-Jui Lee,et al.  Bridging Structure and Feature Representations in Graph Matching , 2012, Int. J. Pattern Recognit. Artif. Intell..

[6]  Daniela Giorgi,et al.  PHOG: Photometric and geometric functions for textured shape retrieval , 2013, SGP '13.

[7]  King-Sun Fu,et al.  A distance measure between attributed relational graphs for pattern recognition , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[8]  Daniel Cohen-Or,et al.  Consistent mesh partitioning and skeletonisation using the shape diameter function , 2008, The Visual Computer.

[9]  Rasmus Larsen,et al.  Shape Analysis Using the Auto Diffusion Function , 2009 .

[10]  Ioannis Pratikakis,et al.  Retrieval of 3D Articulated Objects Using a Graph-based Representation , 2009, 3DOR@Eurographics.

[11]  Louis Chevallier,et al.  SHREC'13 Track: Retrieval on Textured 3D Models , 2013, 3DOR@Eurographics.

[12]  Kaspar Riesen,et al.  Approximate graph edit distance computation by means of bipartite graph matching , 2009, Image Vis. Comput..

[13]  Terry Caelli,et al.  An eigenspace projection clustering method for inexact graph matching , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  Wan-Jui Lee,et al.  An Inexact Graph Comparison Approach in Joint Eigenspace , 2008, SSPR/SPR.

[15]  Raif M. Rustamov,et al.  Laplace-Beltrami eigenfunctions for deformation invariant shape representation , 2007 .

[16]  Shin‐Tson Wu,et al.  Wiley Series in Pure and Applied Optics , 2012 .

[17]  Tamal K. Dey,et al.  Persistent Heat Signature for Pose‐oblivious Matching of Incomplete Models , 2010, Comput. Graph. Forum.

[18]  Pierre Alliez,et al.  Computational geometry algorithms library , 2008, SIGGRAPH '08.

[19]  J. Koenderink.  The structure of images , 2004, Biological Cybernetics.

[20]  Nils J. Nilsson,et al.  A Formal Basis for the Heuristic Determination of Minimum Cost Paths , 1968, IEEE Trans. Syst. Sci. Cybern..

[21]  David Cohen-Steiner,et al.  Restricted delaunay triangulations and normal cycle , 2003, SCG '03.

[22]  Guillaume Lavoué,et al.  Combination of bag-of-words descriptors for robust partial shape retrieval , 2012, The Visual Computer.

[23]  Luc Brun,et al.  Hierarchical Bag of Paths for Kernel Based Shape Classification , 2008, SSPR/SPR.

[24]  Herbert Edelsbrunner,et al.  Topological Persistence and Simplification , 2000, Proceedings 41st Annual Symposium on Foundations of Computer Science.

[25]  Taku Komura,et al.  Topology matching for fully automatic similarity estimation of 3D shapes , 2001, SIGGRAPH.

[26]  Alexander M. Bronstein,et al.  Diffusion framework for geometric and photometric data fusion in non-rigid shape analysis , 2011, ArXiv.

[27]  Ioannis Pratikakis,et al.  3D articulated object retrieval using a graph-based representation , 2010, The Visual Computer.

[28]  Ulrich Pinkall,et al.  Computing Discrete Minimal Surfaces and Their Conjugates , 1993, Exp. Math..

[29]  Andrea Giachetti,et al.  Retrieval and Classification on Textured 3D Models , 2014, 3DOR@Eurographics.

[30]  Leonidas J. Guibas,et al.  A concise and provably informative multi-scale signature based on heat diffusion , 2009 .

[31]  Harold W. Kuhn,et al.  The Hungarian method for the assignment problem , 1955, 50 Years of Integer Programming.

[32]  Niklas Peinecke,et al.  Laplace-Beltrami spectra as 'Shape-DNA' of surfaces and solids , 2006, Comput. Aided Des..

[33]  G. Finlayson,et al.  Coefficient color constancy , 1995 .

[34]  Thomas Gärtner,et al.  Cyclic pattern kernels for predictive graph mining , 2004, KDD.

[35]  Vincent Barra,et al.  3D shape retrieval using Kernels on Extended Reeb Graphs , 2013, Pattern Recognit..

[36]  Horst Bunke,et al.  Inexact graph matching for structural pattern recognition , 1983, Pattern Recognit. Lett..

[37]  Horst Bunke,et al.  On Graphs with Unique Node Labels , 2003, GbRPR.

[38]  Remco C. Veltkamp,et al.  A survey of content based 3D shape retrieval methods , 2004, Proceedings Shape Modeling Applications, 2004..

[39]  Alain Rakotomamonjy,et al.  Kernel on Bag of Paths For Measuring Similarity of Shapes , 2007, ESANN.

[40]  Andrea Giachetti,et al.  TreeSha: 3D Shape Retrieval with a Tree Graph Representation based on the Autodiffusion Function Topology , 2014, 3DOR@Eurographics.

[41]  Longin Jan Latecki,et al.  Path Similarity Skeleton Graph Matching , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[42]  Sylvie Philipp-Foliguet,et al.  Indexing of 3d models based on graph of surfacic regions , 2010, 3DOR '10.

[43]  Hamid Laga,et al.  Geometry and context for semantic correspondences and functionality recognition in man-made 3D shapes , 2013, TOGS.

[44]  Leonidas J. Guibas,et al.  Persistence-based segmentation of deformable shapes , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops.

[45]  Edsger W. Dijkstra,et al.  A note on two problems in connexion with graphs , 1959, Numerische Mathematik.

[46]  Andrea Giachetti,et al.  Radial Symmetry Detection and Shape Characterization with the Multiscale Area Projection Transform , 2012, Comput. Graph. Forum.

[47]  Paul Suetens,et al.  A comparison of methods for non-rigid 3D shape retrieval , 2013, Pattern Recognit..

[48]  Kaspar Riesen,et al.  Fast Suboptimal Algorithms for the Computation of Graph Edit Distance , 2006, SSPR/SPR.

[49]  Tony Lindeberg,et al.  Scale-Space Theory in Computer Vision , 1993, Lecture Notes in Computer Science.

[50]  Sven J. Dickinson,et al.  Skeleton based shape matching and retrieval , 2003, 2003 Shape Modeling International..

[51]  Tony Tung,et al.  The Augmented Multiresolution Reeb Graph Approach for Content-based Retrieval of 3d Shapes , 2005, Int. J. Shape Model..

[52]  Leonidas J. Guibas,et al.  Persistence-Based Clustering in Riemannian Manifolds , 2013, JACM.

[53]  Shinji Umeyama,et al.  An Eigendecomposition Approach to Weighted Graph Matching Problems , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[54]  A. Ben Hamza,et al.  Symmetry discovery and retrieval of nonrigid 3D shapes using geodesic skeleton paths , 2013, Multimedia Tools and Applications.