Topologically-robust 3D shape matching based on diffusion geometry and seed growing

3D Shape matching is an important problem in computer vision. One of the major difficulties in finding dense correspondences between 3D shapes is related to the topological discrepancies that often arise due to complex kinematic motions. In this paper we propose a shape matching method that is robust to such changes in topology. The algorithm starts from a sparse set of seed matches and outputs dense matching. We propose to use a shape descriptor based on properties of the heat-kernel and which provides an intrinsic scale-space representation. This descriptor incorporates (i) heat-flow from already matched points and (ii) self diffusion. At small scales the descriptor behaves locally and hence it is robust to global changes in topology. Therefore, it can be used to build a vertex-to-vertex matching score conditioned by an initial correspondence set. This score is then used to iteratively add new correspondences based on a novel seed-growing method that iteratively propagates the seed correspondences to nearby vertices. The matching is farther densified via an EM-like method that explores the congruency between the two shape embeddings. Our method is compared with two recently proposed algorithms and we show that we can deal with substantial topological differences between the two shapes.

[1]  Michal Perdoch,et al.  Efficient sequential correspondence selection by cosegmentation , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Martin Reuter,et al.  Hierarchical Shape Segmentation and Registration via Topological Features of Laplace-Beltrami Eigenfunctions , 2010, International Journal of Computer Vision.

[3]  Thomas Malzbender,et al.  A Survey of Methods for Volumetric Scene Reconstruction from Photographs , 2001, VG.

[4]  Radu Horaud,et al.  Learning Shape Segmentation Using Constrained Spectral Clustering and Probabilistic Label Transfer , 2010, ECCV.

[5]  Leonidas J. Guibas,et al.  SHREC 2010: robust correspondence benchmark , 2010 .

[6]  Robert C. Bolles,et al.  Locating Partially Visible Objects: The Local Feature Focus Method , 1980, AAAI.

[7]  Radu Horaud,et al.  Articulated shape matching using Laplacian eigenfunctions and unsupervised point registration , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  Takashi Matsuyama,et al.  Dynamic surface matching by geodesic mapping for 3D animation transfer , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[9]  H. Seidel,et al.  Isometric registration of ambiguous and partial data , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  Radu Horaud,et al.  Rigid and Articulated Point Registration with Expectation Conditional Maximization , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Leonidas J. Guibas,et al.  Non-Rigid Registration Under Isometric Deformations , 2008 .

[12]  Adrian Hilton,et al.  Correspondence labelling for wide-timeframe free-form surface matching , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[13]  U. Feige,et al.  Spectral Graph Theory , 2015 .

[14]  Günther Greiner,et al.  Reconstructing Animated Meshes from Time‐Varying Point Clouds , 2008, Comput. Graph. Forum.

[15]  Alexander M. Bronstein,et al.  Topology-Invariant Similarity of Nonrigid Shapes , 2009, International Journal of Computer Vision.

[16]  Leonidas J. Guibas,et al.  One Point Isometric Matching with the Heat Kernel , 2010, Comput. Graph. Forum.

[17]  Nikos Paragios,et al.  Dense non-rigid surface registration using high-order graph matching , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[18]  Radu Horaud,et al.  Shape matching based on diffusion embedding and on mutual isometric consistency , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops.

[19]  Radu Horaud,et al.  Temporal Surface Tracking Using Mesh Evolution , 2008, ECCV.

[20]  Hans-Peter Seidel,et al.  Isometric registration of ambiguous and partial data , 2009, CVPR.

[21]  Yücel Yemez,et al.  3D Shape correspondence by isometry-driven greedy optimization , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[22]  Slobodan Ilic,et al.  Probabilistic Deformable Surface Tracking from Multiple Videos , 2010, ECCV.

[23]  Wolfgang Heidrich,et al.  Globally Consistent Space‐Time Reconstruction , 2010, Comput. Graph. Forum.

[24]  Edmond Boyer,et al.  Efficient Polyhedral Modeling from Silhouettes , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[25]  Wojciech Matusik,et al.  Articulated mesh animation from multi-view silhouettes , 2008, ACM Trans. Graph..

[26]  R. Horaud,et al.  Surface feature detection and description with applications to mesh matching , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[27]  Adrian Hilton,et al.  Surface Capture for Performance-Based Animation , 2007, IEEE Computer Graphics and Applications.

[28]  Christian Rössl,et al.  Dense correspondence finding for parametrization-free animation reconstruction from video , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[29]  Richard Szeliski,et al.  A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[30]  R. Bolles,et al.  Recognizing and Locating Partially Visible Objects: The Local-Feature-Focus Method , 1982 .

[31]  Martial Hebert,et al.  A spectral technique for correspondence problems using pairwise constraints , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.