Automatic Registration for Articulated Shapes

We present an unsupervised algorithm for aligning a pair of shapes in the presence of significant articulated motion and missing data, while assuming no knowledge of a template, user‐placed markers, segmentation, or the skeletal structure of the shape. We explicitly sample the motion, which gives a priori the set of possible rigid transformations between parts of the shapes. This transforms the problem into a discrete labeling problem, where the goal is to find an optimal assignment of transformations for aligning the shapes. We then apply graph cuts to optimize a novel cost function, which encodes a preference for a consistent motion assignment from both source to target and target to source. We demonstrate the robustness of our method by aligning several synthetic and real‐world datasets.

[1]  Wayne E. Carlson,et al.  Shape transformation for polyhedral objects , 1992, SIGGRAPH.

[2]  Vladimir Kolmogorov,et al.  Convergent Tree-Reweighted Message Passing for Energy Minimization , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Ryutarou Ohbuchi,et al.  Blending shapes by using subdivision surfaces , 2001, Comput. Graph..

[4]  Leonidas J. Guibas,et al.  Dynamic geometry registration , 2007, Symposium on Geometry Processing.

[5]  Peter Schröder,et al.  Consistent mesh parameterizations , 2001, SIGGRAPH.

[6]  Fernando Casas,et al.  On the convergence and optimization of the Baker–Campbell–Hausdorff formula , 2004 .

[7]  Leonidas J. Guibas,et al.  Eurographics Symposium on Geometry Processing (2007) Reconstruction of Deforming Geometry from Time-varying Point Clouds , 2022 .

[8]  Zoran Popovic,et al.  The space of human body shapes: reconstruction and parameterization from range scans , 2003, ACM Trans. Graph..

[9]  Jovan Popović,et al.  Deformation transfer for triangle meshes , 2004, SIGGRAPH 2004.

[10]  Gérard G. Medioni,et al.  Object modeling by registration of multiple range images , 1991, Proceedings. 1991 IEEE International Conference on Robotics and Automation.

[11]  Leonidas J. Guibas,et al.  Partial and approximate symmetry detection for 3D geometry , 2006, ACM Trans. Graph..

[12]  Alla Sheffer,et al.  Cross-parameterization and compatible remeshing of 3D models , 2004, ACM Trans. Graph..

[13]  Jovan Popovic,et al.  Deformation transfer for triangle meshes , 2004, ACM Trans. Graph..

[14]  Paul J. Besl,et al.  A Method for Registration of 3-D Shapes , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Jarek Rossignac,et al.  Solid-interpolating deformations: Construction and animation of PIPs , 1991, Comput. Graph..

[16]  Anand Rangarajan,et al.  A new point matching algorithm for non-rigid registration , 2003, Comput. Vis. Image Underst..

[17]  Hiromasa Suzuki,et al.  3D geometric metamorphosis based on harmonic map , 1997, Proceedings The Fifth Pacific Conference on Computer Graphics and Applications.

[18]  Dinesh Manocha,et al.  Feature-based surface decomposition for correspondence and morphing between polyhedra , 1998, Proceedings Computer Animation '98 (Cat. No.98EX169).

[19]  Luc Van Gool,et al.  Fast 3D Scanning with Automatic Motion Compensation , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[20]  Szymon Rusinkiewicz,et al.  Global non-rigid alignment of 3-D scans , 2007, ACM Trans. Graph..

[21]  Craig Gotsman,et al.  Articulated Object Reconstruction and Markerless Motion Capture from Depth Video , 2008, Comput. Graph. Forum.

[22]  Szymon Rusinkiewicz,et al.  Estimating curvatures and their derivatives on triangle meshes , 2004, Proceedings. 2nd International Symposium on 3D Data Processing, Visualization and Transmission, 2004. 3DPVT 2004..

[23]  Christian R. Shelton,et al.  Morphable Surface Models , 2000, International Journal of Computer Vision.

[24]  Olga Veksler,et al.  Fast Approximate Energy Minimization via Graph Cuts , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[25]  Hiromasa Suzuki,et al.  Metamorphosis of Arbitrary Triangular Meshes , 2000, IEEE Computer Graphics and Applications.

[26]  Vladislav Kraevoy,et al.  Cross-parameterization and compatible remeshing of 3D models , 2004, SIGGRAPH 2004.

[27]  Szymon Rusinkiewicz,et al.  Global non-rigid alignment of 3-D scans , 2007, SIGGRAPH 2007.

[28]  Andrew Blake,et al.  LogCut - Efficient Graph Cut Optimization for Markov Random Fields , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[29]  Michael Garland,et al.  Surface simplification using quadric error metrics , 1997, SIGGRAPH.

[30]  Andrew E. Johnson,et al.  Spin-Images: A Representation for 3-D Surface Matching , 1997 .

[31]  Olga Veksler,et al.  Fast approximate energy minimization via graph cuts , 2001, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[32]  Ryutarou Ohbuchi,et al.  Explicit control of topological transitions in morphing shapes of 3D meshes , 2001, Proceedings Ninth Pacific Conference on Computer Graphics and Applications. Pacific Graphics 2001.

[33]  Sebastian Thrun,et al.  The Correlated Correspondence Algorithm for Unsupervised Registration of Nonrigid Surfaces , 2004, NIPS.

[34]  Yasushi Yagi,et al.  Deformable Registration of Textured Range Images by Using Texture and Shape Features , 2007, Sixth International Conference on 3-D Digital Imaging and Modeling (3DIM 2007).

[35]  Sami Romdhani,et al.  Optimal Step Nonrigid ICP Algorithms for Surface Registration , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[36]  David P. Dobkin,et al.  MAPS: multiresolution adaptive parameterization of surfaces , 1998, SIGGRAPH.

[37]  S. Rusinkiewicz.  Estimating curvatures and their derivatives on triangle meshes , 2004 .

[38]  Peter Meer,et al.  Simultaneous multiple 3D motion estimation via mode finding on Lie groups , 2005, Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1.

[39]  Leonidas J. Guibas,et al.  Example-Based 3D Scan Completion , 2005 .

[40]  David P. Dobkin,et al.  Multiresolution mesh morphing , 1999, SIGGRAPH.