Hierarchical Framework for Shape Correspondence

Hierarchical Framework for Shape Correspondence

Year:    2013

Numerical Mathematics: Theory, Methods and Applications, Vol. 6 (2013), Iss. 1 : pp. 245–261

Abstract

Detecting similarity between non-rigid shapes is one of the fundamental problems in computer vision. In order to measure the similarity the shapes must first be aligned. As opposite to rigid alignment that can be parameterized using a small number of unknowns representing rotations, reflections and translations, non-rigid alignment is not easily parameterized. Majority of the methods addressing this problem boil down to a minimization of a certain distortion measure. The complexity of a matching process is exponential by nature, but it can be heuristically reduced to a quadratic or even linear for shapes which are smooth two-manifolds. Here we model the shapes using both local and global structures, employ these to construct a quadratic dissimilarity measure, and provide a hierarchical framework for minimizing it to obtain sparse set of corresponding points. These correspondences may serve as an initialization for dense linear correspondence search.

You do not have full access to this article.

Already a Subscriber? Sign in as an individual or via your institution

Journal Article Details

Publisher Name:    Global Science Press

Language:    English

DOI:    https://doi.org/10.4208/nmtma.2013.mssvm13

Numerical Mathematics: Theory, Methods and Applications, Vol. 6 (2013), Iss. 1 : pp. 245–261

Published online:    2013-01

AMS Subject Headings:   

Copyright:    COPYRIGHT: © Global Science Press

Pages:    17

Keywords:    Shape correspondence Laplace-Beltrami diffusion geometry local signatures

  1. Computer Vision – ECCV 2020

    Cyclic Functional Mapping: Self-supervised Correspondence Between Non-isometric Deformable Shapes

    Ginzburg, Dvir | Raviv, Dan

    2020

    https://doi.org/10.1007/978-3-030-58558-7_3 [Citations: 20]
  2. Computer Vision – ECCV 2018

    3D-CODED: 3D Correspondences by Deep Deformation

    Groueix, Thibault | Fisher, Matthew | Kim, Vladimir G. | Russell, Bryan C. | Aubry, Mathieu

    2018

    https://doi.org/10.1007/978-3-030-01216-8_15 [Citations: 146]
  3. Matching Misaligned Two-Resolution Metrology Data

    Wang, Yaping | Moreno-Centeno, Erick | Ding, Yu

    IEEE Transactions on Automation Science and Engineering, Vol. 14 (2017), Iss. 1 P.222

    https://doi.org/10.1109/TASE.2016.2587219 [Citations: 9]
  4. Reliable Isometric Point Correspondence from Depth

    Kupcu, Emel | Yemez, Yucel

    2017 IEEE International Conference on Computer Vision Workshops (ICCVW), (2017), P.1266

    https://doi.org/10.1109/ICCVW.2017.152 [Citations: 1]
  5. 3-D Shape Matching and Non-Rigid Correspondence for Hippocampi Based on Markov Random Fields

    Xiao, Pengdong | Barnes, Nick | Caetano, Tiberio

    IEEE Transactions on Image Processing, Vol. 27 (2018), Iss. 3 P.1271

    https://doi.org/10.1109/TIP.2017.2779277 [Citations: 4]
  6. Robust Nonrigid Registration by Convex Optimization

    Chen, Qifeng | Koltun, Vladlen

    2015 IEEE International Conference on Computer Vision (ICCV), (2015), P.2039

    https://doi.org/10.1109/ICCV.2015.236 [Citations: 73]
  7. Unsupervised Learning of Dense Shape Correspondence

    Halimi, Oshri | Litany, Or | Rodola, Emanuele Rodola | Bronstein, Alex M. | Kimmel, Ron

    2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), (2019), P.4365

    https://doi.org/10.1109/CVPR.2019.00450 [Citations: 97]