Local Geometry Inclusive Global Shape Representation

Abstract

A local geometry-inclusive global representation of 3D shapes based on the shortest quasi-geodesic paths between all possible pairs of points on the shape manifold is proposed. In the proposed representation, the normal curvature values along the quasi-geodesic paths are shown preserve the local shape geometry. The eigenspectrum of the proposed global representation is exploited to characterize the shape self-symmetry. The commutative property of the shape descriptor spectrum is exploited to address region-based correspondence determination between isometric 3D shapes without requiring prior correspondence maps and to extract stable regions between 3D shapes that differ from one another by a high degree of isometry transformation. Eigenspectrum-based characterization metrics are proposed to quantify the performance of the proposed 3D shape descriptor for correspondence determination and self-symmetry detection in comparison to its relevant state-of-the-art counterparts. The proposed shape descriptor spectrum and the optimization criterion based on spectral commutativity are observed to yield competitive performance compared to relevant state-of-the-art methods.

Cite

Text

Das and Bhandarkar. "Local Geometry Inclusive Global Shape Representation." IEEE/CVF International Conference on Computer Vision Workshops, 2017. doi:10.1109/ICCVW.2017.151

Markdown

[Das and Bhandarkar. "Local Geometry Inclusive Global Shape Representation." IEEE/CVF International Conference on Computer Vision Workshops, 2017.](https://mlanthology.org/iccvw/2017/das2017iccvw-local/) doi:10.1109/ICCVW.2017.151

BibTeX

@inproceedings{das2017iccvw-local,
  title     = {{Local Geometry Inclusive Global Shape Representation}},
  author    = {Das, Somenath and Bhandarkar, Suchendra M.},
  booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
  year      = {2017},
  pages     = {1256-1265},
  doi       = {10.1109/ICCVW.2017.151},
  url       = {https://mlanthology.org/iccvw/2017/das2017iccvw-local/}
}