ML Anthology

Geodesic Shape Retrieval via Optimal Mass Transport

Julien Rabin, Gabriel Peyré, Laurent D. Cohen
ECCV 2010 pp. 771-784
doi:10.1007/978-3-642-15555-0_56 /eccv/2010/rabin2010eccv-geodesic/

Abstract

This paper presents a new method for 2-D and 3-D shape retrieval based on geodesic signatures. These signatures are high dimensional statistical distributions computed by extracting several features from the set of geodesic distance maps to each point. The resulting high dimensional distributions are matched to perform retrieval using a fast approximate Wasserstein metric. This allows to propose a unifying framework for the compact description of planar shapes and 3-D surfaces.

PDF ECCV Semantic Scholar

Cite

Text

Rabin et al. "Geodesic Shape Retrieval via Optimal Mass Transport." European Conference on Computer Vision, 2010. doi:10.1007/978-3-642-15555-0_56

Markdown

[Rabin et al. "Geodesic Shape Retrieval via Optimal Mass Transport." European Conference on Computer Vision, 2010.](https://mlanthology.org/eccv/2010/rabin2010eccv-geodesic/) doi:10.1007/978-3-642-15555-0_56

BibTeX

@inproceedings{rabin2010eccv-geodesic,
  title     = {{Geodesic Shape Retrieval via Optimal Mass Transport}},
  author    = {Rabin, Julien and Peyré, Gabriel and Cohen, Laurent D.},
  booktitle = {European Conference on Computer Vision},
  year      = {2010},
  pages     = {771-784},
  doi       = {10.1007/978-3-642-15555-0_56},
  url       = {https://mlanthology.org/eccv/2010/rabin2010eccv-geodesic/}
}