Geodesic Shape Retrieval via Optimal Mass Transport - Archive ouverte HAL Access content directly
Conference Papers Year : 2010

Geodesic Shape Retrieval via Optimal Mass Transport


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.
Fichier principal
Vignette du fichier
ShapesECCV10.pdf (1.22 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-00498607 , version 1 (07-07-2010)



Julien Rabin, Gabriel Peyré, Laurent D. Cohen. Geodesic Shape Retrieval via Optimal Mass Transport. 11th European Conference on Computer Vision, Sep 2010, Heraklion, Crete, Greece. pp.771-784, ⟨10.1007/978-3-642-15555-0_56⟩. ⟨hal-00498607⟩
320 View
1292 Download



Gmail Facebook X LinkedIn More