Many algorithms for the computation of correspondences between deformable shapes rely on some variant of nearest neighbor matching in a descriptor space. Such are, for example, various point-wise correspondence recovery algorithms used as a post-processing stage in the functional correspondence framework. Such frequently used techniques implicitly make restrictive assumptions (e.g., near-isometry) on the considered shapes and in practice suffer from lack of accuracy and result in poor surjectivity. We propose an alternative recovery technique capable of guaranteeing a bijective correspondence and producing significantly higher accuracy and smoothness. Unlike other methods our approach does not depend on the assumption that the analyzed shapes are isometric. We derive the proposed method from the statistical framework of kernel density estimation and demonstrate its performance on several challenging deformable 3D shape matching datasets.

Product manifold filter: Non-rigid shape correspondence via kernel density estimation in the product space / Vestner, Matthias; Litman, Roee; Rodolà, Emanuele; Bronstein, Alex; Cremers, Daniel. - 2017- January(2017), pp. 6681-6690. ((Intervento presentato al convegno 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 tenutosi a Honolulu; USA [10.1109/CVPR.2017.707].

Product manifold filter: Non-rigid shape correspondence via kernel density estimation in the product space

Rodolà, Emanuele;
2017

Abstract

Many algorithms for the computation of correspondences between deformable shapes rely on some variant of nearest neighbor matching in a descriptor space. Such are, for example, various point-wise correspondence recovery algorithms used as a post-processing stage in the functional correspondence framework. Such frequently used techniques implicitly make restrictive assumptions (e.g., near-isometry) on the considered shapes and in practice suffer from lack of accuracy and result in poor surjectivity. We propose an alternative recovery technique capable of guaranteeing a bijective correspondence and producing significantly higher accuracy and smoothness. Unlike other methods our approach does not depend on the assumption that the analyzed shapes are isometric. We derive the proposed method from the statistical framework of kernel density estimation and demonstrate its performance on several challenging deformable 3D shape matching datasets.
9781538604571
File allegati a questo prodotto
File Dimensione Formato  
Rodola_Product_2017.pdf

solo gestori archivio

Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 910.03 kB
Formato Adobe PDF
910.03 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11573/1229069
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 75
  • ???jsp.display-item.citation.isi??? 32
social impact