3D Shape Similarity Using Vectors of Locally Aggregated Tensors

Hedi Tabia 1 David Picard 2 Hamid Laga 3 Philippe-Henri Gosselin 1, 4
2 MIDI
ETIS - Equipes Traitement de l'Information et Systèmes
4 TEXMEX - Multimedia content-based indexing
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : In this paper, we present an efficient 3D object retrieval method invariant to scale, orientation and pose. Our approach is based on the dense extraction of discriminative local descriptors extracted from 2D views. We aggregate the descriptors into a single vector signature using tensor products. The similarity between 3D models can then be efficiently computed with a simple dot product. Experiments on the SHREC12 commonly-used benchmark demonstrate that our approach obtains superior performance in searching for generic shapes.
Document type :
Conference papers
IEEE International Conference on Image Processing, Sep 2013, Melbourne, Australia. pp.2694-2698, 2013
Liste complète des métadonnées

Cited literature [16 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00832182
Contributor : Philippe-Henri Gosselin <>
Submitted on : Monday, June 10, 2013 - 3:03:14 PM
Last modification on : Wednesday, May 16, 2018 - 11:23:05 AM
Document(s) archivé(s) le : Tuesday, April 4, 2017 - 6:57:31 PM

File

tabia13icip.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00832182, version 1

Citation

Hedi Tabia, David Picard, Hamid Laga, Philippe-Henri Gosselin. 3D Shape Similarity Using Vectors of Locally Aggregated Tensors. IEEE International Conference on Image Processing, Sep 2013, Melbourne, Australia. pp.2694-2698, 2013. 〈hal-00832182〉

Share

Metrics

Record views

626

Files downloads

1146