3D shape similarity using vectors of locally aggregated tensors

H. Tabia; D. Picard; H. Laga; P-H Gosselin

doi:10.1109/ICIP.2013.6738555

Back

Conference paper

3D shape similarity using vectors of locally aggregated tensors

H. Tabia, D. Picard, H. Laga and P-H Gosselin

2013 IEEE International Conference on Image Processing

20th IEEE International Conference on Image Processing (ICIP) 2013 (Melbourne Convention and Exhibition Centre, Melbourne, VIC, 15/09/2013–18/09/2013)

2013

DOI: https://doi.org/10.1109/ICIP.2013.6738555

Files and links (1)

url

Link to Published Version *Subscription may be requiredView

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.

Details

Title: 3D shape similarity using vectors of locally aggregated tensors
Authors/Creators: H. Tabia (Author/Creator) - École Nationale Supérieure de l'Électronique et de ses Applications
D. Picard (Author/Creator) - École Nationale Supérieure de l'Électronique et de ses Applications
H. Laga (Author/Creator) - University of South Australia
P-H Gosselin (Author/Creator) - École Nationale Supérieure de l'Électronique et de ses Applications
Publication Details: 2013 IEEE International Conference on Image Processing
Conference: 20th IEEE International Conference on Image Processing (ICIP) 2013 (Melbourne Convention and Exhibition Centre, Melbourne, VIC, 15/09/2013–18/09/2013)
Identifiers: 991005540196507891
Murdoch Affiliation: Murdoch University
Language: English
Resource Type: Conference paper

Metrics

33 Record Views