Murdoch University Research Repository

Welcome to the Murdoch University Research Repository

The Murdoch University Research Repository is an open access digital collection of research
created by Murdoch University staff, researchers and postgraduate students.

Learn more

3D shape similarity using vectors of locally aggregated tensors

Tabia, H., Picard, D., Laga, H.ORCID: 0000-0002-4758-7510 and Gosselin, P-H (2013) 3D shape similarity using vectors of locally aggregated tensors. In: 20th IEEE International Conference on Image Processing (ICIP) 2013, 15 - 18 September 2013, Melbourne Convention and Exhibition Centre, Melbourne, VIC

Link to Published Version:
*Subscription may be required


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.

Item Type: Conference Paper
Item Control Page Item Control Page