A comparison of neural networks architectures for geometric modelling of 3D objects

TitleA comparison of neural networks architectures for geometric modelling of 3D objects
Publication TypeConference Paper
Year of Publication2004
AuthorsCretu, A. - M., E. M. Petriu, and G. G. Patry
Conference NameComputational Intelligence for Measurement Systems and Applications, 2004. CIMSA. 2004 IEEE International Conference on
Pagination155 - 160
Date Publishedjul.
Keywords3D object representation, geometric modelling, image segmentation, motion estimation, neural nets, neural network architecture, object detection, object morphing, object motion estimation, object recognition, object segmentation, solid modelling
Abstract

This paper presents a critical comparison between three neural architectures for 3D object representation in terms of purpose, computational cost, complexity, conformance and convenience, ease of manipulation and potential uses in the context of virtualized reality. The models can be easily transformed in size, position and shape. Potential uses of the presented architectures in the context of virtualized reality are for the modeling of set operations and object morphing, for the detection of objects collision, for object recognition, object motion estimation and segmentation.

URLhttp://dx.doi.org/10.1109/CIMSA.2004.1397253
DOI10.1109/CIMSA.2004.1397253

a place of mind, The University of British Columbia

Electrical and Computer Engineering
2332 Main Mall
Vancouver, BC Canada V6T 1Z4
Tel +1.604.822.2872
Fax +1.604.822.5949
Email:

Emergency Procedures | Accessibility | Contact UBC | © Copyright 2020 The University of British Columbia