Neural-network-based models of 3-D objects for virtualized reality: a comparative study

TitleNeural-network-based models of 3-D objects for virtualized reality: a comparative study
Publication TypeJournal Article
Year of Publication2006
AuthorsCretu, A. - M., E. M. Petriu, and G. G. Patry
JournalInstrumentation and Measurement, IEEE Transactions on
Pagination99 - 111
Date Publishedfeb.
Keywords3D object representation, computational complexity, feedforward neural nets, multilayer feedforward neural network, multilayer perceptrons, neural gas network, neural-network-based models, object collision detection, object morphing, object motion estimation, object recognition, self-organising feature maps, self-organizing map, surface representation, unsupervised learning, virtual reality, virtualized reality

The paper presents a comprehensive analysis and comparison of the representational capabilities of three neural architectures for three-dimensional (3-D) object representation in terms of purpose, computational cost, complexity, conformance and convenience, ease of manipulation, and potential applications in the context of virtualized reality. Starting from a pointcloud that embeds the shape of the object to be modeled, a volumetric representation is obtained using a multilayer feedforward neural network (MLFFNN) or a surface representation using either the self-organizing map (SOM) or the neural gas network. The representation provided by the neural networks (NNs) is simple, compact, and accurate. The models can be easily transformed in size, position, and shape. Some potential applications of the presented architectures in the context of virtualized reality are for the modeling of set operations and object morphing, for the detection of object collision, and for object recognition, object motion estimation, and segmentation.


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

Emergency Procedures | Accessibility | Contact UBC | © Copyright 2021 The University of British Columbia