Neural network architecture for 3D object representation

TitleNeural network architecture for 3D object representation
Publication TypeConference Paper
Year of Publication2003
AuthorsCretu, A. - M., E. M. Petriu, and G. G. Patry
Conference NameHaptic, Audio and Visual Environments and Their Applications, 2003. HAVE 2003. Proceedings. The 2nd IEEE Internatioal Workshop on
Pagination31 - 36
Date Publishedsep.
Keywords3-dimensional object representation, 3D coordinates, 3D object generation, 3D object training, computer graphics, feedforward neural nets, feedforward structure, image morphing, image representation, multilayer perceptrons, neural net architecture, neural network architecture, object morphing, object recognition, operation setting, transformation neural network module

The paper discusses a neural network architecture for 3D object modeling. A multi-layered feedforward structure having as inputs the 3D-coordinates of the object points is employed to model the object space. Cascaded with a transformation neural network module, the proposed architecture can be used to generate and train 3D objects, perform transformations, set operations and object morphing. A possible application for object recognition is also presented.


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