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

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 transfor...

Full description

Saved in:
Bibliographic Details
Main Authors: Cretu, A.-M., Petriu, E.M., Patry, G.G.
Format: Conference Proceeding
Language:English
Subjects:
Computational efficiency
Computer architecture
Context modeling
Motion detection
Motion estimation
Neural networks
Object detection
Object recognition
Shape
Solid modeling
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
DOI:10.1109/CIMSA.2004.1397253