A self-organized neural network for 3D surface reconstruction

Abstract

We present a multiresolution surface reconstruction method from point clouds in 3D space based on Kononen’s self-organizing neural networks. It uses a set of mesh operators and simple rules for selective mesh refinement. Experimental results shows the method is very sucessfull to reconstruct forms of varied geometry.

7 Figures and Tables

Cite this paper

@inproceedings{MEDEIROS2005ASN, title={A self-organized neural network for 3D surface reconstruction}, author={AGOSTINHO DE MEDEIROS and B. A. Junior and A. M. de Oliveira Duarte and D Neto and Jorge Dantas and D Melo}, year={2005} }