Using Growing Cell Structures for Surface Reconstruction

Authors:
I. P. Ivrissimtzis;W-K. Jeong;H-P. Seidel
Affiliations:
-;-;-
Venue:
SMI '03 Proceedings of the Shape Modeling International 2003
Year:
2003

Citing 0
Cited 15

Neural Meshes: Statistical Learning Based on Normals

PG '03 Proceedings of the 11th Pacific Conference on Computer Graphics and Applications
An integrating approach to meshing scattered point data

Proceedings of the 2005 ACM symposium on Solid and physical modeling
A composite approach to meshing scattered data

Graphical Models - Special issue on SPM 05
A mesh optimization algorithm based on neural networks

Information Sciences: an International Journal
Improving the neural meshes algorithm for 3D surface reconstruction with edge swap operations

Proceedings of the 2008 ACM symposium on Applied computing
Evaluating approximations generated by the GNG3D method for mesh simplification

AIKED'08 Proceedings of the 7th WSEAS International Conference on Artificial intelligence, knowledge engineering and data bases
Error measurements and parameters choice in the GNG3D model for mesh simplification

WSEAS Transactions on Information Science and Applications
Robust mesh reconstruction from unoriented noisy points

2009 SIAM/ACM Joint Conference on Geometric and Physical Modeling
Growing self-organizing surface map: Learning a surface topology from a point cloud

Neural Computation
Surface reconstruction from large point clouds using virtual shared memory manager

ICCSA'06 Proceedings of the 6th international conference on Computational Science and Its Applications - Volume Part I
2012 Special Issue: Using GNG to improve 3D feature extraction-Application to 6DoF egomotion

Neural Networks
A study of a soft computing based method for 3D scenario reconstruction

Applied Soft Computing
GPGPU implementation of growing neural gas: Application to 3D scene reconstruction

Journal of Parallel and Distributed Computing
2013 Special Issue: Self-organizing adaptive map: Autonomous learning of curves and surfaces from point samples

Neural Networks
Self-organizing maps with a time-varying structure

ACM Computing Surveys (CSUR)

Quantified Score

Hi-index	0.00

Visualization

Abstract

We study the use of neural network algorithms in surfacereconstruction from an unorganized point cloud, andmeshing of an implicit surface. We found that for such applications,the most suitable type of neural networks is amodified version of the Growing Cell Structure we proposehere. The algorithm works by sampling randomly a targetspace, usually a point cloud or an implicit surface, and adjustingaccordingly the neural network. The adjustment includesthe connectivity of the network. Doing several experimentswe found that the algorithm gives satisfactory resultsin some challenging situations involving sharp features andconcavities. Another attractive feature of the algorithm isthat its speed is virtually independent from the size of theinput data, making it particularly suitable for the reconstructionof a surface from a very large point set.