Neural Mesh Ensembles

Authors:
Ioannis Ivrissimtzis;Yunjin Lee;Seungyong Lee;Won-Ki Jeong;Hans-Peter Seidel
Affiliations:
MPI Informatik;POSTECH & MPI Informatik;POSTECH & MPI Informatik;University of Utah;MPI Informatik
Venue:
3DPVT '04 Proceedings of the 3D Data Processing, Visualization, and Transmission, 2nd International Symposium
Year:
2004

Citing 0
Cited 5

Surface and normal ensembles for surface reconstruction

Computer-Aided Design
Growing self-organizing surface map: Learning a surface topology from a point cloud

Neural Computation
Ensembles for normal and surface reconstructions

GMP'06 Proceedings of the 4th international conference on Geometric Modeling and Processing
SMI 2012: Full Consensus meshing

Computers and Graphics
Robust filtering of noisy scattered point data

SPBG'05 Proceedings of the Second Eurographics / IEEE VGTC conference on Point-Based Graphics

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes the use of neural network ensembles to boost the performance of a neural network based surface reconstruction algorithm. Ensemble is a very popular and powerful statistical technique based on the idea of averaging several outputs of a probabilistic algorithm. In the context of surface reconstruction, two main problems arise. The first is finding an efficient way to average meshes with different connectivity, and the second is tuning the parameters for surface reconstruction to maximize the performance of the ensemble. We solve the first problem by voxelizing all the meshes on the same regular grid and taking majority vote on each voxel. We tune the parameters experimentally, borrowing ideas from weak learning methods.