File Download

There are no files associated with this item.

  • Find it @ UNIST can give you direct access to the published full text of this article. (UNISTARs only)
Related Researcher

정원기

Jeong, Won-Ki
Read More

Views & Downloads

Detailed Information

Cited time in webofscience Cited time in scopus
Metadata Downloads

Neural mesh ensembles

Author(s)
Ivrissimtzis, ILee, YunjinLee, SeungyongJeong, Won-KiSeidel, H.-P.
Issued Date
2004-09-06
DOI
10.1109/TDPVT.2004.1335216
URI
https://scholarworks.unist.ac.kr/handle/201301/34815
Fulltext
https://ieeexplore.ieee.org/document/1335216
Citation
Proceedings - 2nd International Symposium on 3D Data Processing, Visualization, and Transmission. 3DPVT 2004, pp.308 - 315
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.
Publisher
IEEE Computer Society

qrcode

Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.