Neural mesh ensembles

Neural mesh ensembles
复制标题

神经网络集成

DOI:
10.1109/tdpvt.2004.1335216
复制
发表时间:
2004
期刊:
Proceedings. 2nd International Symposium on 3D Data Processing, Visualization and Transmission, 2004. 3DPVT 2004.
影响因子:
--
通讯作者:
H. Seidel
H. Seidel
中科院分区:
--
文献类型:
--
作者:
I. Ivrissimtzis;Yunjin Lee;Seungyong Lee;W. Jeong;H. Seidel

文献摘要

被引文献

相似文献

这项工作提出了使用神经网络集成,以提高基于神经网络的表面重建算法的性能。枚举是一种非常流行和强大的统计技术,它基于对概率算法的多个输出进行平均的思想。在表面重建的背景下,出现两个主要问题。第一个是找到一种有效的方法来平均具有不同连通性的网格,第二个是调整参数的表面重建,以最大限度地提高整体的性能。我们解决了第一个问题,体素化所有的网格在同一个规则的网格,并采取多数表决每个体素。我们通过实验调整参数,借用弱学习方法的思想。
This work 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.