首页> 外文期刊>Graphical models >3D mesh segmentation via multi-branch 1D convolutional neural networks
【24h】

3D mesh segmentation via multi-branch 1D convolutional neural networks

机译:通过多分支1D卷积神经网络进行3D网格分割

获取原文
获取原文并翻译 | 示例
           

摘要

There is an increasing interest in applying deep learning to 3D mesh segmentation. We observe that 1) existing feature- based techniques are often slow or sensitive to feature resizing, 2) there are minimal comparative studies and 3) techniques often suffer from reproducibility issue. This study contributes in two ways. First, we propose a novel convolutional neural network (CNN) for mesh segmentation. It uses 1D data, filters and a multi- branch architecture for separate training of multi- scale features. Together with a novel way of computing conformal factor (CF), our technique clearly out- performs existing work. Secondly, we publicly provide implementations of several deep learning techniques, namely, neural networks (NNs), autoencoders (AEs) and CNNs, whose architectures are at least two layers deep. The significance of this study is that it proposes a robust form of CF, offers a novel and accurate CNN technique, and a comprehensive study of several deep learning techniques for baseline comparison.
机译:将深度学习应用于3D网格分割的兴趣日益浓厚。我们观察到:1)现有的基于特征的技术通常对特征大小调整缓慢或敏感,2)进行的比较研究很少,并且3)技术经常遭受可再现性问题的困扰。这项研究有两种方式。首先,我们提出了一种新颖的卷积神经网络(CNN)用于网格分割。它使用一维数据,过滤器和多分支架构来分别训练多尺度特征。结合计算保形因子(CF)的新颖方法,我们的技术明显胜过现有工作。其次,我们公开提供了几种深度学习技术的实现,即深度至少两层的神经网络(NN),自动编码器(AE)和CNN。这项研究的意义在于,它提出了一种健壮的CF形式,提供了一种新颖而准确的CNN技术,并对几种用于基线比较的深度学习技术进行了全面研究。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号