Point clouds, being the simple and compact representation of surface geometry of 3D objects, have gained increasing popularity with the evolution of deep learning networks for classification and segmentation tasks. Unlike human, teaching the machine to analyze the segments of an object is a challenging task and quite essential in various machine vision applications. In this paper, we address the problem of segmentation and labelling of the 3D point clouds by proposing a inception based deep network architecture called PIG-Net, that effectively characterizes the local and global geometric details of the point clouds. In PIG-Net, the local features are extracted from the transformed input points using the proposed inception layers and then aligned by feature transform. These local features are aggregated using the global average pooling layer to obtain the global features. Finally, feed the concatenated local and global features to the convolution layers for segmenting the 3D point clouds. We perform an exhaustive experimental analysis of the PIG-Net architecture on two state-of-the-art datasets, namely, ShapeNet [1] and PartNet [2]. We evaluate the effectiveness of our network by performing ablation study.
翻译:3D对象的地表几何结构简单而紧凑,随着分类和分解任务的深层次学习网络的演变,点云越来越受欢迎。与人类不同,教授机器分析物体各部分是一项具有挑战性的任务,在各种机器视觉应用中相当必要。在本文件中,我们通过提出一个基于初始的称为PIG-Net的深层次网络结构来解决3D点云的分解和标签问题,这个结构可以有效地描述点云的当地和全球几何细节。在PIG-Net中,从转型输入点中提取当地特征,使用拟议的起始层,然后通过特征转换加以调整。这些地方特征是利用全球平均集合层进行汇总,以获得全球特征。最后,将凝聚的本地和全球特征提供给3D点云的交汇层。我们对两个状态的数据集,即ShapeNet [1] 和PartNet进行彻底的实验分析。我们通过进行减缩研究来评估我们的网络的有效性。