Learning Polynomial-Based Separable Convolution for 3D Point Cloud Analysis.
Learning Polynomial-Based Separable Convolution for 3D Point Cloud Analysis.
复制标题
学习基于多项式的可分离卷积进行 3D 点云分析
DOI：
10.3390/s21124211
复制
发表时间：
2021-06-19
期刊：
影响因子：
--
通讯作者：
Sun J
中科院分区：
文献类型：
--
作者：
Yu R;Sun J
点云数据的形状分类和分割是摄影测量和遥感应用中要求最高的两项任务，其目的是识别物体类别或点标记。在这些任务中，点卷积是在点云上设计网络时必不可少的操作，它有助于探索3D局部点以进行特征学习。本文提出了一种利用多项式学习的可分离权值进行三维点云分析的新颖点卷积（PSConv）方法。具体来说，我们通过学习基于变换后的局部点坐标多项式的点卷积核，将传统的正则数据上定义的卷积推广到三维点云。我们进一步提出了卷积核的可分离假设，以减少点卷积的参数大小和计算成本。利用这种新颖的点卷积，提出了一种定义在点云上的分层网络（PSNet），用于三维形状分类和分割等三维形状分析任务。实验在标准数据集上进行，包括合成和真实扫描数据集，我们的PSNet在形状分类方面达到了最先进的精度，在形状分割方面与以前的方法相比具有竞争力。
Shape classification and segmentation of point cloud data are two of the most demanding tasks in photogrammetry and remote sensing applications, which aim to recognize object categories or point labels. Point convolution is an essential operation when designing a network on point clouds for these tasks, which helps to explore 3D local points for feature learning. In this paper, we propose a novel point convolution (PSConv) using separable weights learned with polynomials for 3D point cloud analysis. Specifically, we generalize the traditional convolution defined on the regular data to a 3D point cloud by learning the point convolution kernels based on the polynomials of transformed local point coordinates. We further propose a separable assumption on the convolution kernels to reduce the parameter size and computational cost for our point convolution. Using this novel point convolution, a hierarchical network (PSNet) defined on the point cloud is proposed for 3D shape analysis tasks such as 3D shape classification and segmentation. Experiments are conducted on standard datasets, including synthetic and real scanned ones, and our PSNet achieves state-of-the-art accuracies for shape classification, as well as competitive results for shape segmentation compared with previous methods.
影响因子：
6.2
作者：
Wang, Yue;Sun, Yongbin;Solomon, Justin M.
通讯作者：
Solomon, Justin M.
影响因子：
1.8
作者：
Olshausen, BA;Field, DJ
通讯作者：
Field, DJ
影响因子：
5.2
作者：
Ben-Shabat, Yizhak;Lindenbaum, Michael;Fischer, Anath
通讯作者：
Fischer, Anath