文章基本信息

标题：NormNet: Point-wise normal estimation network for three-dimensional point cloud data
本地全文：下载
作者：Janghun Hyeon ; Janghun Hyeon ; Weonsuk Lee 等
期刊名称：International Journal of Advanced Robotic Systems
印刷版ISSN：1729-8806
电子版ISSN：1729-8814
出版年度：2019
卷号：16
期号：4
页码：1-11
DOI：10.1177/1729881419857532
出版社：SAGE Publications
摘要：In this article, a point-wise normal estimation network for three-dimensional point cloud data called NormNet is proposed. We propose the multiscale K-nearest neighbor convolution module for strengthened local feature extraction. With the multiscale K-nearest neighbor convolution module and PointNet-like architecture, we achieved a hybrid of three features: a global feature, a semantic feature from the segmentation network, and a local feature from the multiscale K-nearest neighbor convolution module. Those features, by mutually supporting each other, not only increase the normal estimation performance but also enable the estimation to be robust under severe noise perturbations or point deficiencies. The performance was validated in three different data sets: Synthetic CAD data (ModelNet), RGB-D sensor-based real 3D PCD (S3DIS), and LiDAR sensor-based real 3D PCD that we built and shared.
关键词：Normal estimation ; 3-D deep learning ; 3-D sensor system ; 3-D indoor LiDAR data set ; robustness