论文标题
球形插值卷积网络，具有距离功能密度的3D语义分割的点云
Spherical Interpolated Convolutional Network with Distance-Feature Density for 3D Semantic Segmentation of Point Clouds
论文作者
论文摘要
点云的语义分割是机器人环境感知的重要组成部分。但是，由于点云的非结构化属性，很难直接采用传统的3D卷积内核来从RAW 3D点云中提取功能。在本文中，提出了一个球形插值卷积操作员，以取代传统的网格形3D卷积操作员。这个新提出的功能提取操作员提高了网络的准确性并减少了网络的参数。此外，本文根据距离的距离分析了点云插值方法的缺陷，并通过结合距离和特征相关性来提出自我学习的距离功能密度。提出的方法使球形插值卷积网络的特征提取更合理和有效。提出的网络的有效性在点云的3D语义分割任务上得到了证明。实验表明，所提出的方法在扫描仪数据集和巴黎 - 莱尔-3D数据集上实现了良好的性能。
The semantic segmentation of point clouds is an important part of the environment perception for robots. However, it is difficult to directly adopt the traditional 3D convolution kernel to extract features from raw 3D point clouds because of the unstructured property of point clouds. In this paper, a spherical interpolated convolution operator is proposed to replace the traditional grid-shaped 3D convolution operator. This newly proposed feature extraction operator improves the accuracy of the network and reduces the parameters of the network. In addition, this paper analyzes the defect of point cloud interpolation methods based on the distance as the interpolation weight and proposes the self-learned distance-feature density by combining the distance and the feature correlation. The proposed method makes the feature extraction of spherical interpolated convolution network more rational and effective. The effectiveness of the proposed network is demonstrated on the 3D semantic segmentation task of point clouds. Experiments show that the proposed method achieves good performance on the ScanNet dataset and Paris-Lille-3D dataset.
