论文标题
面向形状的卷积神经网络用于点云分析
Shape-Oriented Convolution Neural Network for Point Cloud Analysis
论文作者
论文摘要
点云是用于3D几何信息编码的主要数据结构。与其他常规的视觉数据（例如图像和视频）不同，这些不规则的点描述了3D对象的复杂形状特征，这使得形状的特征学习是点云分析的重要组成部分。为此，提议以形状为导向的消息传递方案将ShapeConv称为ShapeConv，以关注每个局部相邻点形成的基本形状的表示。尽管存在这种形状的关系学习，但ShapeConv还旨在通过捕获局部基础形状之间的长期依赖关系来纳入形状之间的上下文效应。这个面向形状的操作员堆叠在我们的层次学习体系结构中，即以形状为导向的卷积神经网络（SOCNN），用于点云分析。已经进行了广泛的实验，以评估其在点云分类和部分分段的任务中的重要性。
Point cloud is a principal data structure adopted for 3D geometric information encoding. Unlike other conventional visual data, such as images and videos, these irregular points describe the complex shape features of 3D objects, which makes shape feature learning an essential component of point cloud analysis. To this end, a shape-oriented message passing scheme dubbed ShapeConv is proposed to focus on the representation learning of the underlying shape formed by each local neighboring point. Despite this intra-shape relationship learning, ShapeConv is also designed to incorporate the contextual effects from the inter-shape relationship through capturing the long-ranged dependencies between local underlying shapes. This shape-oriented operator is stacked into our hierarchical learning architecture, namely Shape-Oriented Convolutional Neural Network (SOCNN), developed for point cloud analysis. Extensive experiments have been performed to evaluate its significance in the tasks of point cloud classification and part segmentation.
