论文标题
Pointscnet：基于空间填充曲线引导的采样的点云结构和相关学习
PointSCNet: Point Cloud Structure and Correlation Learning Based on Space Filling Curve-Guided Sampling
论文作者
论文摘要
几何结构和内部局部区域关系，例如对称，常规阵列，连接等，对于理解3D形状至关重要。本文提出了一个名为Pointscnet的点云特征提取网络，以捕获点云的几何结构信息和局部区域相关信息。 Pointscnet由三个主要模块组成：填充空间曲线引导的采样模块，信息融合模块和通道空间注意模块。填充空间曲线引导的采样模块使用Z阶曲线编码对包含几何相关的样品点。信息融合模块使用相关张量和一组跳过连接来融合结构和相关信息。通道空间注意模块增强了关键点和关键特征通道的表示，以完善网络。对所提出的Pointscnet进行了对形状分类和部分分割任务的评估。实验结果表明，通过有效地学习点云的结构和相关性，点cnet优于最先进的方法或与最新方法相提并论。
Geometrical structures and the internal local region relationship, such as symmetry, regular array, junction, etc., are essential for understanding a 3D shape. This paper proposes a point cloud feature extraction network named PointSCNet, to capture the geometrical structure information and local region correlation information of a point cloud. The PointSCNet consists of three main modules: the space-filling curve-guided sampling module, the information fusion module, and the channel-spatial attention module. The space-filling curve-guided sampling module uses Z-order curve coding to sample points that contain geometrical correlation. The information fusion module uses a correlation tensor and a set of skip connections to fuse the structure and correlation information. The channel-spatial attention module enhances the representation of key points and crucial feature channels to refine the network. The proposed PointSCNet is evaluated on shape classification and part segmentation tasks. The experimental results demonstrate that the PointSCNet outperforms or is on par with state-of-the-art methods by learning the structure and correlation of point clouds effectively.
