基于 Dynamic Graph CNN 利用局部几何结构的点云去噪与离群点检测
Point Cloud Denoising and Outlier Detection with Local Geometric Structure by Dynamic Graph CNN
AI总结：
针对 PointCloudNet 未考虑 patch 局部几何结构的问题，提出基于 Dynamic Graph CNN 的两种图卷积层方法，在 AUPR 和 Chamfer Distance 指标上优于传统方法，提升了点云去噪与离群点检测精度。
摘要：
社会的数字化正朝着实现数字孪生和元宇宙的方向快速发展。特别是，点云作为 3D 空间的一种媒体格式正受到关注。由于测量误差，点云数据被噪声和离群点污染。因此，点云处理需要进行去噪和离群点检测。其中，PointCleanNet 是一种有效的点云去噪和离群点检测方法。然而，它没有考虑 patch 的局部几何结构。我们通过应用两种基于 Dynamic Graph CNN 设计的图卷积层来解决这一问题。实验结果表明，所提出的方法在表示离群点检测精度的 AUPR 和表示去噪精度的 Chamfer Distance 上均优于传统方法。
英文摘要：
The digitalization of society is rapidly developing toward the realization of the digital twin and metaverse. In particular, point clouds are attracting attention as a media format for 3D space. Point cloud data is contaminated with noise and outliers due to measurement errors. Therefore, denoising and outlier detection are necessary for point cloud processing. Among them, PointCleanNet is an effective method for point cloud denoising and outlier detection. However, it does not consider the local geometric structure of the patch. We solve this problem by applying two types of graph convolutional layer designed based on the Dynamic Graph CNN. Experimental results show that the proposed methods outperform the conventional method in AUPR, which indicates outlier detection accuracy, and Chamfer Distance, which indicates denoising accuracy.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
