论文标题
部分可观测时空混沌系统的无模型预测
GeoGCN: Geometric Dual-domain Graph Convolution Network for Point Cloud Denoising
论文作者
论文摘要
我们提出了GeoGCN，这是一种新型的几何双域图卷积网络，用于点云DeNoising（PCD）。除了PCD的传统智慧之外，为了充分利用点云的几何信息，我们定义了两种表面正常，一个称为“真实正常（RN）”，另一个称为“实际正常（RN）”，而另一种是虚拟的（VN）。 RN保留了嘈杂点云的当地细节，而VN避免了在Denoising期间的全球形状收缩。 GEOGCN是一种新的PCD范式，1）首先在VNS的帮助下通过基于空间的GCN回归点位置，2）然后通过对回归点进行主成分分析来估算初始RN，而3）最终通过基于正常的GCN来回归Fine RNS。与现有的PCD方法不同，GeoGCN不仅利用了两种几何专业知识（即RN和VN），而且还从培训数据中受益。实验验证了GeoGCN在噪声和局部和全球特征保存方面均优于SOTA。
We propose GeoGCN, a novel geometric dual-domain graph convolution network for point cloud denoising (PCD). Beyond the traditional wisdom of PCD, to fully exploit the geometric information of point clouds, we define two kinds of surface normals, one is called Real Normal (RN), and the other is Virtual Normal (VN). RN preserves the local details of noisy point clouds while VN avoids the global shape shrinkage during denoising. GeoGCN is a new PCD paradigm that, 1) first regresses point positions by spatialbased GCN with the help of VNs, 2) then estimates initial RNs by performing Principal Component Analysis on the regressed points, and 3) finally regresses fine RNs by normalbased GCN. Unlike existing PCD methods, GeoGCN not only exploits two kinds of geometry expertise (i.e., RN and VN) but also benefits from training data. Experiments validate that GeoGCN outperforms SOTAs in terms of both noise-robustness and local-and-global feature preservation.
