Lei Huan, Akhtar Naveed, Mian Ajmal
IEEE Trans Pattern Anal Mach Intell. 2021 Oct;43(10):3664-3680. doi: 10.1109/TPAMI.2020.2983410. Epub 2021 Sep 2.
We propose a spherical kernel for efficient graph convolution of 3D point clouds. Our metric-based kernels systematically quantize the local 3D space to identify distinctive geometric relationships in the data. Similar to the regular grid CNN kernels, the spherical kernel maintains translation-invariance and asymmetry properties, where the former guarantees weight sharing among similar local structures in the data and the latter facilitates fine geometric learning. The proposed kernel is applied to graph neural networks without edge-dependent filter generation, making it computationally attractive for large point clouds. In our graph networks, each vertex is associated with a single point location and edges connect the neighborhood points within a defined range. The graph gets coarsened in the network with farthest point sampling. Analogous to the standard CNNs, we define pooling and unpooling operations for our network. We demonstrate the effectiveness of the proposed spherical kernel with graph neural networks for point cloud classification and semantic segmentation using ModelNet, ShapeNet, RueMonge2014, ScanNet and S3DIS datasets. The source code and the trained models can be downloaded from https://github.com/hlei-ziyan/SPH3D-GCN.
我们提出了一种用于三维点云高效图卷积的球形内核。我们基于度量的内核系统地量化局部三维空间，以识别数据中独特的几何关系。与常规网格卷积神经网络内核类似，球形内核保持平移不变性和不对称性，前者保证数据中相似局部结构之间的权重共享，后者有助于精细几何学习。所提出的内核应用于图神经网络，无需依赖边生成滤波器，这使其在处理大型点云时具有计算吸引力。在我们的图网络中，每个顶点与单个点位置相关联，边连接定义范围内的邻域点。通过最远点采样，图在网络中逐渐粗化。类似于标准卷积神经网络，我们为网络定义了池化和解池化操作。我们使用ModelNet、ShapeNet、RueMonge2014、ScanNet和S3DIS数据集，展示了所提出的球形内核与图神经网络在点云分类和语义分割方面的有效性。源代码和训练模型可从https://github.com/hlei-ziyan/SPH3D-GCN下载。
