Recent works attempt to extend Graph Convolution Networks (GCNs) to point clouds for classification and segmentation tasks. These works tend to sample and group points to create smaller point sets locally and mainly focus on extracting local features through GCNs, while ignoring the relationship between point sets. In this paper, we propose the Dynamic Hop Graph Convolution Network (DHGCN) for explicitly learning the contextual relationships between the voxelized point parts, which are treated as graph nodes. Motivated by the intuition that the contextual information between point parts lies in the pairwise adjacent relationship, which can be depicted by the hop distance of the graph quantitatively, we devise a novel self-supervised part-level hop distance reconstruction task and design a novel loss function accordingly to facilitate training. In addition, we propose the Hop Graph Attention (HGA), which takes the learned hop distance as input for producing attention weights to allow edge features to contribute distinctively in aggregation. Eventually, the proposed DHGCN is a plug-and-play module that is compatible with point-based backbone networks. Comprehensive experiments on different backbones and tasks demonstrate that our self-supervised method achieves state-of-the-art performance. Our source code is available at: https://github.com/Jinec98/DHGCN.

翻译：近期研究尝试将图卷积网络（GCNs）扩展至点云分类与分割任务中。这类工作通常对点云进行采样与分组以构建局部点集，并通过GCNs提取局部特征，但忽略了点集间的关联关系。本文提出动态跳数图卷积网络（DHGCN），旨在显式学习被视作图节点的体素化点部件间的上下文关系。基于"点部件间的上下文信息蕴含于成对邻接关系中，可借助图的跳数距离定量刻画"这一直觉，我们设计了一种新颖的自监督部件级跳数距离重建任务，并据此设计对应损失函数以促进训练。此外，我们提出跳数图注意力机制（HGA），将学习到的跳数距离作为输入生成注意力权重，使边特征在聚合过程中具有差异化贡献。最终，所提出的DHGCN是一种即插即用模块，可与基于点云的骨干网络兼容。在不同骨干网络与任务上的综合实验表明，我们的自监督方法达到了最先进性能。源代码已发布于：https://github.com/Jinec98/DHGCN。