Abstract Semantic segmentation of point cloud is a fundamental problem in scene-level understanding. Despite advancement in recent years by leveraging capabilities of Neural Networks and massive labeling datasets available, providing fine-grained semantic segmentation for point cloud is still challenging, given the fact that point cloud is usually unstructured, unordered and sparse. In this paper, we achieve semantic point cloud labeling by adaptively exploring semantic relation and aggregating contextual information between points. Specifically, we first introduce an attention-based local relation learning module for collecting local features, which can capture semantic relation in a manner of anisotropy. And we then design a novel context aggregation module guided by multi-scale supervision to obtain long-range dependencies between semantically-correlated points and enhance the distinctive ability of points in feature space. In addition, a gated propagation strategy is adopted instead of skip links to conditionally concatenate local point features in different layers. We empirically evaluate our method on public benchmarks (S3DIS and ShapeNetPart), and demonstrate our performance is on par or better than state-of-the-art methods.

中文翻译：

---

基于注意力的点云语义分割关系和上下文建模

摘要 点云的语义分割是场景级理解中的一个基本问题。尽管近年来通过利用神经网络的功能和可用的海量标签数据集取得了进步，但鉴于点云通常是非结构化、无序和稀疏的事实，为点云提供细粒度语义分割仍然具有挑战性。在本文中，我们通过自适应探索语义关系和聚合点之间的上下文信息来实现语义点云标记。具体来说，我们首先引入了一个基于注意力的局部关系学习模块来收集局部特征，它可以以各向异性的方式捕捉语义关系。然后我们设计了一个新的基于多尺度监督的上下文聚合模块，以获得语义相关点之间的长期依赖关系，并增强特征空间中点的区分能力。此外，采用门控传播策略而不是跳过链接来有条件地连接不同层中的局部点特征。我们在公共基准（S3DIS 和 ShapeNetPart）上凭经验评估我们的方法，并证明我们的性能与最先进的方法相当或更好。