论文标题
双向功能全球化，用于3D点云场景的几个射击语义分割
Bidirectional Feature Globalization for Few-shot Semantic Segmentation of 3D Point Cloud Scenes
论文作者
论文摘要
点云的几乎没有分割仍然是一项具有挑战性的任务，因为没有有效的方法将局部点云信息转换为全局表示，这阻碍了点特征的概括能力。在这项研究中，我们提出了一种双向特征全球化（BFG）方法，该方法利用点特征和原型向量之间的相似性测量，以双向方式将全球感知嵌入到局部点特征中。随着点对点型全球化（PO2PRG），BFG根据从密度点特征到稀疏原型的相似权重汇总了原型的本地点特征。使用原型到点全球化（PR2POG），基于从稀疏原型到密集点特征的相似性权重，全局感知嵌入到局部点特征中。每个类嵌入全局感知的类的稀疏原型汇总到基于度量学习框架的几个射击3D分割的单个原型。对S3DIS和SCANNET的广泛实验表明，BFG的表现明显优于最新方法。
Few-shot segmentation of point cloud remains a challenging task, as there is no effective way to convert local point cloud information to global representation, which hinders the generalization ability of point features. In this study, we propose a bidirectional feature globalization (BFG) approach, which leverages the similarity measurement between point features and prototype vectors to embed global perception to local point features in a bidirectional fashion. With point-to-prototype globalization (Po2PrG), BFG aggregates local point features to prototypes according to similarity weights from dense point features to sparse prototypes. With prototype-to-point globalization (Pr2PoG), the global perception is embedded to local point features based on similarity weights from sparse prototypes to dense point features. The sparse prototypes of each class embedded with global perception are summarized to a single prototype for few-shot 3D segmentation based on the metric learning framework. Extensive experiments on S3DIS and ScanNet demonstrate that BFG significantly outperforms the state-of-the-art methods.
