标题： BAGNet：一种用于3D点云语义分割的边界感知图注意力网络 显示英文标题

标题： BAGNet: A Boundary-Aware Graph Attention Network for 3D Point Cloud Semantic Segmentation

摘要： 由于点云数据本质上是不规则且无结构的，因此点云语义分割一直是一项具有挑战性的任务。基于图的方法试图通过将其表示为图来建模不规则点云；然而，这种方法由于需要为大规模点云中的每个点构建一个图而产生了巨大的计算成本。 本文观察到边界点具有更复杂的空间结构信息，并开发了一种新的图注意力网络，称为边界感知图注意力网络（BAGNet）。一方面，BAGNet 包含一个边界感知图注意力层（BAGLayer），该层利用边顶点融合和注意力系数来捕获边界点的特征，从而减少计算时间。另一方面，BAGNet 使用轻量级注意池化层提取点云的整体特征以保持模型准确性。 标准数据集上的大量实验表明，BAGNet 在点云语义分割方面优于最先进的方法，具有更高的准确性和更少的推理时间。 显示英文摘要

摘要： Since the point cloud data is inherently irregular and unstructured, point cloud semantic segmentation has always been a challenging task. The graph-based method attempts to model the irregular point cloud by representing it as a graph; however, this approach incurs substantial computational cost due to the necessity of constructing a graph for every point within a large-scale point cloud. In this paper, we observe that boundary points possess more intricate spatial structural information and develop a novel graph attention network known as the Boundary-Aware Graph attention Network (BAGNet). On one hand, BAGNet contains a boundary-aware graph attention layer (BAGLayer), which employs edge vertex fusion and attention coefficients to capture features of boundary points, reducing the computation time. On the other hand, BAGNet employs a lightweight attention pooling layer to extract the global feature of the point cloud to maintain model accuracy. Extensive experiments on standard datasets demonstrate that BAGNet outperforms state-of-the-art methods in point cloud semantic segmentation with higher accuracy and less inference time.