Semantic segmentation of large-scale 3D landscape meshes is pivotal for various geospatial applications, including spatial analysis, automatic mapping and localization of target objects, and urban planning and development. This requires an efficient and accurate 3D perception system to understand and analyze real-world environments. However, traditional mesh segmentation methods face challenges in accurately segmenting small objects and maintaining computational efficiency due to the complexity and large size of 3D landscape mesh datasets. This paper presents an end-to-end deep graph message-passing network, LMSeg, designed to efficiently and accurately perform semantic segmentation on large-scale 3D landscape meshes. The proposed approach takes the barycentric dual graph of meshes as inputs and applies deep message-passing neural networks to hierarchically capture the geometric and spatial features from the barycentric graph structures and learn intricate semantic information from textured meshes. The hierarchical and local pooling of the barycentric graph, along with the effective geometry aggregation modules of LMSeg, enable fast inference and accurate segmentation of small-sized and irregular mesh objects in various complex landscapes. Extensive experiments on two benchmark datasets (natural and urban landscapes) demonstrate that LMSeg significantly outperforms existing learning-based segmentation methods in terms of object segmentation accuracy and computational efficiency. Furthermore, our method exhibits strong generalization capabilities across diverse landscapes and demonstrates robust resilience against varying mesh densities and landscape topologies.

翻译：大规模三维景观网格的语义分割对于多种地理空间应用至关重要，包括空间分析、目标对象的自动测绘与定位以及城市规划与发展。这需要一个高效且精确的三维感知系统来理解和分析真实世界环境。然而，由于三维景观网格数据集的复杂性和大规模性，传统的网格分割方法在精确分割小物体和保持计算效率方面面临挑战。本文提出了一种端到端的深度图消息传递网络LMSeg，旨在高效且精确地对大规模三维景观网格执行语义分割。所提方法以网格的重心对偶图作为输入，应用深度消息传递神经网络，从重心图结构中分层捕获几何与空间特征，并从带纹理的网格中学习复杂的语义信息。重心图的分层与局部池化操作，结合LMSeg有效的几何聚合模块，能够实现对各种复杂景观中尺寸小且不规则的网格对象进行快速推理与精确分割。在两个基准数据集（自然与城市景观）上进行的大量实验表明，LMSeg在物体分割精度和计算效率方面显著优于现有的基于学习的分割方法。此外，我们的方法在不同景观间展现出强大的泛化能力，并对变化的网格密度和景观拓扑结构表现出鲁棒的适应性。