We present PolyGNN, a polyhedron-based graph neural network for 3D building reconstruction from point clouds. PolyGNN learns to assemble primitives obtained by polyhedral decomposition via graph node classification, achieving a watertight, compact, and weakly semantic reconstruction. To effectively represent arbitrary-shaped polyhedra in the neural network, we propose three different sampling strategies to select representative points as polyhedron-wise queries, enabling efficient occupancy inference. Furthermore, we incorporate the inter-polyhedron adjacency to enhance the classification of the graph nodes. We also observe that existing city-building models are abstractions of the underlying instances. To address this abstraction gap and provide a fair evaluation of the proposed method, we develop our method on a large-scale synthetic dataset covering 500k+ buildings with well-defined ground truths of polyhedral class labels. We further conduct a transferability analysis across cities and on real-world point clouds. Both qualitative and quantitative results demonstrate the effectiveness of our method, particularly its efficiency for large-scale reconstructions. The source code and data of our work are available at https://github.com/chenzhaiyu/polygnn.

翻译：我们提出PolyGNN，一种基于多面体的图神经网络，用于从点云实现三维建筑重建。PolyGNN通过学习通过图节点分类来组装多面体分解得到的基元，从而实现水密、紧凑且弱语义的重建。为有效表示神经网络中任意形状的多面体，我们提出三种不同的采样策略，选择代表性点作为多面体级别的查询，从而实现高效的占用率推断。此外，我们引入多面体间的邻接关系以增强图节点的分类。我们还观察到，现有的城市建筑模型是对底层实例的抽象。为弥合这一抽象差距并对所提方法进行公平评估，我们在大规模合成数据集上开发方法，该数据集涵盖超过50万栋建筑，并具有定义良好的多面体类别标签真值。我们进一步跨城市以及在实际点云上进行了可迁移性分析。定性和定量结果均证明了我们方法的有效性，尤其在大规模重建中的高效性。我们的源代码和数据可在https://github.com/chenzhaiyu/polygnn获取。