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 and compact reconstruction. To effectively represent arbitrary-shaped polyhedra in the neural network, we propose a skeleton-based sampling strategy to generate polyhedron-wise queries. These queries are then incorporated with inter-polyhedron adjacency to enhance the classification. PolyGNN is end-to-end optimizable and is designed to accommodate variable-size input points, polyhedra, and queries with an index-driven batching technique. To address the abstraction gap between existing city-building models and the underlying instances, and provide a fair evaluation of the proposed method, we develop our method on a large-scale synthetic dataset with well-defined ground truths of polyhedral 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 are available at https://github.com/chenzhaiyu/polygnn.

中文翻译：

---

PolyGNN：基于多面体的图形神经网络，用于从点云进行 3D 建筑重建


我们介绍了 PolyGNN，这是一种基于多面体的图神经网络，用于从点云进行 3D 建筑重建。PolyGNN 学习通过图节点分类组装多面体分解得到的基元，实现水密紧凑的重建。为了在神经网络中有效地表示任意形状的多面体，我们提出了一种基于骨架的采样策略来生成多面体查询。然后将这些查询与多面体间邻接相结合，以增强分类。PolyGNN 是端到端可优化的，旨在通过索引驱动的批处理技术容纳可变大小的输入点、多面体和查询。为了解决现有城市建设模型和底层实例之间的抽象差距，并对所提出的方法进行公平的评估，我们在具有定义明确的多面体标签基本事实的大规模合成数据集上开发了我们的方法。我们进一步对城市和现实世界的点云进行可转移性分析。定性和定量结果都证明了我们方法的有效性，特别是它对大规模重建的效率。源代码和数据可在 https://github.com/chenzhaiyu/polygnn 上获得。