Three-dimensional (3D) building models play a crucial role in shaping digital twin cities and enabling a wide range of urban applications. However, one challenge remains in obtaining a compact representation of buildings from remote sensing. This paper introduces a novel deep learning approach to reconstructing polygonal building models from LiDAR point clouds. Our method leverages a graph neural network to assemble the polyhedra generated through space partitioning, thereby formulating building surface reconstruction as a graph node classification problem. To facilitate network training, we construct a synthetic dataset by simulating aerial LiDAR point clouds on building surface meshes. Experimental results demonstrate the effectiveness of our method, achieving a polyhedral classification accuracy of 96.4%. Moreover, our approach offers high efficiency and interpretability through end-to-end optimization.
Paper
Full text
Polyhedron-Based Graph Neural Network for Compact Building Model Reconstruction
Semantic Scholar · Computer Science · 2023
Abstract
Three-dimensional (3D) building models play a crucial role in shaping digital twin cities and enabling a wide range of urban applications. However, one challenge remains in obtaining a compact representation of buildings from remote sensing. This paper introduces a novel deep learning approach to reconstructing polygonal building models from LiDAR point clouds. Our method leverages a graph neural network to assemble the polyhedra generated through space partitioning, thereby formulating building surface reconstruction as a graph node classification problem. To facilitate network training, we construct a synthetic dataset by simulating aerial LiDAR point clouds on building surface meshes. Experimental results demonstrate the effectiveness of our method, achieving a polyhedral classification accuracy of 96.4%. Moreover, our approach offers high efficiency and interpretability through end-to-end optimization.