Building clustering is a key problem that needs to be solved in the realization of the automatic synthesis of large-scale maps. The selection of different feature and spatial distance calculation methods has a great impact on the clustering results, and the need to manually select appropriate feature and distance metrics leads to the problem of not being able to fully consider the complexity and diversity of buildings. In this paper, we propose a multi-scale clustering method for buildings that takes visual perception into account using the Gestalt principle to simulate how humans classify buildings through visual perception. Moreover, by analyzing the spatial features and texture attributes of buildings, a visual distance is designed to be used as a condition for building classification to assess the similarity between buildings, solving the complexity of manually selecting feature vectors and spatial distances and realizing the adaptive selection of features. Through experimental validation at different scales (macro, meso and micro), the present method is able to achieve the accurate clustering of buildings, and a frequency threshold of 91% is found, which is able to determine the optimal clustering results. The experimental results show that the proposed method can not only fully consider the complexity and diversity of buildings but also effectively support the understanding and analysis of urban spatial structure and provide a scientific decision-making basis for urban planning and management.

Building clustering is a key challenge in cartographic generalization, where the goal is to group spatially related buildings into semantically coherent clusters while preserving the true distribution patterns of urban structures. Existing methods often rely on either spatial distance or building feature similarity alone, leading to clusters that sacrifice either accuracy or spatial continuity. Moreover, most deep learning-based approaches, including graph attention networks (GATs), fail to explicitly incorporate spatial distance constraints and typically restrict message passing to first-order neighborhoods, limiting their ability to capture long-range structural dependencies. To address these issues, this paper proposes LA-GATs, a multi-feature constrained and spatially adaptive building clustering network. First, a Delaunay triangulation is constructed based on nearest-neighbor distances to represent spatial topology, and a heterogeneous feature matrix is built by integrating architectural spatial features, including compactness, orientation, color, and height. Then, a spatial distance-constrained attention mechanism is designed, where attention weights are adjusted using a distance decay function to enhance local spatial correlation. A second-order neighborhood aggregation strategy is further introduced to extend message propagation and mitigate the impact of triangulation errors. Finally, spectral clustering is performed on the learned similarity matrix. Comprehensive experimental validation on real-world datasets from Xi’an and Beijing, showing that LA-GATs outperforms existing clustering methods in both compactness, silhouette coefficient and adjusted rand index, with up to about 21% improvement in residential clustering accuracy.

The rendering of urban 3D scenes involves a large number of models. In order to render scenes more efficiently, the main solution is to build a level of detail model (LOD). This may have the problem of building fragmentation, while relying on building a level of detail model (LOD) alone cannot meet the accuracy and fluency of large‐scale scene visualisation. Effective and reasonable data organisation has important research significance for the authors to achieve accurate and fast rendering of scenes. Therefore, the authors propose a large‐scale city model data organisation method considering building distribution to solve the above problems. This method first classifies the buildings in the scene at macro‐, meso‐ and microscales and records the classification using R‐trees. Then an adaptive quadtree is used to construct the data index of the city model. Finally, the data organisation of the large‐scale 3D city model is achieved by using the information of each node of the R‐tree as a constraint and combining with the adaptive quadtree. The results show that the method not only ensures the integrity of the user's area of interest but also can improve the efficiency of 3D scene construction.