A Method for 3D Building Individualization Integrating SAMPolyBuild and Multiple Spatial-Geometric Features

Cao, Lianshuai; Cheng, Yi; Zhang, Zheng; Zhu, Ge; Ma, Kunyang; Xu, Xinyue

doi:10.3390/s26030999

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

A Method for 3D Building Individualization Integrating SAMPolyBuild and Multiple Spatial-Geometric Features

by

Lianshuai Cao

,

Yi Cheng

^*,

Zheng Zhang

,

Ge Zhu

,

Kunyang Ma

and

Xinyue Xu

Institute of Geographic Spatial Information, PLA Information Engineering University, Zhengzhou 450001, China

^*

Author to whom correspondence should be addressed.

Sensors 2026, 26(3), 999; https://doi.org/10.3390/s26030999

Submission received: 5 November 2025 / Revised: 12 January 2026 / Accepted: 13 January 2026 / Published: 3 February 2026

(This article belongs to the Special Issue Remote Sensing, Geophysics and GIS)

Download Versions Notes

Abstract

Individualization of buildings is one of the key issues in the establishment of three-dimensional (3D) building models. Most existing individualization methods rely on inefficient manual separation, while deep learning approaches require extensive pre-training and are highly influenced by the spatial structure of the models. To address these issues, this paper proposes a novel method for 3D building individualization that integrates SAMPolyBuild with multiple spatial-geometric features. Leveraging the zero-shot learning capability of SAMPolyBuild, the method first performs coarse extraction of individual buildings, then refines the extraction accuracy using multiple spatial-geometric features. Innovatively, two statistical parameters—Jensen-Shannon Divergence and Earth Mover’s Distance—are introduced into the building identification process. To validate the feasibility and effectiveness of the proposed method, experiments were conducted on the Semantic Urban Meshes (SUM) dataset. The results demonstrate that the method can effectively extract individual building models from urban oblique photogrammetric 3D models, achieving an F1-score of approximately 0.83 for buildings with typical spatial structures.

Keywords: 3D building individualization; SAMPolyBuild; spatial-geometric features; Jensen-Shannon divergence; Earth Mover’s Distance

Share and Cite

MDPI and ACS Style

Cao, L.; Cheng, Y.; Zhang, Z.; Zhu, G.; Ma, K.; Xu, X. A Method for 3D Building Individualization Integrating SAMPolyBuild and Multiple Spatial-Geometric Features. Sensors 2026, 26, 999. https://doi.org/10.3390/s26030999

AMA Style

Cao L, Cheng Y, Zhang Z, Zhu G, Ma K, Xu X. A Method for 3D Building Individualization Integrating SAMPolyBuild and Multiple Spatial-Geometric Features. Sensors. 2026; 26(3):999. https://doi.org/10.3390/s26030999

Chicago/Turabian Style

Cao, Lianshuai, Yi Cheng, Zheng Zhang, Ge Zhu, Kunyang Ma, and Xinyue Xu. 2026. "A Method for 3D Building Individualization Integrating SAMPolyBuild and Multiple Spatial-Geometric Features" Sensors 26, no. 3: 999. https://doi.org/10.3390/s26030999

APA Style

Cao, L., Cheng, Y., Zhang, Z., Zhu, G., Ma, K., & Xu, X. (2026). A Method for 3D Building Individualization Integrating SAMPolyBuild and Multiple Spatial-Geometric Features. Sensors, 26(3), 999. https://doi.org/10.3390/s26030999

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Article metric data becomes available approximately 24 hours after publication online.

Article Menu

A Method for 3D Building Individualization Integrating SAMPolyBuild and Multiple Spatial-Geometric Features

Abstract

Share and Cite

Article Metrics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI