View in EDS

Automating graph-based geometric digital model generation for building digital twin applications from point cloud and image data.

Saved in:
Bibliographic Details
Title: Automating graph-based geometric digital model generation for building digital twin applications from point cloud and image data.
Authors: Wang, Mudan1 (AUTHOR), Pan, Yuandong1,2 (AUTHOR) ydpan@stanford.edu, Lu, Linjun1 (AUTHOR), Pärn, Erika1,3 (AUTHOR), Liu, Junying4 (AUTHOR), Brilakis, Ioannis1 (AUTHOR)
Source: Building & Environment. Mar2026, Vol. 291, pN.PAG-N.PAG. 1p.
Subject Terms: *Built environment, Digital twin, Point cloud, Image processing, Deep learning, Representations of graphs, Space perception
Abstract: Creating geometric digital twins of buildings remains a labor-intensive process, often limited to the reconstruction of structural elements. Non-structural components and their spatial relationships with indoor spaces are rarely integrated into a unified digital representation. This paper proposes a novel semi-automated method for generating graph-based geometric digital models for digital twins from 3D point cloud and image data. The approach extracts spatial and object information from these data based on deep learning methods. Multiple 2D detectors are trained on different public and customized datasets to broaden class coverage, and their predictions are mapped into a unified label space, fused per view, projected into 3D space, and merged into object instances that correspond to the same physical element. A new graph schema is then introduced to represent indoor spaces and elements, capturing both hierarchical and spatial relationships. The schema links each entity to its geometric representation and supports temporal snapshots. All extracted information is structured and stored in a graph database using the proposed schema. The method is validated on two real-world datasets, one residential house and one institutional facility, capturing a broader and more differentiated range of object classes across different building types and topologies. The promising results indicate that the method has the potential to be generalized to a wider range of buildings. [Display omitted] • Propose a novel method to create graph-based representations of indoor building environments from point cloud and image data. • Identify room spaces and detect non-structural elements such as furniture via multi-detector, multi-view fusion. • Design a graph schema that captures hierarchical spatial relationships, links to geometric data with temporal snapshots. • Represent extracted elements and their relationships using graph structures for efficient data storage and analysis. • Demonstrate the method on real-world point cloud data for validation. [ABSTRACT FROM AUTHOR]
Copyright of Building & Environment is the property of Pergamon Press - An Imprint of Elsevier Science and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: GreenFILE
Description
Abstract:Creating geometric digital twins of buildings remains a labor-intensive process, often limited to the reconstruction of structural elements. Non-structural components and their spatial relationships with indoor spaces are rarely integrated into a unified digital representation. This paper proposes a novel semi-automated method for generating graph-based geometric digital models for digital twins from 3D point cloud and image data. The approach extracts spatial and object information from these data based on deep learning methods. Multiple 2D detectors are trained on different public and customized datasets to broaden class coverage, and their predictions are mapped into a unified label space, fused per view, projected into 3D space, and merged into object instances that correspond to the same physical element. A new graph schema is then introduced to represent indoor spaces and elements, capturing both hierarchical and spatial relationships. The schema links each entity to its geometric representation and supports temporal snapshots. All extracted information is structured and stored in a graph database using the proposed schema. The method is validated on two real-world datasets, one residential house and one institutional facility, capturing a broader and more differentiated range of object classes across different building types and topologies. The promising results indicate that the method has the potential to be generalized to a wider range of buildings. [Display omitted] • Propose a novel method to create graph-based representations of indoor building environments from point cloud and image data. • Identify room spaces and detect non-structural elements such as furniture via multi-detector, multi-view fusion. • Design a graph schema that captures hierarchical spatial relationships, links to geometric data with temporal snapshots. • Represent extracted elements and their relationships using graph structures for efficient data storage and analysis. • Demonstrate the method on real-world point cloud data for validation. [ABSTRACT FROM AUTHOR]
ISSN:03601323
DOI:10.1016/j.buildenv.2026.114211