BIM Module for Deep Learning-driven parametric IFC reconstruction

The creation of Building Information Models (BIM) is driven by cutting-edge software applications, plug-ins, and APIs that constitute the backbone of BIM authoring tools. While free tools and APIs offer visualization and customization options, geometric modelling remains largely restricted to intera...

Full description

Saved in:
Bibliographic Details
Main Authors: O. Roman, M. Bassier, S. De Geyter, H. De Winter, E. M. Farella, F. Remondino
Format: Article
Language:English
Published: Copernicus Publications 2024-12-01
Series:The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Online Access:https://isprs-archives.copernicus.org/articles/XLVIII-2-W8-2024/403/2024/isprs-archives-XLVIII-2-W8-2024-403-2024.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850111125185626112
author O. Roman
O. Roman
M. Bassier
S. De Geyter
H. De Winter
E. M. Farella
F. Remondino
author_facet O. Roman
O. Roman
M. Bassier
S. De Geyter
H. De Winter
E. M. Farella
F. Remondino
author_sort O. Roman
collection DOAJ
description The creation of Building Information Models (BIM) is driven by cutting-edge software applications, plug-ins, and APIs that constitute the backbone of BIM authoring tools. While free tools and APIs offer visualization and customization options, geometric modelling remains largely restricted to interactive work and proprietary platforms, which sometimes limits flexibility and efficiency. There are still only a few comprehensive workflows that fully automate the reconstruction of building elements from reality-based surveyed data. This paper introduces an innovative reconstruction pipeline developed for the Scan-to-BIM Challenge at the CVPR 2024 Workshop, where it achieved second place in the competition. A deep learning (DL)-driven BIM Module for parametric IFC reconstruction is designed to accurately reconstruct both primary and secondary building elements within a BIM framework, starting from unstructured point cloud data captured via Terrestrial Laser Scanning (TLS). By leveraging DL techniques, particularly Convolutional Neural Networks (CNNs) and Transformers Networks (PTv3), our approach uses late fusion instance segmentation across both 2D and 3D modalities to accurately identify and reconstruct class-specific elements. The pipeline ultimately generates Industry Foundation Classes (IFC) elements, enhancing modelling accuracy, parameter estimation, and consistency in subsequent stages. Results highlight the pipeline’s strong performance on various datasets, underscoring the crucial role of DL in advancing Scan-to-BIM workflows.
format Article
id doaj-art-b3b3790dc74a47b092a9e4e006f2373a
institution OA Journals
issn 1682-1750
2194-9034
language English
publishDate 2024-12-01
publisher Copernicus Publications
record_format Article
series The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
spelling doaj-art-b3b3790dc74a47b092a9e4e006f2373a2025-08-20T02:37:41ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342024-12-01XLVIII-2-W8-202440341010.5194/isprs-archives-XLVIII-2-W8-2024-403-2024BIM Module for Deep Learning-driven parametric IFC reconstructionO. Roman0O. Roman1M. Bassier2S. De Geyter3H. De Winter4E. M. Farella5F. Remondino6Department Information Engineering and Computer Science (IECS), University of Trento, Trento, Italy3D Optical Metrology (3DOM) unit, Bruno Kessler Foundation (FBK), Trento, ItalyDept. of Civil Engineering, TC Construction - Geomatics, Faculty of Engineering Technology, KU Leuven, Ghent, BelgiumDept. of Civil Engineering, TC Construction - Geomatics, Faculty of Engineering Technology, KU Leuven, Ghent, BelgiumDept. of Civil Engineering, TC Construction - Geomatics, Faculty of Engineering Technology, KU Leuven, Ghent, Belgium3D Optical Metrology (3DOM) unit, Bruno Kessler Foundation (FBK), Trento, Italy3D Optical Metrology (3DOM) unit, Bruno Kessler Foundation (FBK), Trento, ItalyThe creation of Building Information Models (BIM) is driven by cutting-edge software applications, plug-ins, and APIs that constitute the backbone of BIM authoring tools. While free tools and APIs offer visualization and customization options, geometric modelling remains largely restricted to interactive work and proprietary platforms, which sometimes limits flexibility and efficiency. There are still only a few comprehensive workflows that fully automate the reconstruction of building elements from reality-based surveyed data. This paper introduces an innovative reconstruction pipeline developed for the Scan-to-BIM Challenge at the CVPR 2024 Workshop, where it achieved second place in the competition. A deep learning (DL)-driven BIM Module for parametric IFC reconstruction is designed to accurately reconstruct both primary and secondary building elements within a BIM framework, starting from unstructured point cloud data captured via Terrestrial Laser Scanning (TLS). By leveraging DL techniques, particularly Convolutional Neural Networks (CNNs) and Transformers Networks (PTv3), our approach uses late fusion instance segmentation across both 2D and 3D modalities to accurately identify and reconstruct class-specific elements. The pipeline ultimately generates Industry Foundation Classes (IFC) elements, enhancing modelling accuracy, parameter estimation, and consistency in subsequent stages. Results highlight the pipeline’s strong performance on various datasets, underscoring the crucial role of DL in advancing Scan-to-BIM workflows.https://isprs-archives.copernicus.org/articles/XLVIII-2-W8-2024/403/2024/isprs-archives-XLVIII-2-W8-2024-403-2024.pdf
spellingShingle O. Roman
O. Roman
M. Bassier
S. De Geyter
H. De Winter
E. M. Farella
F. Remondino
BIM Module for Deep Learning-driven parametric IFC reconstruction
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
title BIM Module for Deep Learning-driven parametric IFC reconstruction
title_full BIM Module for Deep Learning-driven parametric IFC reconstruction
title_fullStr BIM Module for Deep Learning-driven parametric IFC reconstruction
title_full_unstemmed BIM Module for Deep Learning-driven parametric IFC reconstruction
title_short BIM Module for Deep Learning-driven parametric IFC reconstruction
title_sort bim module for deep learning driven parametric ifc reconstruction
url https://isprs-archives.copernicus.org/articles/XLVIII-2-W8-2024/403/2024/isprs-archives-XLVIII-2-W8-2024-403-2024.pdf
work_keys_str_mv AT oroman bimmodulefordeeplearningdrivenparametricifcreconstruction
AT oroman bimmodulefordeeplearningdrivenparametricifcreconstruction
AT mbassier bimmodulefordeeplearningdrivenparametricifcreconstruction
AT sdegeyter bimmodulefordeeplearningdrivenparametricifcreconstruction
AT hdewinter bimmodulefordeeplearningdrivenparametricifcreconstruction
AT emfarella bimmodulefordeeplearningdrivenparametricifcreconstruction
AT fremondino bimmodulefordeeplearningdrivenparametricifcreconstruction