Repository logo

Infoscience

  • English
  • French
Log In
Logo EPFL, École polytechnique fédérale de Lausanne

Infoscience

  • English
  • French
Log In
  1. Home
  2. Academic and Research Output
  3. Journal articles
  4. Generating LOD3 building models from structure-from-motion and semantic segmentation
 
research article

Generating LOD3 building models from structure-from-motion and semantic segmentation

Pantoja-Rosero, B. G.  
•
Achanta, R.  
•
Kozinski, M.  
Show more
September 1, 2022
Automation In Construction

This paper describes a pipeline for automatically generating level of detail (LOD) models (digital twins), specifically LOD2 and LOD3, from free-standing buildings. Our approach combines structure from motion (SfM) with deep-learning-based segmentation techniques. Given multiple-view images of a building, we compute a three-dimensional (3D) planar abstraction (LOD2 model) of its point cloud using SfM techniques. To obtain LOD3 models, we use deep learning to perform semantic segmentation of the openings in the two-dimensional (2D) images. Unlike existing approaches, we do not rely on complex input, pre-defined 3D shapes or manual intervention. To demonstrate the robustness of our method, we show that it can generate 3D building shapes from a collection of building images with no further input. For evaluating reconstructions, we also propose two novel metrics. The first is a Euclidean-distance-based correlation of the 3D building model with the point cloud. The second involves re-projecting 3D model facades onto source photos to determine dice scores with respect to the ground-truth masks. Finally, we make the code, the image datasets, SfM outputs, and digital twins reported in this work publicly available in github.com/eesd-epfl/LOD3_buildings and doi.org/10.5281/zenodo.6651663. With this work we aim to contribute research in applications such as construction management, city planning, and mechanical analysis, among others.

  • Details
  • Metrics
Type
research article
DOI
10.1016/j.autcon.2022.104430
Web of Science ID

WOS:000833417000002

Author(s)
Pantoja-Rosero, B. G.  
Achanta, R.  
Kozinski, M.  
Fua, P.  
Perez-Cruz, F.  
Beyer, K.  
Date Issued

2022-09-01

Published in
Automation In Construction
Volume

141

Article Number

104430

Subjects

Construction & Building Technology

•

Engineering, Civil

•

Construction & Building Technology

•

Engineering

•

digital twin

•

lod models

•

deep learning

•

structure from motion

•

3d building models

•

masonry buildings

•

urban facades

Editorial or Peer reviewed

REVIEWED

Written at

EPFL

EPFL units
SDSC  
EESD  
Available on Infoscience
August 15, 2022
Use this identifier to reference this record
https://infoscience.epfl.ch/handle/20.500.14299/189977
Logo EPFL, École polytechnique fédérale de Lausanne
  • Contact
  • infoscience@epfl.ch

  • Follow us on Facebook
  • Follow us on Instagram
  • Follow us on LinkedIn
  • Follow us on X
  • Follow us on Youtube
AccessibilityLegal noticePrivacy policyCookie settingsEnd User AgreementGet helpFeedback

Infoscience is a service managed and provided by the Library and IT Services of EPFL. © EPFL, tous droits réservés