liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Semantic annotation of 3D point clouds via label transfer from BIM models for AEC applications
Linköping University, Department of Management and Engineering, Product Realisation. Linköping University, Faculty of Science & Engineering.ORCID iD: 0009-0001-0160-4899
Linköping University, Department of Electrical Engineering, Computer Vision. Linköping University, Faculty of Science & Engineering.ORCID iD: 0000-0002-5698-5983
Linköping University, Department of Management and Engineering, Product Realisation. Linköping University, Faculty of Science & Engineering.ORCID iD: 0000-0002-7210-0209
2026 (English)In: Results in Engineering (RINENG), ISSN 2590-1230, Vol. 30, article id 110796Article in journal (Refereed) Published
Abstract [en]

The lack of large, high-quality annotated datasets remains a fundamental bottleneck for 3D deep learning in architecture, engineering, and construction (AEC), where point-wise labeling of building-scale scans is costly and time-consuming. Many AEC workflows already produce Building Information Models (BIM) for design and documentation, providing an underutilized source of structured semantic information. We present a deterministic BIM-to-point-cloud label transfer pipeline that converts expert-authored BIM models into dense point-wise semantic annotations on real scans. Given a registered BIM-scan pair, object classes are propagated using FAISS-based nearest-neighbor search under explicit geometric tolerances, combined with vertical constraints and conflict filtering. The method enables scalable annotation without learning and serves as a tolerance-controlled measure of BIM-scan agreement. The approach is evaluated on the Stanford 3D Indoor Semantics Dataset (S3DIS) and two real-world buildings. For S3DIS, Areas 1 and 2 were reconstructed in BIM and used to relabel the original scans, enabling direct pointwise comparison without additional annotation. The pipeline is further demonstrated on a medieval castle (approximate to 8,000 m2) and a modern school building. On S3DIS Area 1, relabeling the same scan with a 25 mm tolerance yields high agreement with reference annotations (mean F1 = 88.54%) and 72.34% modeled-label coverage. Area 2 serves as a robustness study, with coverage remaining within five percentage points across tolerances. The method provides a scalable way to generate supervision directly on real scans when BIM-scan pairs are available and exposes unclassified regions as a QA signal for BIM incompleteness, misalignment, and geometric ambiguity. Results represent label agreement on the same scan rather than independent semantic accuracy.

Place, publisher, year, edition, pages
ELSEVIER , 2026. Vol. 30, article id 110796
Keywords [en]
3D point cloud; Semantic segmentation; BIM; Label transfer; Scan-to-BIM; AEC; FAISS
National Category
Computer Sciences Computer Vision and Learning Systems
Identifiers
URN: urn:nbn:se:liu:diva-224581DOI: 10.1016/j.rineng.2026.110796ISI: 001777534900001Scopus ID: 2-s2.0-105039482636OAI: oai:DiVA.org:liu-224581DiVA, id: diva2:2068990
Available from: 2026-06-10 Created: 2026-06-10 Last updated: 2026-08-31

Open Access in DiVA

fulltext(17465 kB)73 downloads
File information
File name FULLTEXT01.pdfFile size 17465 kBChecksum SHA-512
9b0ae847a6a14da7484e830159cbe229d01c84800724d52959dccde809dae963f1404aaf7fe2afcca3392c27c53c7cf8b0f68c0e214595149e5874ee1a768e56
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopus

Search in DiVA

By author/editor
Hoffstedt, CarlForssén, Per-ErikWiberg, Anton
By organisation
Product RealisationFaculty of Science & EngineeringComputer Vision
In the same journal
Results in Engineering (RINENG)
Computer SciencesComputer Vision and Learning Systems

Search outside of DiVA

GoogleGoogle Scholar
Total: 73 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 67 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf