View in EDS HTML Full Text PDF Full Text

Three-Dimensional Instance Segmentation of Rooms in Indoor Building Point Clouds Using Mask3D.

Saved in:
Bibliographic Details
Title: Three-Dimensional Instance Segmentation of Rooms in Indoor Building Point Clouds Using Mask3D.
Authors: Brunklaus, Michael1,2 (AUTHOR) michael.brunklaus@inatech.uni-freiburg.de, Kellner, Maximilian1,2 (AUTHOR), Reiterer, Alexander1,2 (AUTHOR)
Source: Remote Sensing. Apr2025, Vol. 17 Issue 7, p1124. 27p.
Subjects: Orthographic projection, Building repair, Graphical projection, Point cloud, Construction industry, Deep learning
Abstract: While most recent work in room instance segmentation relies on orthographic top-down projections of 3D point clouds to 2D density maps, leading to information loss of one dimension, 3D instance segmentation methods based on deep learning were rarely considered. We explore the potential of the general 3D instance segmentation deep learning model Mask3D for room instance segmentation in indoor building point clouds. We show that Mask3D generates meaningful predictions for multi-floor scenes. After hyperparameter optimization, Mask3D outperforms the current state-of-the-art method RoomFormer evaluated in 3D on the synthetic Structured3D dataset. We provide generalization results of Mask3D trained on Structured3D to the real-world S3DIS and Matterport3D datasets, showing a domain gap. Fine-tuning improves the results. In contrast to related work in room instance segmentation, we employ the more expressive mean average precision (mAP) metric, and we propose the more intuitive successfully detected rooms (SDR) metric, which is an absolute recall measure. Our results indicate potential for the digitization of the construction industry. [ABSTRACT FROM AUTHOR]
Copyright of Remote Sensing is the property of MDPI 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: Engineering Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 184440602
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Three-Dimensional Instance Segmentation of Rooms in Indoor Building Point Clouds Using Mask3D.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Brunklaus%2C+Michael%22">Brunklaus, Michael</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> michael.brunklaus@inatech.uni-freiburg.de</i><br /><searchLink fieldCode="AR" term="%22Kellner%2C+Maximilian%22">Kellner, Maximilian</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Reiterer%2C+Alexander%22">Reiterer, Alexander</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Remote+Sensing%22">Remote Sensing</searchLink>. Apr2025, Vol. 17 Issue 7, p1124. 27p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Orthographic+projection%22">Orthographic projection</searchLink><br /><searchLink fieldCode="DE" term="%22Building+repair%22">Building repair</searchLink><br /><searchLink fieldCode="DE" term="%22Graphical+projection%22">Graphical projection</searchLink><br /><searchLink fieldCode="DE" term="%22Point+cloud%22">Point cloud</searchLink><br /><searchLink fieldCode="DE" term="%22Construction+industry%22">Construction industry</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: While most recent work in room instance segmentation relies on orthographic top-down projections of 3D point clouds to 2D density maps, leading to information loss of one dimension, 3D instance segmentation methods based on deep learning were rarely considered. We explore the potential of the general 3D instance segmentation deep learning model Mask3D for room instance segmentation in indoor building point clouds. We show that Mask3D generates meaningful predictions for multi-floor scenes. After hyperparameter optimization, Mask3D outperforms the current state-of-the-art method RoomFormer evaluated in 3D on the synthetic Structured3D dataset. We provide generalization results of Mask3D trained on Structured3D to the real-world S3DIS and Matterport3D datasets, showing a domain gap. Fine-tuning improves the results. In contrast to related work in room instance segmentation, we employ the more expressive mean average precision (mAP) metric, and we propose the more intuitive successfully detected rooms (SDR) metric, which is an absolute recall measure. Our results indicate potential for the digitization of the construction industry. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Remote Sensing is the property of MDPI 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.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=184440602
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3390/rs17071124
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 27
        StartPage: 1124
    Subjects:
      – SubjectFull: Orthographic projection
        Type: general
      – SubjectFull: Building repair
        Type: general
      – SubjectFull: Graphical projection
        Type: general
      – SubjectFull: Point cloud
        Type: general
      – SubjectFull: Construction industry
        Type: general
      – SubjectFull: Deep learning
        Type: general
    Titles:
      – TitleFull: Three-Dimensional Instance Segmentation of Rooms in Indoor Building Point Clouds Using Mask3D.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Brunklaus, Michael
      – PersonEntity:
          Name:
            NameFull: Kellner, Maximilian
      – PersonEntity:
          Name:
            NameFull: Reiterer, Alexander
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 04
              Text: Apr2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 20724292
          Numbering:
            – Type: volume
              Value: 17
            – Type: issue
              Value: 7
          Titles:
            – TitleFull: Remote Sensing
              Type: main
ResultId 1