View in EDS

Impact of color and mixing proportion of synthetic point clouds on semantic segmentation.

Saved in:
Bibliographic Details
Title: Impact of color and mixing proportion of synthetic point clouds on semantic segmentation.
Authors: Zhou, Shaojie1,2 (AUTHOR), Lin, Jia-Rui1,2 (AUTHOR) lin611@tsinghua.edu.cn, Pan, Peng1,2 (AUTHOR), Pan, Yuandong3 (AUTHOR), Brilakis, Ioannis3 (AUTHOR)
Source: Automation in Construction. Mar2025, Vol. 171, pN.PAG-N.PAG. 1p.
Subjects: Point cloud, Deep learning, Built environment, Color, Scarcity
Abstract: Deep learning (DL)-based point cloud segmentation is essential for understanding built environment. Despite synthetic point clouds (SPC) having the potential to compensate for data shortage, how synthetic color and mixing proportion impact DL-based segmentation remains a long-standing question. Therefore, this paper addresses this question with extensive experiments by introducing: 1) method to generate SPC with real colors and uniform colors from BIM, and 2) enhanced benchmarks for better performance evaluation. Experiments on DL models including PointNet, PointNet++, and DGCNN show that model performance on SPC with real colors outperforms that on SPC with uniform colors by 8.2 % + on both OA and mIoU. Furthermore, a higher than 70 % mixing proportion of SPC usually leads to better performance. And SPC can replace real ones to train a DL model for detecting large and flat building elements. Overall, this paper unveils the performance-improving mechanism of SPC and brings new insights to boost SPC's value. • A framework to generate synthetic point clouds based on BIM. • Enhanced benchmarks for better performance evaluation • A synthetic dataset with real color outperforms that with uniform color by 8.2 % +. • A higher than 70 % mixing proportion of synthetic data usually leads to better performance. • Synthetic point clouds can replace real ones for detecting large and flat elements. [ABSTRACT FROM AUTHOR]
Copyright of Automation in Construction is the property of Elsevier B.V. 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
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 183034487
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Impact of color and mixing proportion of synthetic point clouds on semantic segmentation.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Zhou%2C+Shaojie%22">Zhou, Shaojie</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Lin%2C+Jia-Rui%22">Lin, Jia-Rui</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> lin611@tsinghua.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Pan%2C+Peng%22">Pan, Peng</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Pan%2C+Yuandong%22">Pan, Yuandong</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Brilakis%2C+Ioannis%22">Brilakis, Ioannis</searchLink><relatesTo>3</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Automation+in+Construction%22">Automation in Construction</searchLink>. Mar2025, Vol. 171, pN.PAG-N.PAG. 1p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Point+cloud%22">Point cloud</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Built+environment%22">Built environment</searchLink><br /><searchLink fieldCode="DE" term="%22Color%22">Color</searchLink><br /><searchLink fieldCode="DE" term="%22Scarcity%22">Scarcity</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Deep learning (DL)-based point cloud segmentation is essential for understanding built environment. Despite synthetic point clouds (SPC) having the potential to compensate for data shortage, how synthetic color and mixing proportion impact DL-based segmentation remains a long-standing question. Therefore, this paper addresses this question with extensive experiments by introducing: 1) method to generate SPC with real colors and uniform colors from BIM, and 2) enhanced benchmarks for better performance evaluation. Experiments on DL models including PointNet, PointNet++, and DGCNN show that model performance on SPC with real colors outperforms that on SPC with uniform colors by 8.2 % + on both OA and mIoU. Furthermore, a higher than 70 % mixing proportion of SPC usually leads to better performance. And SPC can replace real ones to train a DL model for detecting large and flat building elements. Overall, this paper unveils the performance-improving mechanism of SPC and brings new insights to boost SPC's value. • A framework to generate synthetic point clouds based on BIM. • Enhanced benchmarks for better performance evaluation • A synthetic dataset with real color outperforms that with uniform color by 8.2 % +. • A higher than 70 % mixing proportion of synthetic data usually leads to better performance. • Synthetic point clouds can replace real ones for detecting large and flat elements. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Automation in Construction is the property of Elsevier B.V. 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=183034487
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1016/j.autcon.2025.105963
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 1
        StartPage: N.PAG
    Subjects:
      – SubjectFull: Point cloud
        Type: general
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Built environment
        Type: general
      – SubjectFull: Color
        Type: general
      – SubjectFull: Scarcity
        Type: general
    Titles:
      – TitleFull: Impact of color and mixing proportion of synthetic point clouds on semantic segmentation.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Zhou, Shaojie
      – PersonEntity:
          Name:
            NameFull: Lin, Jia-Rui
      – PersonEntity:
          Name:
            NameFull: Pan, Peng
      – PersonEntity:
          Name:
            NameFull: Pan, Yuandong
      – PersonEntity:
          Name:
            NameFull: Brilakis, Ioannis
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 03
              Text: Mar2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 09265805
          Numbering:
            – Type: volume
              Value: 171
          Titles:
            – TitleFull: Automation in Construction
              Type: main
ResultId 1