View in EDS

Joint Detection and Parameters Regression of Detailed Windows based on Facade Textures via an Adaptive Soft Teacher.

Saved in:
Bibliographic Details
Title: Joint Detection and Parameters Regression of Detailed Windows based on Facade Textures via an Adaptive Soft Teacher.
Authors: Han Hu1,2, Chenwei Li1,2, Bo Xu1,2 xubo@swjtu.edu.cn, Min Chen1,2, Qing Zhu1,2, Zujie Han3, Xinwen Ning3, Xuesong Fu3
Source: Photogrammetric Engineering & Remote Sensing. Dec2025, Vol. 91 Issue 12, p763-775. 13p.
Abstract: The detailed and precise reconstruction of building facades with semantic information conforming to the level-of-detail protocol has drawn increasing attention in recent years. However, despite windows being a major component of building facades, current research often oversimplifies them in the modeling process, primarily focusing on their location and size. This study proposes a joint approach to simultaneously address window detection and detailed parametric modeling. All required window information, including type, location, and interior structure parameters, is obtained via an end-to-end network. This information is then consolidated into predefined window syntax accessible via the SketchUp Ruby application programming interface (API), resulting in the construction of detailed three-dimensional window models. To resolve the issue of training the network with limited labeled data, an adaptive threshold method based on Soft Teacher is proposed, leveraging the pseudolabel technique and consistency regularization to enhance detection precision. Experiments performed on multiple datasets demonstrate that the proposed methods achieve improved window-detection precision with reduced cell estimation errors compared with existing Faster R-CNN-based methods. The mean average precision and average precision at the intersection of union = 0.5 (AP50) metrics increased from 47.9% and 61.9% to 69.0% and 83.1%, respectively. The mean absolute error metric for cell estimation improved from 0.103 to 0.076. [ABSTRACT FROM AUTHOR]
Copyright of Photogrammetric Engineering & Remote Sensing is the property of ASPRS: The Imaging & Geospatial Information Society 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: 189377864
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Joint Detection and Parameters Regression of Detailed Windows based on Facade Textures via an Adaptive Soft Teacher.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Han+Hu%22">Han Hu</searchLink><relatesTo>1,2</relatesTo><br /><searchLink fieldCode="AR" term="%22Chenwei+Li%22">Chenwei Li</searchLink><relatesTo>1,2</relatesTo><br /><searchLink fieldCode="AR" term="%22Bo+Xu%22">Bo Xu</searchLink><relatesTo>1,2</relatesTo><i> xubo@swjtu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Min+Chen%22">Min Chen</searchLink><relatesTo>1,2</relatesTo><br /><searchLink fieldCode="AR" term="%22Qing+Zhu%22">Qing Zhu</searchLink><relatesTo>1,2</relatesTo><br /><searchLink fieldCode="AR" term="%22Zujie+Han%22">Zujie Han</searchLink><relatesTo>3</relatesTo><br /><searchLink fieldCode="AR" term="%22Xinwen+Ning%22">Xinwen Ning</searchLink><relatesTo>3</relatesTo><br /><searchLink fieldCode="AR" term="%22Xuesong+Fu%22">Xuesong Fu</searchLink><relatesTo>3</relatesTo>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Photogrammetric+Engineering+%26+Remote+Sensing%22">Photogrammetric Engineering & Remote Sensing</searchLink>. Dec2025, Vol. 91 Issue 12, p763-775. 13p.
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: The detailed and precise reconstruction of building facades with semantic information conforming to the level-of-detail protocol has drawn increasing attention in recent years. However, despite windows being a major component of building facades, current research often oversimplifies them in the modeling process, primarily focusing on their location and size. This study proposes a joint approach to simultaneously address window detection and detailed parametric modeling. All required window information, including type, location, and interior structure parameters, is obtained via an end-to-end network. This information is then consolidated into predefined window syntax accessible via the SketchUp Ruby application programming interface (API), resulting in the construction of detailed three-dimensional window models. To resolve the issue of training the network with limited labeled data, an adaptive threshold method based on Soft Teacher is proposed, leveraging the pseudolabel technique and consistency regularization to enhance detection precision. Experiments performed on multiple datasets demonstrate that the proposed methods achieve improved window-detection precision with reduced cell estimation errors compared with existing Faster R-CNN-based methods. The mean average precision and average precision at the intersection of union = 0.5 (AP50) metrics increased from 47.9% and 61.9% to 69.0% and 83.1%, respectively. The mean absolute error metric for cell estimation improved from 0.103 to 0.076. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Photogrammetric Engineering & Remote Sensing is the property of ASPRS: The Imaging & Geospatial Information Society 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=189377864
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.14358/PERS.25-00037R3
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 13
        StartPage: 763
    Titles:
      – TitleFull: Joint Detection and Parameters Regression of Detailed Windows based on Facade Textures via an Adaptive Soft Teacher.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Han Hu
      – PersonEntity:
          Name:
            NameFull: Chenwei Li
      – PersonEntity:
          Name:
            NameFull: Bo Xu
      – PersonEntity:
          Name:
            NameFull: Min Chen
      – PersonEntity:
          Name:
            NameFull: Qing Zhu
      – PersonEntity:
          Name:
            NameFull: Zujie Han
      – PersonEntity:
          Name:
            NameFull: Xinwen Ning
      – PersonEntity:
          Name:
            NameFull: Xuesong Fu
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 12
              Text: Dec2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 00991112
          Numbering:
            – Type: volume
              Value: 91
            – Type: issue
              Value: 12
          Titles:
            – TitleFull: Photogrammetric Engineering & Remote Sensing
              Type: main
ResultId 1