View in EDS PDF Full Text

Attention Feature Map Guided Self-Supervised Monocular Visual Odometry.

Saved in:
Bibliographic Details
Title: Attention Feature Map Guided Self-Supervised Monocular Visual Odometry.
Authors: Nan, Bingfei1,2 nanbf@tdmarco.com
Source: Journal of Imaging Science & Technology. Nov/Dec2025, Vol. 69 Issue 6, p1-8. 8p.
Subjects: Visual odometry, Attention, Trajectory measurements, Depth maps (Digital image processing), Machine learning, Measurement errors
Abstract: This paper presents a self-supervised monocular visual odometry (VO) method guided by attention feature maps, aimed at effectively mitigating the impact of redundant pixels during network training. Existing self-supervised VO methods typically treat all pixels equally when computing photometric error, which can lead to increased sensitivity to noise from irrelevant pixels and, consequently, training errors. To address this issue, the authors adopt a soft-attention mechanism to generate attention feature maps that allow the model to focus on more relevant pixels while downweighting the influence of disruptive ones. This approach enhances the robustness and accuracy of depth estimation and pose tracking. The proposed method achieves competitive results on the KITTI dataset, with Sequences 09 and 10 demonstrating relative rotation errors of 0.022 and 0.032 and relative translation errors of 5.56 and 7.29, respectively. [ABSTRACT FROM AUTHOR]
Copyright of Journal of Imaging Science & Technology is the property of International Society for Imaging Science & Technology 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 Links:
  – Type: pdflink
Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 192458518
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Attention Feature Map Guided Self-Supervised Monocular Visual Odometry.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Nan%2C+Bingfei%22">Nan, Bingfei</searchLink><relatesTo>1,2</relatesTo><i> nanbf@tdmarco.com</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Journal+of+Imaging+Science+%26+Technology%22">Journal of Imaging Science & Technology</searchLink>. Nov/Dec2025, Vol. 69 Issue 6, p1-8. 8p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Visual+odometry%22">Visual odometry</searchLink><br /><searchLink fieldCode="DE" term="%22Attention%22">Attention</searchLink><br /><searchLink fieldCode="DE" term="%22Trajectory+measurements%22">Trajectory measurements</searchLink><br /><searchLink fieldCode="DE" term="%22Depth+maps+%28Digital+image+processing%29%22">Depth maps (Digital image processing)</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Measurement+errors%22">Measurement errors</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: This paper presents a self-supervised monocular visual odometry (VO) method guided by attention feature maps, aimed at effectively mitigating the impact of redundant pixels during network training. Existing self-supervised VO methods typically treat all pixels equally when computing photometric error, which can lead to increased sensitivity to noise from irrelevant pixels and, consequently, training errors. To address this issue, the authors adopt a soft-attention mechanism to generate attention feature maps that allow the model to focus on more relevant pixels while downweighting the influence of disruptive ones. This approach enhances the robustness and accuracy of depth estimation and pose tracking. The proposed method achieves competitive results on the KITTI dataset, with Sequences 09 and 10 demonstrating relative rotation errors of 0.022 and 0.032 and relative translation errors of 5.56 and 7.29, respectively. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Journal of Imaging Science & Technology is the property of International Society for Imaging Science & Technology 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=192458518
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.2352/J.ImagingSci.Technol.2025.69.6.060403
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 8
        StartPage: 1
    Subjects:
      – SubjectFull: Visual odometry
        Type: general
      – SubjectFull: Attention
        Type: general
      – SubjectFull: Trajectory measurements
        Type: general
      – SubjectFull: Depth maps (Digital image processing)
        Type: general
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Measurement errors
        Type: general
    Titles:
      – TitleFull: Attention Feature Map Guided Self-Supervised Monocular Visual Odometry.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Nan, Bingfei
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 11
              Text: Nov/Dec2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 10623701
          Numbering:
            – Type: volume
              Value: 69
            – Type: issue
              Value: 6
          Titles:
            – TitleFull: Journal of Imaging Science & Technology
              Type: main
ResultId 1