View in EDS HTML Full Text PDF Full Text

MagneticPillars++: Efficient LiDAR Odometry Via Deep Frame-To-Keyframe Point Cloud Registration.

Saved in:
Bibliographic Details
Title: MagneticPillars++: Efficient LiDAR Odometry Via Deep Frame-To-Keyframe Point Cloud Registration.
Authors: Fischer, Kai1,2 (AUTHOR) kai.fischer@valeo.com, Simon, Martin2 (AUTHOR), Milz, Stefan1,3 (AUTHOR), Mäder, Patrick1 (AUTHOR) patrick.maeder@tu-ilmenau.de
Source: Applied Artificial Intelligence. Dec2025, Vol. 39 Issue 1, p1-40. 40p.
Subjects: LIDAR, Visual odometry, Signal processing, Point cloud
Abstract: Downstream applications for point cloud registration, like LiDAR Odometry, often conduct Iterative Closest Points (ICP) in the initial frame-to-frame matching and/or subsequent map refinement. However, due to its distance-based processing nature, ICP relies on an accurate pose initialization while implicating increased computational complexity with a growing number of points. To meet specific runtime requirements, methods often apply the extensive mapping step at low frequencies, e.g. every 10 frames, which in turn leads to increased noise on the calculated trajectory. To tackle the discrepancy between runtime and accuracy, we present MagneticPillars++, an extension of our previous point cloud registration approach optimized for LiDAR Odometry, introducing novel intermediate cell correspondence filtering and accelerated match normalization. Furthermore, we propose a frame-to-keyframe matching technique replacing the simple frame-to-frame matching within a LiDAR Odometry pipeline. This can tremendously reduce noise without the need for expensive ICP corrections. We conduct extensive experiments for various tasks like point cloud registration, LiDAR Odometry, and loop closure estimation, demonstrating the versatility of our approach, where we are able to outperform state-of-the-art approaches in terms of accuracy and runtime, resulting in residual translation and rotation errors of up to 4.7 cm and 0.231 with an average runtime of. [ABSTRACT FROM AUTHOR]
Copyright of Applied Artificial Intelligence is the property of Taylor & Francis Ltd 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: 189934080
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: MagneticPillars++: Efficient LiDAR Odometry Via Deep Frame-To-Keyframe Point Cloud Registration.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Fischer%2C+Kai%22">Fischer, Kai</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> kai.fischer@valeo.com</i><br /><searchLink fieldCode="AR" term="%22Simon%2C+Martin%22">Simon, Martin</searchLink><relatesTo>2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Milz%2C+Stefan%22">Milz, Stefan</searchLink><relatesTo>1,3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Mäder%2C+Patrick%22">Mäder, Patrick</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> patrick.maeder@tu-ilmenau.de</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Applied+Artificial+Intelligence%22">Applied Artificial Intelligence</searchLink>. Dec2025, Vol. 39 Issue 1, p1-40. 40p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22LIDAR%22">LIDAR</searchLink><br /><searchLink fieldCode="DE" term="%22Visual+odometry%22">Visual odometry</searchLink><br /><searchLink fieldCode="DE" term="%22Signal+processing%22">Signal processing</searchLink><br /><searchLink fieldCode="DE" term="%22Point+cloud%22">Point cloud</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Downstream applications for point cloud registration, like LiDAR Odometry, often conduct Iterative Closest Points (ICP) in the initial frame-to-frame matching and/or subsequent map refinement. However, due to its distance-based processing nature, ICP relies on an accurate pose initialization while implicating increased computational complexity with a growing number of points. To meet specific runtime requirements, methods often apply the extensive mapping step at low frequencies, e.g. every 10 frames, which in turn leads to increased noise on the calculated trajectory. To tackle the discrepancy between runtime and accuracy, we present MagneticPillars++, an extension of our previous point cloud registration approach optimized for LiDAR Odometry, introducing novel intermediate cell correspondence filtering and accelerated match normalization. Furthermore, we propose a frame-to-keyframe matching technique replacing the simple frame-to-frame matching within a LiDAR Odometry pipeline. This can tremendously reduce noise without the need for expensive ICP corrections. We conduct extensive experiments for various tasks like point cloud registration, LiDAR Odometry, and loop closure estimation, demonstrating the versatility of our approach, where we are able to outperform state-of-the-art approaches in terms of accuracy and runtime, resulting in residual translation and rotation errors of up to 4.7 cm and 0.231 with an average runtime of. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Applied Artificial Intelligence is the property of Taylor & Francis Ltd 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=189934080
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1080/08839514.2025.2472105
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 40
        StartPage: 1
    Subjects:
      – SubjectFull: LIDAR
        Type: general
      – SubjectFull: Visual odometry
        Type: general
      – SubjectFull: Signal processing
        Type: general
      – SubjectFull: Point cloud
        Type: general
    Titles:
      – TitleFull: MagneticPillars++: Efficient LiDAR Odometry Via Deep Frame-To-Keyframe Point Cloud Registration.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Fischer, Kai
      – PersonEntity:
          Name:
            NameFull: Simon, Martin
      – PersonEntity:
          Name:
            NameFull: Milz, Stefan
      – PersonEntity:
          Name:
            NameFull: Mäder, Patrick
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 12
              Text: Dec2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 08839514
          Numbering:
            – Type: volume
              Value: 39
            – Type: issue
              Value: 1
          Titles:
            – TitleFull: Applied Artificial Intelligence
              Type: main
ResultId 1