MagneticPillars++: Efficient LiDAR Odometry Via Deep Frame-To-Keyframe Point Cloud Registration
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 i...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2025-12-01
|
| Series: | Applied Artificial Intelligence |
| Online Access: | https://www.tandfonline.com/doi/10.1080/08839514.2025.2472105 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850213852812148736 |
|---|---|
| author | Kai Fischer Martin Simon Stefan Milz Patrick Mäder |
| author_facet | Kai Fischer Martin Simon Stefan Milz Patrick Mäder |
| author_sort | Kai Fischer |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-2b83091e64db4422b3ec5c23e9e10207 |
| institution | OA Journals |
| issn | 0883-9514 1087-6545 |
| language | English |
| publishDate | 2025-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Applied Artificial Intelligence |
| spelling | doaj-art-2b83091e64db4422b3ec5c23e9e102072025-08-20T02:09:02ZengTaylor & Francis GroupApplied Artificial Intelligence0883-95141087-65452025-12-0139110.1080/08839514.2025.2472105MagneticPillars++: Efficient LiDAR Odometry Via Deep Frame-To-Keyframe Point Cloud RegistrationKai Fischer0Martin Simon1Stefan Milz2Patrick Mäder3Data-intensive Systems and Visualization Group (dAI.SY), Technische Universität Ilmenau, Ilmenau, GermanyBrain Division Kronach, Valeo Schalter und Sensoren GmbH, Kronach, GermanyData-intensive Systems and Visualization Group (dAI.SY), Technische Universität Ilmenau, Ilmenau, GermanyData-intensive Systems and Visualization Group (dAI.SY), Technische Universität Ilmenau, Ilmenau, GermanyDownstream 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.https://www.tandfonline.com/doi/10.1080/08839514.2025.2472105 |
| spellingShingle | Kai Fischer Martin Simon Stefan Milz Patrick Mäder MagneticPillars++: Efficient LiDAR Odometry Via Deep Frame-To-Keyframe Point Cloud Registration Applied Artificial Intelligence |
| title | MagneticPillars++: Efficient LiDAR Odometry Via Deep Frame-To-Keyframe Point Cloud Registration |
| title_full | MagneticPillars++: Efficient LiDAR Odometry Via Deep Frame-To-Keyframe Point Cloud Registration |
| title_fullStr | MagneticPillars++: Efficient LiDAR Odometry Via Deep Frame-To-Keyframe Point Cloud Registration |
| title_full_unstemmed | MagneticPillars++: Efficient LiDAR Odometry Via Deep Frame-To-Keyframe Point Cloud Registration |
| title_short | MagneticPillars++: Efficient LiDAR Odometry Via Deep Frame-To-Keyframe Point Cloud Registration |
| title_sort | magneticpillars efficient lidar odometry via deep frame to keyframe point cloud registration |
| url | https://www.tandfonline.com/doi/10.1080/08839514.2025.2472105 |
| work_keys_str_mv | AT kaifischer magneticpillarsefficientlidarodometryviadeepframetokeyframepointcloudregistration AT martinsimon magneticpillarsefficientlidarodometryviadeepframetokeyframepointcloudregistration AT stefanmilz magneticpillarsefficientlidarodometryviadeepframetokeyframepointcloudregistration AT patrickmader magneticpillarsefficientlidarodometryviadeepframetokeyframepointcloudregistration |