POPL-KF: A Pose-Only Geometric Representation-Based Kalman Filter for Point-Line-Based Visual-Inertial Odometry

• URL: http://arxiv.org/abs/2602.06425v1
• Date: Fri, 06 Feb 2026 06:45:39 GMT
• Title: POPL-KF: A Pose-Only Geometric Representation-Based Kalman Filter for Point-Line-Based Visual-Inertial Odometry
• Authors: Aiping Wang, Zhaolong Yang, Shuwen Chen, Hai Zhang,
• Abstract summary: We develop POPL-KF, a Kalman filter-based VIO system that employs a pose-only geometric representation for both point and line features.<n> POPL-KF mitigates linearization errors by explicitly eliminating both point and line feature coordinates from the measurement equations.<n>To further improve line feature quality, a line feature filter based on image grid segmentation and bidirectional optical flow consistency is proposed.
• Score: 2.222792685950058
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Mainstream Visual-inertial odometry (VIO) systems rely on point features for motion estimation and localization. However, their performance degrades in challenging scenarios. Moreover, the localization accuracy of multi-state constraint Kalman filter (MSCKF)-based VIO systems suffers from linearization errors associated with feature 3D coordinates and delayed measurement updates. To improve the performance of VIO in challenging scenes, we first propose a pose-only geometric representation for line features. Building on this, we develop POPL-KF, a Kalman filter-based VIO system that employs a pose-only geometric representation for both point and line features. POPL-KF mitigates linearization errors by explicitly eliminating both point and line feature coordinates from the measurement equations, while enabling immediate update of visual measurements. We also design a unified base-frames selection algorithm for both point and line features to ensure optimal constraints on camera poses within the pose-only measurement model. To further improve line feature quality, a line feature filter based on image grid segmentation and bidirectional optical flow consistency is proposed. Our system is evaluated on public datasets and real-world experiments, demonstrating that POPL-KF outperforms the state-of-the-art (SOTA) filter-based methods (OpenVINS, PO-KF) and optimization-based methods (PL-VINS, EPLF-VINS), while maintaining real-time performance.

Related papers

• MS-ISSM: Objective Quality Assessment of Point Clouds Using Multi-scale Implicit Structural Similarity [65.85858856481131]
  unstructured and irregular nature of point clouds poses a significant challenge for objective quality assessment (PCQA)<n>We propose the Multi-scale Implicit Structural Similarity Measurement (MS-ISSM)
  arXiv  Detail & Related papers  (2026-01-03T14:58:52Z)
• MARVO: Marine-Adaptive Radiance-aware Visual Odometry [0.5336398444466023]
  We introduce MARVO, a physics-aware, learning-integratedometry framework that fuses underwater image formation modeling, differentiable matching, and reinforcement learning.<n>A Reinforcement-based PoseGraph refines global trajectories beyond local minima of classical least-squares by learning optimal retraction actions on SE(2).
  arXiv  Detail & Related papers  (2025-11-28T03:31:40Z)
• Adaptive Point-Prompt Tuning: Fine-Tuning Heterogeneous Foundation Models for 3D Point Cloud Analysis [51.37795317716487]
  We propose the Adaptive Point-Prompt Tuning (APPT) method, which fine-tunes pre-trained models with a modest number of parameters.<n>We convert raw point clouds into point embeddings by aggregating local geometry to capture spatial features followed by linear layers.<n>To calibrate self-attention across source domains of any modality to 3D, we introduce a prompt generator that shares weights with the point embedding module.
  arXiv  Detail & Related papers  (2025-08-30T06:02:21Z)
• PO-MSCKF: An Efficient Visual-Inertial Odometry by Reconstructing the Multi-State Constrained Kalman Filter with the Pose-only Theory [0.0]
  Visual-Inertial Odometry (VIO) is crucial for payload-constrained robots. We propose to reconstruct the MSCKF VIO with the novel Pose-Only (PO) multi-view geometry description. New filter does not require any feature position information, which removes the computational cost and linearization errors.
  arXiv  Detail & Related papers  (2024-07-02T02:18:35Z)
• Improving Gaussian Splatting with Localized Points Management [52.009874685460694]
  Localized Point Management (LPM) is capable of identifying those error-contributing zones in greatest need for both point addition and geometry calibration.<n>LPM applies point densification in the identified zones and then reset the opacity of the points in front of these regions, creating a new opportunity to correct poorly conditioned points.<n> Notably, LPM improves both static 3DGS and dynamic SpaceTimeGS to achieve state-of-the-art rendering quality while retaining real-time speeds.
  arXiv  Detail & Related papers  (2024-06-06T16:55:07Z)
• RD-VIO: Robust Visual-Inertial Odometry for Mobile Augmented Reality in Dynamic Environments [55.864869961717424]
  It is typically challenging for visual or visual-inertial odometry systems to handle the problems of dynamic scenes and pure rotation. We design a novel visual-inertial odometry (VIO) system called RD-VIO to handle both of these problems.
  arXiv  Detail & Related papers  (2023-10-23T16:30:39Z)
• Vanishing Point Estimation in Uncalibrated Images with Prior Gravity Direction [82.72686460985297]
  We tackle the problem of estimating a Manhattan frame. We derive two new 2-line solvers, one of which does not suffer from singularities affecting existing solvers. We also design a new non-minimal method, running on an arbitrary number of lines, to boost the performance in local optimization.
  arXiv  Detail & Related papers  (2023-08-21T13:03:25Z)
• IDLS: Inverse Depth Line based Visual-Inertial SLAM [9.38589798999922]
  Inverse Depth Line SLAM (IDLS) is proposed to track the line features in SLAM in an accurate and efficient way. IDLS is extensively evaluated in multiple perceptually-challenging datasets.
  arXiv  Detail & Related papers  (2023-04-23T20:53:05Z)
• Pose Refinement with Joint Optimization of Visual Points and Lines [6.780018205514503]
  We propose a point-line joint optimization method for pose refinement with the help of the innovatively designed line extracting CNN named VLSE. In this paper, we adopt a novel line representation and customize a hybrid convolutional block based on the Stacked Hourglass network. A following point-line joint cost function is constructed to optimize the camera pose with the initial coarse pose.
  arXiv  Detail & Related papers  (2021-10-08T07:22:51Z)
• Tight-Integration of Feature-Based Relocalization in Monocular Direct Visual Odometry [49.89611704653707]
  We propose a framework for integrating map-based relocalization into online visual odometry. We integrate image features into Direct Sparse Odometry (DSO) and rely on feature matching to associate online visual odometry with a previously built map.
  arXiv  Detail & Related papers  (2021-02-01T21:41:05Z)
• Pushing the Envelope of Rotation Averaging for Visual SLAM [69.7375052440794]
  We propose a novel optimization backbone for visual SLAM systems. We leverage averaging to improve the accuracy, efficiency and robustness of conventional monocular SLAM systems. Our approach can exhibit up to 10x faster with comparable accuracy against the state-art on public benchmarks.
  arXiv  Detail & Related papers  (2020-11-02T18:02:26Z)
• PL-VINS: Real-Time Monocular Visual-Inertial SLAM with Point and Line Features [11.990163046319974]
  This paper presents PL-VINS, a real-time optimization-based monocular VINS method with point and line features. Experiments in a public benchmark dataset show that the localization error of our method is 12-16% less than that of VINS-Mono at the same pose update frequency.
  arXiv  Detail & Related papers  (2020-09-16T04:27:33Z)
• Leveraging Planar Regularities for Point Line Visual-Inertial Odometry [13.51108336267342]
  With monocular Visual-Inertial Odometry (VIO) system, 3D point cloud and camera motion can be estimated simultaneously. We propose PLP-VIO, which exploits point features and line features as well as plane regularities. The effectiveness of the proposed method is verified on both synthetic data and public datasets.
  arXiv  Detail & Related papers  (2020-04-16T18:20:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.