Graph Theoretical Outlier Rejection for 4D Radar Registration in Feature-Poor Environments

• URL: http://arxiv.org/abs/2604.14857v1
• Date: Thu, 16 Apr 2026 10:44:47 GMT
• Title: Graph Theoretical Outlier Rejection for 4D Radar Registration in Feature-Poor Environments
• Abstract summary: Automotive 4D imaging radar is well suited for operation in dusty and low-visibility environments.<n>But registration remains challenging due to scan sparsity and spurious detections caused by noise and multipath reflections.<n>We propose a radar-adapted pairwise distance-invariant scoring function for clique-based graph (PCM)<n>Our method reduces segment relative position error (RPE) by 29.6% on 1 m segments and by up to on 100 m segments.
• Score: 0.6171990546748666
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Automotive 4D imaging radar is well suited for operation in dusty and low-visibility environments, but scan registration remains challenging due to scan sparsity and spurious detections caused by noise and multipath reflections. This difficulty is compounded in feature-poor open-pit mines, where the lack of distinctive landmarks reduces correspondence reliability. We integrate graph-based pairwise consistency maximization (PCM) as an outlier rejection step within the iterative closest points (ICP) loop. We propose a radar-adapted pairwise distance-invariant scoring function for graph-based (PCM) that incorporates anisotropic, per-detection uncertainty derived from a radar measurement model. The consistency maximization problem is approximated with a greedy heuristic that finds a large clique in the pairwise consistency graph. The refined correspondence set improves robustness when the initial association set is heavily contaminated. We evaluate a standard Euclidean distance residual and our uncertainty-aware residual on an open-pit mine dataset collected with a 4D imaging radar. Compared to the generalized ICP (GICP) baseline without PCM, our method reduces segment relative position error (RPE) by 29.6% on 1 m segments and by up to 55% on 100 m segments. The presented method is intended for integration into localization pipelines and is suitable for online use due to the greedy heuristic in graph-based (PCM).

Related papers

• Sub-Pixel Affine Registration of Space Debris Images via the Radon Point Spread Function [8.083475003173758]
  Inter-frame affine misalignment poses a fundamental challenge for multi-frame analysis of point targets in optical surveillance.<n>We introduce the Radon Point Spread Function (RPSF) to characterize point targets in the Radon-transformed domain.<n>We derive a closed-form framework that jointly estimates inter-frame translation and rotation from as few as four RPSF samples per frame pair.
  arXiv  Detail & Related papers  (2026-09-07T01:56:13Z)
• FIRE-LIVWO: Robust LiDAR-Inertial-Visual-Wheel Odometry via Failure-Immune mmWave Radar Enhancement [15.680013764871966]
  FIRE-LIVWO: Failure-Immune mmWave Radar-Enhanced LiDAR-Inertial-Visual-Wheel Odometry.<n>We propose a tightly coupled multi-modal odometry framework based on an iterated error-state Kalman filter (IESKF)<n>In smoke-filled environments, we exploit the strong penetration of 4D mmWave radar and introduce pointwise Doppler velocity constraints.<n>In geometrically degenerate corridors, we tightly couple wheel odometry using non-holonomic constraints (NHC) and online lever-arm compensation to reduce drift.
  arXiv  Detail & Related papers  (2026-09-04T16:19:58Z)
• Rethinking Pixel Mean Flows via Interval Denoiser [95.11499828543344]
  We propose the Interval Denoiser, a framework for latent-free generation.<n>Our model achieves an FID of 4.55 in one step (1-NFE) and 3.98 in two steps (2-NFE) without perceptual losses.
  arXiv  Detail & Related papers  (2026-08-05T13:22:43Z)
• RaDiVe: Robust 4D Radar Odometry with Distance-Bounded NDT and Velocity-Discrepancy Point Uncertainty [12.2982667950681]
  RaDiVe is a 4D radar odometry framework designed to improve the accuracy and robustness of radar point-cloud registration.<n>We introduce a distance-bounded Normal Distributions Transform (NDT), which improves optimization stability and computational efficiency.<n>We incorporate Signed Distance Function (SDF)-based surface point extraction via implicit neural mapping to construct a geometrically consistent and noise-filtered local submap.
  arXiv  Detail & Related papers  (2026-07-30T11:26:41Z)
• Dense Soft Weighting for Radar Ego-Velocity Estimation [6.356174487225252]
  We present Dense Soft Weighting, an analytic radar front-end for ego-velocity estimation.<n>It maps every range-Doppler cell to a continuous confidence metric rather than enforcing a binary detection threshold.<n>It reduces mean absolute pose error by 31-45% relative to the strongest CFAR point-cloud baseline.
  arXiv  Detail & Related papers  (2026-07-29T14:37:52Z)
• Cross-Coordinate Correspondence Pruning for Image-to-Point Cloud Registration [70.44225088078274]
  We propose a novel Cross-Coordinate Correspondences Pruning (CCP) strategy to acquire sufficient inliers while ensuring a low outlier ratio.<n>Our method achieves a significant performance improvement, surpassing existing state-of-the-art methods by at least 8.6% in Registration Recall across various benchmarks.
  arXiv  Detail & Related papers  (2026-07-19T11:45:14Z)
• Flow Map Denoisers: Traversing the Distortion-Perception Plane for Inverse Problems [48.501415601682815]
  Image restoration faces a fundamental tradeoff: methods that minimize error produce blurry reconstructions, while those that maximize perceptual quality yield sharp but less faithful images.<n>We show that flow map models implicitly define a one- parameter family of denoisers that continuously spans the distortion perception frontier.<n>Within a Plug-and-Play solver, the same mechanism extends to general inverse problems, where it controls a tradeoff between perceptual alignment and data consistency.
  arXiv  Detail & Related papers  (2026-06-18T05:15:43Z)
• Closed-Form Spectral Regularization for Multi-Task Model Merging [96.82449201305234]
  Model merging combines several independently fine-tuned experts into a single multi-task model without any training data.<n>State-of-the-art merging methods formulate merging as a layer-wise interference problem.<n>We propose SWUDI, a closed-form method that combines a soft exponential filter, which matches the gradient-flow trajectory of iterative descent.
  arXiv  Detail & Related papers  (2026-06-05T14:00:47Z)
• H-RINS: Hierarchical Tightly-coupled Radar-Inertial Navigation via Smoothing and Mapping [2.3821762993135507]
  Millimeter-wave radar provides robust perception in visually degraded environments.<n>Radar-inertial state estimation is inherently susceptible to drift.<n>We propose a tightly coupled, hierarchical radar-inertial factor graph framework.
  arXiv  Detail & Related papers  (2026-03-14T20:30:49Z)
• Optimized Hybrid Feature Engineering for Resource-Efficient Arrhythmia Detection in ECG Signals: An Optimization Framework [0.0]
  This study proposes a resource-efficient, data-centric framework that prioritizes feature engineering over complexity.<n>Our optimized pipeline makes the complex, high-dimensional arrhythmia data linearly separable.<n> validation on the MIT-BIH and INCART datasets yields 98.44% diagnostic accuracy with an 8.54 KB model footprint.
  arXiv  Detail & Related papers  (2026-01-01T03:44:42Z)
• Super4DR: 4D Radar-centric Self-supervised Odometry and Gaussian-based Map Optimization [13.79944715452315]
  We propose Super4DR, a 4D radar-centric framework for learning-based odometry estimation and map optimization.<n>Super4DR achieves a 67% performance gain over prior self-supervised methods, nearly matches supervised odometry, and narrows the map quality disparity with LiDAR.<n> Experiments show that Super4DR achieves a 67% performance gain over prior self-supervised methods, nearly matches supervised odometry, and narrows the map quality disparity with LiDAR.
  arXiv  Detail & Related papers  (2025-12-10T12:55:05Z)
• RadProPoser: A Framework for Human Pose Estimation with Uncertainty Quantification from Raw Radar Data [1.5318029014836756]
  We introduce RadProPoser, a probabilistic encoder-decoder architecture that processes complex-valued radar tensors.<n>By incorporating variational inference into keypoint regression, RadProPoser jointly predicts 26 three-dimensional joint locations.<n>On our newly released dataset with optical motion-capture ground truth, RadProPoser achieves an overall mean per-joint position error (MPJPE) of 6.425 cm, with 5.678 cm at the 45 degree angle.
  arXiv  Detail & Related papers  (2025-08-05T15:46:05Z)
• SPARE: Symmetrized Point-to-Plane Distance for Robust Non-Rigid 3D Registration [77.13381026159111]
  We propose SPARE, a novel formulation that utilizes a symmetrized point-to-plane distance for robust non-rigid registration.<n>The proposed method greatly improves the accuracy of non-rigid registration problems and maintains relatively high solution efficiency.
  arXiv  Detail & Related papers  (2024-05-30T15:55:04Z)
• Multi-Irreducible Spectral Synchronization for Robust Rotation Averaging [1.2289361708127877]
  We show how to estimate a set of unknown orientations $R_1,..., R_N in SO$, given noisy measurements. Results indicate how to devise measurement networks that are emph guaranteed to achieve accurate estimation.
  arXiv  Detail & Related papers  (2023-11-28T06:25:26Z)
• Deep Metric Learning for Unsupervised Remote Sensing Change Detection [60.89777029184023]
  Remote Sensing Change Detection (RS-CD) aims to detect relevant changes from Multi-Temporal Remote Sensing Images (MT-RSIs) The performance of existing RS-CD methods is attributed to training on large annotated datasets. This paper proposes an unsupervised CD method based on deep metric learning that can deal with both of these issues.
  arXiv  Detail & Related papers  (2023-03-16T17:52:45Z)
• The KFIoU Loss for Rotated Object Detection [115.334070064346]
  In this paper, we argue that one effective alternative is to devise an approximate loss who can achieve trend-level alignment with SkewIoU loss. Specifically, we model the objects as Gaussian distribution and adopt Kalman filter to inherently mimic the mechanism of SkewIoU. The resulting new loss called KFIoU is easier to implement and works better compared with exact SkewIoU.
  arXiv  Detail & Related papers  (2022-01-29T10:54:57Z)

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.