UQ-Loc: Uncertainty-Aware LiDAR Scene Coordinate Regression

• URL: http://arxiv.org/abs/2608.06307v1
• Date: Thu, 06 Aug 2026 17:23:17 GMT
• Title: UQ-Loc: Uncertainty-Aware LiDAR Scene Coordinate Regression
• Abstract summary: LiDAR maps point clouds directly to 3D scene coordinates, enabling precise 6-DoF localisation without explicit map retrieval.<n>Existing methods produce deterministic predictions, discarding aleatoric uncertainty that could improve robustness and downstream decision-making.<n>We present UQ-Loc, which extends the LightLoc architecture with an anisotropic Gaussian covariance head that predicts a full 3x3 positive-definite covariance matrix per voxel.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: LiDAR-based Scene Coordinate Regression (SCR) maps point clouds directly to 3D scene coordinates, enabling precise 6-DoF localisation without explicit map retrieval. However, existing methods produce deterministic predictions, discarding aleatoric uncertainty that could improve robustness and downstream decision-making. We present UQ-Loc, which extends the LightLoc architecture with an anisotropic Gaussian covariance head that predicts a full 3x3 positive-definite covariance matrix per voxel. Training uses a Negative Log-Likelihood (NLL) loss augmented with a kNN-based spatial smoothness regulariser, while inference employs a modified SC2-PCR solver with uncertainty-weighted seed scoring and a Mahalanobis-distance inlier test. We adopt Expected Calibration Error (ECE) as a principled metric for evaluating the quality of the predicted uncertainty. Experiments demonstrate that UQ-Loc achieves consistent improvement in 6-DoF localization accuracy while producing well-calibrated covariances.

Related papers

• Unscented KalmanNet: a hybrid deep learning filter with calibrated posterior covariance for nonlinear state estimation [3.3318820340878528]
  State estimation for nonlinear dynamical systems is commonly performed with the Unscented Kalman filter (UKF)<n>This paper introduces the Unscented KalmanNet (UKN), a hybrid recursion estimator that augments the UKF with two structurally distinct learned components.<n>UKN achieves the lowest aggregate state-estimation error in all four examples and reduces RMSE by $26.4$-$49.7%$ compared to UKF in the synthetic cases.
  arXiv  Detail & Related papers  (2026-08-04T19:58:01Z)
• Calibrated Closed-Form Uncertainty for Radiative Gaussian Splatting in Sparse-View CT [13.147279382369293]
  We present the first systematic calibration study for Gaussian-splatting CT.<n>We show that the resulting per-voxel uncertainty ranks true reconstruction error on 14 of 15 scenes of the official benchmark.<n>We then dissect why uncalibrated acquisition scores can nevertheless select acceptable views.
  arXiv  Detail & Related papers  (2026-07-15T10:25:05Z)
• Decision Kernels for Quantum Error Mitigation: Why Accuracy Gains Need Not Improve Downstream Decisions [0.0]
  We develop a theory of finite-shot QEM for downstream decisions.<n>We prove quotient factorization, gap-law minimality, a marginal no-go theorem, a QEM pullback theorem, and a fixed-allocation shot-level converse.
  arXiv  Detail & Related papers  (2026-07-03T02:35:57Z)
• Learning from Emptiness: De-biasing Listwise Rerankers with Content-Agnostic Probability Calibration [76.08899010904652]
  CapCal is a training-free framework that mechanically decouples positional bias from ranking decisions.<n>It achieves superior performance among training-free methods while preserving single-pass efficiency.
  arXiv  Detail & Related papers  (2026-04-11T10:47:22Z)
• CAGE: Curvature-Aware Gradient Estimation For Accurate Quantization-Aware Training [73.46600457802693]
  We introduce a new method that counteracts the loss induced by quantization.<n>CAGE significantly improves upon the state-of-theart methods in terms of accuracy, for similar computational cost.<n>For QAT pre-training of Llama models, CAGE matches the accuracy achieved at 4-bits (W4A4) with the prior best method.
  arXiv  Detail & Related papers  (2025-10-21T16:33:57Z)
• Towards Robust LiDAR Localization: Deep Learning-based Uncertainty Estimation [1.9268905951820923]
  Iterative Closest Point (ICP) is prone to errors in featureless environments and dynamic scenes, leading to inaccurate pose estimation.<n>We propose a data-driven framework that leverages deep learning to estimate the registration error covariance of ICP before matching.<n>Our method enables seamless integration of ICP within Kalman filtering, enhancing localization accuracy and robustness.
  arXiv  Detail & Related papers  (2025-09-23T13:02:44Z)
• Density-Calibrated Conformal Quantile Regression [2.0485358181172453]
  This paper introduces the Density-Calibrated Conformal Quantile Regression (CQR-d) method.<n>CQR-d incorporates local information through a weighted combination of local and global conformity scores, where the weights are determined by local data density.<n>We prove that CQR-d provides valid marginal coverage at level $1 - alpha - epsilon$, where $epsilon$ represents a small tolerance from numerical optimization.
  arXiv  Detail & Related papers  (2024-11-29T07:41:20Z)
• Uncertainty-Aware AB3DMOT by Variational 3D Object Detection [74.8441634948334]
  Uncertainty estimation is an effective tool to provide statistically accurate predictions. In this paper, we propose a Variational Neural Network-based TANet 3D object detector to generate 3D object detections with uncertainty.
  arXiv  Detail & Related papers  (2023-02-12T14:30:03Z)
• Uncertainty-Aware Camera Pose Estimation from Points and Lines [101.03675842534415]
  Perspective-n-Point-and-Line (Pn$PL) aims at fast, accurate and robust camera localizations with respect to a 3D model from 2D-3D feature coordinates.
  arXiv  Detail & Related papers  (2021-07-08T15:19:36Z)
• Localization Uncertainty Estimation for Anchor-Free Object Detection [48.931731695431374]
  There are several limitations of the existing uncertainty estimation methods for anchor-based object detection. We propose a new localization uncertainty estimation method called UAD for anchor-free object detection. Our method captures the uncertainty in four directions of box offsets that are homogeneous, so that it can tell which direction is uncertain.
  arXiv  Detail & Related papers  (2020-06-28T13:49:30Z)
• Robust 6D Object Pose Estimation by Learning RGB-D Features [59.580366107770764]
  We propose a novel discrete-continuous formulation for rotation regression to resolve this local-optimum problem. We uniformly sample rotation anchors in SO(3), and predict a constrained deviation from each anchor to the target, as well as uncertainty scores for selecting the best prediction. Experiments on two benchmarks: LINEMOD and YCB-Video, show that the proposed method outperforms state-of-the-art approaches.
  arXiv  Detail & Related papers  (2020-02-29T06:24:55Z)

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.