Source-Only Cross-Weather LiDAR via Geometry-Aware Point Drop

• URL: http://arxiv.org/abs/2511.01250v2
• Date: Thu, 06 Nov 2025 12:45:44 GMT
• Title: Source-Only Cross-Weather LiDAR via Geometry-Aware Point Drop
• Abstract summary: LiDAR semantic segmentation degrades in adverse weather because refraction, scattering, and point dropouts corrupt geometry.<n>We present a Light Geometry-aware adapter that aligns azimuth and applies circular padding to preserve neighbor continuity.<n>The adapter improves mIoU by 7.9 percentage points over the data-centric augmentation baseline and by 0.6 points over the class-centric regularization baseline.
• Score: 0.7734726150561086
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: LiDAR semantic segmentation degrades in adverse weather because refraction, scattering, and point dropouts corrupt geometry. Prior work in weather simulation, mixing-based augmentation, domain randomization, and uncertainty or boundary regularization improves robustness but still overlooks structural vulnerabilities near boundaries, corners, and sparse regions. We present a Light Geometry-aware adapter. The module aligns azimuth and applies horizontal circular padding to preserve neighbor continuity across the 0~360 degree wrap-around boundary. A local-window K-Nearest Neighbors gathers nearby points and computes simple local statistics, which are compressed into compact geometry-aware cues. During training, these cues drive region-aware regularization that stabilizes predictions in structurally fragile areas. The adapter is plug and play, complements augmentation, and can be enabled only during training with negligible inference cost. We adopt a source-only cross-weather setup where models train on SemanticKITTI and are evaluated on SemanticSTF without target labels or fine-tuning. The adapter improves mIoU by 7.9 percentage points over the data-centric augmentation baseline and by 0.6 points over the class-centric regularization baseline. These results indicate that geometry-driven regularization is a key direction for all-weather LiDAR segmentation.

Related papers

• Curvature-Aware Radius Shrinkage for Adaptive Nearest Neighbor Classification [52.452902154360565]
  CARSANN is a geometry-driven framework that adapts the spatial support of each neighborhood according to local geometric complexity.<n>Experiments on more than 70 real-world OpenML datasets show that CARSANN consistently improves upon standard $k$-NN.
  arXiv  Detail & Related papers  (2026-08-27T19:19:07Z)
• FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometry [52.232826445242644]
  FoundationGeo bridges relative and metric prediction via spatial calibration and principled data design.<n>Stage 1 learns a high-fidelity, affine-invariant geometry model by initializing with DINOv3.<n>Stage 2 moves beyond global scaling by introducing pixel-wise calibration fields for metric estimation.
  arXiv  Detail & Related papers  (2026-07-13T14:10:01Z)
• FRInGe: Distribution-Space Integrated Gradients with Fisher--Rao Geometry [4.823870413661438]
  We propose Fisher--Rao Integrated Gradients (FRInGe), which defines both the reference and schedule in predictive distribution space.<n> FRInGe replaces input baselines with a maximum-entropy predictive reference and follows a Fisher-Rao geodesic on the probability simplex.
  arXiv  Detail & Related papers  (2026-05-07T15:12:15Z)
• Keep It CALM: Toward Calibration-Free Kilometer-Level SLAM with Visual Geometry Foundation Models via an Assistant Eye [34.902300948471314]
  CAL2M is a plug-and-play framework compatible with arbitrary VGFMs.<n>It uses an "assistant eye" solely to leverage the prior of constant physical spacing.<n>It can effectively rectify rotation and translation errors caused by inaccurate intrinsics.
  arXiv  Detail & Related papers  (2026-04-16T08:58:57Z)
• A Graph Attention Network-Based Framework for Reconstructing Missing LiDAR Beams [0.0]
  This paper proposes a Graph Attention Network framework that reconstructs missing vertical channels using only the current LiDAR frame.<n>A multi-layer GAT learns adaptive attention weights over local geometric neighborhoods and directly regresses the missing elevation (z) values at dropout locations.<n>Inference takes 14.65 seconds per frame on a single GPU, and reconstruction quality remains stable for different neighborhood sizes.
  arXiv  Detail & Related papers  (2025-12-13T17:50:57Z)
• Rethinking the Encoding and Annotating of 3D Bounding Box: Corner-Aware 3D Object Detection from Point Clouds [69.84768614060559]
  Center-aligned regression remains dominant in LiDAR-based 3D object detection, yet it suffers from fundamental instability.<n>We propose corner-aligned regression, which shifts the prediction target from unstable centers to geometrically informative corners.<n>We design a simple yet effective corner-aware detection head that can be plugged into existing detectors.
  arXiv  Detail & Related papers  (2025-11-18T13:49:30Z)
• Gaussian Primitive Optimized Deformable Retinal Image Registration [19.882820812725523]
  Deformable retinal image registration is notoriously difficult due to large homogeneous regions and sparse but critical vascular features.<n>We introduce a novel iterative framework that performs structured message passing to overcome these challenges.<n>Experiments on the FIRE dataset show that GPO reduces the target registration error from 6.2,px to 2.4,px and increases the AUC at 25,px from 0.770 to 0.938.
  arXiv  Detail & Related papers  (2025-08-23T00:44:50Z)
• EmbodiedOcc++: Boosting Embodied 3D Occupancy Prediction with Plane Regularization and Uncertainty Sampler [43.277357306520145]
  This paper introduces EmbodiedOcc++, enhancing the original framework with two key innovations.<n>A Geometry-guided Refinement Module (GRM) constrains Gaussian updates through plane regularization, along with a Semantic-aware Uncertainty Sampler (SUS)<n>Experiments on the EmbodiedOcc-ScanNet benchmark demonstrate that EmbodiedOcc achieves state-of-the-art performance across different settings.
  arXiv  Detail & Related papers  (2025-04-13T12:10:49Z)
• 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)
• LiDAR-Camera Panoptic Segmentation via Geometry-Consistent and Semantic-Aware Alignment [63.83894701779067]
  We propose LCPS, the first LiDAR-Camera Panoptic network. In our approach, we conduct LiDAR-Camera fusion in three stages. Our fusion strategy improves about 6.9% PQ performance over the LiDAR-only baseline on NuScenes dataset.
  arXiv  Detail & Related papers  (2023-08-03T10:57:58Z)
• Data Augmentation-free Unsupervised Learning for 3D Point Cloud Understanding [61.30276576646909]
  We propose an augmentation-free unsupervised approach for point clouds to learn transferable point-level features via soft clustering, named SoftClu. We exploit the affiliation of points to their clusters as a proxy to enable self-training through a pseudo-label prediction task.
  arXiv  Detail & Related papers  (2022-10-06T10:18:16Z)
• Optimal Target Shape for LiDAR Pose Estimation [1.9048510647598205]
  Targets are essential in problems such as object tracking in cluttered or textureless environments. symmetric shapes lead to pose ambiguity when using sparse sensor data. This paper introduces the concept of optimizing target shape to remove pose ambiguity for LiDAR point clouds.
  arXiv  Detail & Related papers  (2021-09-02T19:18:24Z)
• A Point-Cloud Deep Learning Framework for Prediction of Fluid Flow Fields on Irregular Geometries [62.28265459308354]
  Network learns end-to-end mapping between spatial positions and CFD quantities. Incompress laminar steady flow past a cylinder with various shapes for its cross section is considered. Network predicts the flow fields hundreds of times faster than our conventional CFD.
  arXiv  Detail & Related papers  (2020-10-15T12:15:02Z)
• On the Arbitrary-Oriented Object Detection: Classification based Approaches Revisited [94.5455251250471]
  We first show that the boundary problem suffered in existing dominant regression-based rotation detectors, is caused by angular periodicity or corner ordering. We transform the angular prediction task from a regression problem to a classification one. For the resulting circularly distributed angle classification problem, we first devise a Circular Smooth Label technique to handle the periodicity of angle and increase the error tolerance to adjacent angles.
  arXiv  Detail & Related papers  (2020-03-12T03:23:54Z)

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.