LiSu: A Dataset and Method for LiDAR Surface Normal Estimation

• URL: http://arxiv.org/abs/2503.08601v1
• Date: Tue, 11 Mar 2025 16:35:22 GMT
• Title: LiSu: A Dataset and Method for LiDAR Surface Normal Estimation
• Abstract summary: We present LiSu, the first large-scale, synthetic LiDAR point cloud dataset with ground truth surface normal annotations.<n>We also propose a novel annotated method that exploits the temporal characteristics of autonomous driving data to enhance surface normal estimation accuracy.<n>We demonstrate the effectiveness of our method on LiSu, achieving state-of-the-art performance in LiDAR surface normal estimation.
• Score: 12.282805218676208
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While surface normals are widely used to analyse 3D scene geometry, surface normal estimation from LiDAR point clouds remains severely underexplored. This is caused by the lack of large-scale annotated datasets on the one hand, and lack of methods that can robustly handle the sparse and often noisy LiDAR data in a reasonable time on the other hand. We address these limitations using a traffic simulation engine and present LiSu, the first large-scale, synthetic LiDAR point cloud dataset with ground truth surface normal annotations, eliminating the need for tedious manual labeling. Additionally, we propose a novel method that exploits the spatiotemporal characteristics of autonomous driving data to enhance surface normal estimation accuracy. By incorporating two regularization terms, we enforce spatial consistency among neighboring points and temporal smoothness across consecutive LiDAR frames. These regularizers are particularly effective in self-training settings, where they mitigate the impact of noisy pseudo-labels, enabling robust real-world deployment. We demonstrate the effectiveness of our method on LiSu, achieving state-of-the-art performance in LiDAR surface normal estimation. Moreover, we showcase its full potential in addressing the challenging task of synthetic-to-real domain adaptation, leading to improved neural surface reconstruction on real-world data.

Related papers

• Gaussian Linear Functional Manifold Method for Massive Point Cloud Data [5.1885370045206916]
  This paper introduces the Gaussian Linear Functional Manifold (GLFM), a physics-informed statistical framework that represents continuous surface topography.<n>GLFM automatically filters ground points and extracts morphological features, achieving an adjusted Rand index (ARI) of 0.9933 against field-verified ground truth.<n>The framework provides a rigorous, interpretable, and scalable foundation for large-scale point cloud analytics.
  arXiv  Detail & Related papers  (2026-09-04T21:43:16Z)
• Extending Ground-Constraint LiDAR-IMU Calibration to Tilted Surfaces in a Continuous-Time Framework [5.115643891749577]
  This paper presents a novel method that extends targetless LiDAR-IMU calibration for ground vehicles to non- flat environments.<n> typically necessitates full exci- tation of the sensor rig, a requirement that is not fulfilled by ground vehicles in normal operation.<n>To address the degenerate planar motion, state-of-the-art methods propose residuals that assume the colinearity of the gravity and physical surface normal vectors.
  arXiv  Detail & Related papers  (2026-08-25T20:35:18Z)
• Non-line-of-sight imaging with arbitrary relay surface geometries via 3D Gaussian Transient Rendering [19.621253931527082]
  Imaging objects hidden outside the direct line of sight expands the effective field of view and is critical for applications such as autonomous driving and robotic perception.<n>We propose a LOS-guided NLOS imaging pipeline that imposes no geometric assumptions on the relay surface and naturally supports both confocal and non-confocal configurations.<n>Our method represents the hidden scene using 3D Gaussian primitives and couples them with an efficient, differentiable rendering transient model, enabling end-to-end optimization directly from measured transients.
  arXiv  Detail & Related papers  (2026-06-19T09:47:17Z)
• Mobility Anomaly Generation using LLM-Driven Behavior with Kinematic Constraints [1.330528227599978]
  We introduce an end-to-end generative framework designed to synthesize realistic trajectory anomalies at scale.<n>Our architecture bridges the gap between purely synthetic mobility data and complex real-world physical constraints.
  arXiv  Detail & Related papers  (2026-06-09T02:09:02Z)
• PolGS++: Physically-Guided Polarimetric Gaussian Splatting for Fast Reflective Surface Reconstruction [76.9760302941819]
  PolGS++ is a polarimetric Gaussian Splatting framework for fast reflective surface reconstruction.<n>We introduce a depth-guided visibility mask acquisition mechanism that enables angle-of-polarization (AoP)-based tangent-space consistency constraints.
  arXiv  Detail & Related papers  (2026-03-11T14:11:42Z)
• LiDAR-GS++:Improving LiDAR Gaussian Reconstruction via Diffusion Priors [51.724649822336346]
  We present LiDAR-GS++, a reconstruction method enhanced by diffusion priors for real-time and high-fidelity re-simulation.<n>Specifically, we introduce a controllable LiDAR generation model conditioned on coarsely extrapolated rendering to produce extra geometry-consistent scans.<n>By extending reconstruction to under-fitted regions, our approach ensures global geometric consistency for extrapolative novel views.
  arXiv  Detail & Related papers  (2025-11-15T17:33:12Z)
• Scaling Up Occupancy-centric Driving Scene Generation: Dataset and Method [54.461213497603154]
  Occupancy-centric methods have recently achieved state-of-the-art results by offering consistent conditioning across frames and modalities.<n>Nuplan-Occ is the largest occupancy dataset to date, constructed from the widely used Nuplan benchmark.<n>We develop a unified framework that jointly synthesizes high-quality occupancy, multi-view videos, and LiDAR point clouds.
  arXiv  Detail & Related papers  (2025-10-27T03:52:45Z)
• Graph-based Point Cloud Surface Reconstruction using B-Splines [0.0]
  Real-world point clouds are inherently noisy due to various technical and environmental factors.<n>Existing data-driven surface reconstruction algorithms rely heavily on ground truth normals or compute approximate normals as an intermediate step.<n>We develop a Dictionary-Guided Graph Convolutional Network-based surface reconstruction strategy.
  arXiv  Detail & Related papers  (2025-09-19T14:59:51Z)
• LiDAR-GS:Real-time LiDAR Re-Simulation using Gaussian Splatting [50.808933338389686]
  LiDAR simulation plays a crucial role in closed-loop simulation for autonomous driving. We present LiDAR-GS, the first LiDAR Gaussian Splatting method, for real-time high-fidelity re-simulation of LiDAR sensor scans in public urban road scenes. Our approach succeeds in simultaneously re-simulating depth, intensity, and ray-drop channels, achieving state-of-the-art results in both rendering frame rate and quality on publically available large scene datasets.
  arXiv  Detail & Related papers  (2024-10-07T15:07:56Z)
• RaNeuS: Ray-adaptive Neural Surface Reconstruction [87.20343320266215]
  We leverage a differentiable radiance field eg NeRF to reconstruct detailed 3D surfaces in addition to producing novel view renderings. Considering that different methods formulate and optimize the projection from SDF to radiance field with a globally constant Eikonal regularization, we improve with a ray-wise weighting factor. Our proposed textitRaNeuS are extensively evaluated on both synthetic and real datasets.
  arXiv  Detail & Related papers  (2024-06-14T07:54:25Z)
• PSS-BA: LiDAR Bundle Adjustment with Progressive Spatial Smoothing [27.060381833488172]
  This paper presents a LiDAR bundle adjustment with progressive spatial smoothing. The effectiveness and robustness of our proposed approach have been validated on both simulation and real-world datasets.
  arXiv  Detail & Related papers  (2024-03-10T07:56:54Z)
• LiDAR-NeRF: Novel LiDAR View Synthesis via Neural Radiance Fields [112.62936571539232]
  We introduce a new task, novel view synthesis for LiDAR sensors. Traditional model-based LiDAR simulators with style-transfer neural networks can be applied to render novel views. We use a neural radiance field (NeRF) to facilitate the joint learning of geometry and the attributes of 3D points.
  arXiv  Detail & Related papers  (2023-04-20T15:44:37Z)
• NeRF-LOAM: Neural Implicit Representation for Large-Scale Incremental LiDAR Odometry and Mapping [14.433784957457632]
  We propose a novel NeRF-based LiDAR odometry and mapping approach, NeRF-LOAM, consisting of three modules neural odometry, neural mapping, and mesh reconstruction. Our approach achieves state-of-the-art odometry and mapping performance, as well as a strong generalization in large-scale environments utilizing LiDAR data.
  arXiv  Detail & Related papers  (2023-03-19T16:40:36Z)
• Learning to Simulate Realistic LiDARs [66.7519667383175]
  We introduce a pipeline for data-driven simulation of a realistic LiDAR sensor. We show that our model can learn to encode realistic effects such as dropped points on transparent surfaces. We use our technique to learn models of two distinct LiDAR sensors and use them to improve simulated LiDAR data accordingly.
  arXiv  Detail & Related papers  (2022-09-22T13:12:54Z)
• Fast and Robust Ground Surface Estimation from LIDAR Measurements using Uniform B-Splines [3.337790639927531]
  We propose a fast and robust method to estimate the ground surface from LIDAR measurements on an automated vehicle. We model the estimation process as a robust LS optimization problem which can be reformulated as a linear problem. We validate the approach on our research vehicle in real-world scenarios.
  arXiv  Detail & Related papers  (2022-03-02T15:26:51Z)
• Real-time Multi-Adaptive-Resolution-Surfel 6D LiDAR Odometry using Continuous-time Trajectory Optimization [33.67478846305404]
  We propose a real-time method for 6D LiDAR odometry. Our approach combines a continuous-time B-Spline trajectory representation with a Gaussian Mixture Model (GMM) formulation to jointly align local multi-resolution surfel maps. A thorough experimental evaluation shows the performance of our approach on two datasets and during real-robot experiments.
  arXiv  Detail & Related papers  (2021-05-05T12:14:39Z)
• SelfVoxeLO: Self-supervised LiDAR Odometry with Voxel-based Deep Neural Networks [81.64530401885476]
  We propose a self-supervised LiDAR odometry method, dubbed SelfVoxeLO, to tackle these two difficulties. Specifically, we propose a 3D convolution network to process the raw LiDAR data directly, which extracts features that better encode the 3D geometric patterns. We evaluate our method's performances on two large-scale datasets, i.e., KITTI and Apollo-SouthBay.
  arXiv  Detail & Related papers  (2020-10-19T09:23:39Z)
• ePointDA: An End-to-End Simulation-to-Real Domain Adaptation Framework for LiDAR Point Cloud Segmentation [111.56730703473411]
  Training deep neural networks (DNNs) on LiDAR data requires large-scale point-wise annotations. Simulation-to-real domain adaptation (SRDA) trains a DNN using unlimited synthetic data with automatically generated labels. ePointDA consists of three modules: self-supervised dropout noise rendering, statistics-invariant and spatially-adaptive feature alignment, and transferable segmentation learning.
  arXiv  Detail & Related papers  (2020-09-07T23:46:08Z)

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.