L2M-Reg：基于建筑级别的不确定性感知LiDAR点云与语义3D城市模型配准
L2M-Reg: Building-level Uncertainty-aware Registration of Outdoor LiDAR Point Clouds and Semantic 3D City Models
AI总结：
L2M-Reg提出一种基于平面的精细配准方法，解决建筑级别LiDAR点云与语义3D城市模型配准时的模型不确定性问题，实现更准确高效的配准效果。
摘要：
准确配准LiDAR（光探测和测距）点云与语义3D城市模型是城市数字孪生中的基础课题，也是数字建造、变化检测和模型细化等下游任务的前提。然而，实现单个建筑级别的LiDAR到模型配准仍具挑战性，尤其由于语义3D城市模型在Level of Detail 2（LoD2）层级上的泛化不确定性。本文通过提出L2M-Reg，一种基于平面的精细配准方法，明确考虑模型不确定性。L2M-Reg包含三个关键步骤：建立可靠的平面对应关系，构建伪平面约束的高斯-海尔特模型，以及自适应估计垂直平移。总体而言，对五个真实世界数据集的广泛实验表明，L2M-Reg在准确性和计算效率上均优于当前领先的ICP基于方法和平面基于方法。因此，L2M-Reg在存在模型不确定性时提供了一种新的建筑级别LiDAR到模型配准解决方案。数据集和代码可在：https://github.com/Ziyang-Geodesy/L2M-Reg找到。
英文摘要：
Accurate registration between LiDAR (Light Detection and Ranging) point clouds and semantic 3D city models is a fundamental topic in urban digital twinning and a prerequisite for downstream tasks, such as digital construction, change detection, and model refinement. However, achieving accurate LiDAR-to-Model registration at the individual building level remains challenging, particularly due to the generalization uncertainty in semantic 3D city models at the Level of Detail 2 (LoD2). This paper addresses this gap by proposing L2M-Reg, a plane-based fine registration method that explicitly accounts for model uncertainty. L2M-Reg consists of three key steps: establishing reliable plane correspondence, building a pseudo-plane-constrained Gauss-Helmert model, and adaptively estimating vertical translation. Overall, extensive experiments on five real-world datasets demonstrate that L2M-Reg is both more accurate and computationally efficient than current leading ICP-based and plane-based methods. Therefore, L2M-Reg provides a novel building-level solution regarding LiDAR-to-Model registration when model uncertainty is present. The datasets and code for L2M-Reg can be found: https://github.com/Ziyang-Geodesy/L2M-Reg.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
