L2M-Reg: Building-level Uncertainty-aware Registration of Outdoor LiDAR Point Clouds and Semantic 3D City Models

2025-09-20

AI Summary

To address the registration uncertainty of building-level LiDAR point clouds caused by geometric generalization in Level-of-Detail 2 (LoD2) semantic 3D city models, this paper proposes a robust building-level registration method. The core innovation lies in the first explicit modeling of geometric uncertainty inherent in semantic models, formulating a Gauss–Helmert optimization framework with pseudo-planar constraints and incorporating adaptive vertical translation estimation to mitigate elevation bias. The method jointly leverages planar feature matching and uncertainty-aware optimization. Evaluated on three real-world datasets, it achieves an average 18.7% improvement in registration accuracy over ICP and state-of-the-art planar registration methods, while reducing computational time by 42%. Results demonstrate that the proposed approach significantly enhances both the accuracy and robustness of entity-level geometric alignment in digital twin applications.

Technology Category

• Intelligent Robots: State Estimation
• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Location- and context-aware Web and WoT applications and services

Abstract

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 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. Experiments on three real-world datasets demonstrate that L2M-Reg is both more accurate and computationally efficient than existing ICP-based and plane-based methods. Overall, L2M-Reg provides a novel building-level solution regarding LiDAR-to-Model registration when model uncertainty is present.

Problem

• Achieving accurate LiDAR-to-model registration at individual building level
• Addressing generalization uncertainty in semantic 3D city models at LoD2
• Providing uncertainty-aware registration for urban digital twinning applications

Innovation

• Plane-based fine registration method
• Pseudo-plane-constrained Gauss-Helmert model
• Adaptive vertical translation estimation