PlanarMesh: Building Compact 3D Meshes from LiDAR using Incremental Adaptive Resolution Reconstruction

2025-10-15

AI Summary

To address the challenge of simultaneously achieving real-time performance, high accuracy, and storage efficiency in online LiDAR mapping, this paper proposes an incremental adaptive-resolution 3D surface reconstruction method. Our core innovation is a “planar-mesh” joint representation: dominant structural geometry is modeled analytically using planes, while local geometric details are captured via adaptive-resolution triangle meshes; an incrementally updated reconstruction mechanism—driven jointly by curvature estimation and free-space constraints—enables dynamic resolution adjustment. The system integrates a bounding volume hierarchy (BVH) for efficient spatial indexing and leverages multi-threaded optimization. It achieves ~2 Hz real-time processing while matching or surpassing state-of-the-art methods in reconstruction accuracy. Moreover, the output model occupies only 1/10 the volume of the original point cloud and achieves over 5× compression compared to mainstream mesh-based approaches, significantly improving storage and transmission efficiency.

Technology Category

• Computer Vision: 3D Computer Vision
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Building an online 3D LiDAR mapping system that produces a detailed surface reconstruction while remaining computationally efficient is a challenging task. In this paper, we present PlanarMesh, a novel incremental, mesh-based LiDAR reconstruction system that adaptively adjusts mesh resolution to achieve compact, detailed reconstructions in real-time. It introduces a new representation, planar-mesh, which combines plane modeling and meshing to capture both large surfaces and detailed geometry. The planar-mesh can be incrementally updated considering both local surface curvature and free-space information from sensor measurements. We employ a multi-threaded architecture with a Bounding Volume Hierarchy (BVH) for efficient data storage and fast search operations, enabling real-time performance. Experimental results show that our method achieves reconstruction accuracy on par with, or exceeding, state-of-the-art techniques-including truncated signed distance functions, occupancy mapping, and voxel-based meshing-while producing smaller output file sizes (10 times smaller than raw input and more than 5 times smaller than mesh-based methods) and maintaining real-time performance (around 2 Hz for a 64-beam sensor).

Problem

• Builds compact 3D meshes from LiDAR data adaptively
• Combines plane modeling with meshing for detailed geometry
• Achieves real-time performance with incremental reconstruction updates

Innovation

• Incremental adaptive resolution mesh reconstruction system
• Planar-mesh combining plane modeling with meshing
• Multi-threaded BVH architecture for real-time performance