Structured-Li-GS: Structured 3D Gaussians Splatting with LiDAR Incorporation and Spatial Constraints

2026-06-25

AI Summary

This work addresses the inefficiency and excessive Gaussian count inherent in conventional 3D Gaussian splatting by proposing a lightweight reconstruction framework. It introduces, for the first time, a structured dense colored point cloud—generated via LiDAR-inertial-visual SLAM—as a spatial prior to guide the initialization of Gaussian ellipsoids. A joint optimization strategy incorporating photometric, flattening, offset, depth, and normal losses is designed to achieve high-fidelity reconstruction without requiring Gaussian densification. Experimental results demonstrate that the proposed method consistently achieves superior geometric accuracy and scale-consistent, high-quality 3D reconstructions on both public and custom datasets, using significantly fewer Gaussians than existing approaches.

Abstract

In this study, we develop a Structured framework for Gaussian Splatting (3DGS) with LiDAR integration (Structured-Li-GS). It is a lightweight Gaussian Splatting pipeline that leverages LiDAR-inertial-visual SLAM. Structured-Li-GS achieves high-quality 3D reconstructions with fewer Gaussians by training on accurate, dense, colorized point clouds. Gaussian primitives are anchored using sub-sampled point clouds, and their ellipsoidal parameters are initialized from local surface geometry. Our training strategy integrates a comprehensive set of loss terms, including photometric, flattening, offset, depth, and normal losses, guided by the dense point cloud, enabling accurate reconstruction without Gaussian densification. This approach produces up-to-scale, high-fidelity results with a moderate model size. For experimental validation, we develop a custom hardware-synchronized LiDAR-camera handheld scanner. Experiments on both benchmark datasets and our real-world in-house dataset demonstrate that Structured-Li-GS surpasses state-of-the-art methods while using fewer Gaussians.

Problem

• 3D reconstruction
• Gaussian Splatting
• LiDAR integration
• high-fidelity modeling
• sparse representation

Innovation

• Gaussian Splatting
• LiDAR integration
• structured 3D reconstruction
• point cloud initialization
• multi-loss optimization