LI-GS: Gaussian Splatting with LiDAR Incorporated for Accurate Large-Scale Reconstruction

TL;DR

LI-GS is a novel large-scale 3D reconstruction system that integrates LiDAR data with Gaussian Splatting to significantly improve geometric accuracy in outdoor scenes, outperforming existing methods.

Contribution

The paper introduces a new approach combining LiDAR and Gaussian Splatting with a novel GMM modeling method for enhanced accuracy and artifact reduction in large-scale 3D reconstruction.

Findings

Outperforms state-of-the-art methods in accuracy by 52.6% and 68.7%.

Effectively mitigates over-fitting and artifacts in large-scale scenes.

Enhances surface alignment using 2D Gaussian surfels.

Abstract

Large-scale 3D reconstruction is critical in the field of robotics, and the potential of 3D Gaussian Splatting (3DGS) for achieving accurate object-level reconstruction has been demonstrated. However, ensuring geometric accuracy in outdoor and unbounded scenes remains a significant challenge. This study introduces LI-GS, a reconstruction system that incorporates LiDAR and Gaussian Splatting to enhance geometric accuracy in large-scale scenes. 2D Gaussain surfels are employed as the map representation to enhance surface alignment. Additionally, a novel modeling method is proposed to convert LiDAR point clouds to plane-constrained multimodal Gaussian Mixture Models (GMMs). The GMMs are utilized during both initialization and optimization stages to ensure sufficient and continuous supervision over the entire scene while mitigating the risk of over-fitting. Furthermore, GMMs are employed in mesh extraction to eliminate artifacts and improve the overall geometric quality. Experiments demonstrate that our method outperforms state-of-the-art methods in large-scale 3D reconstruction, achieving higher accuracy compared to both LiDAR-based methods and Gaussian-based methods with improvements of 52.6% and 68.7%, respectively.