GTLR-GS: Geometry-Texture Aware LiDAR-Regularized 3D Gaussian Splatting for Realistic Scene Reconstruction

TL;DR

This paper introduces a LiDAR-informed 3D Gaussian Splatting framework that incorporates geometric priors and adaptive refinement strategies to achieve highly accurate, metric-scale scene reconstructions with improved geometric fidelity.

Contribution

It proposes a novel geometry-texture-aware allocation and curvature-adaptive refinement method that explicitly integrates LiDAR data into 3D Gaussian Splatting optimization.

Findings

Achieves state-of-the-art metric-scale scene reconstruction

Demonstrates high geometric fidelity on real-world datasets

Outperforms existing methods in structural accuracy

Abstract

Recent advances in 3D Gaussian Splatting (3DGS) have enabled real-time, photorealistic scene reconstruction. However, conventional 3DGS frameworks typically rely on sparse point clouds derived from Structure-from-Motion (SfM), which inherently suffer from scale ambiguity, limited geometric consistency, and strong view dependency due to the lack of geometric priors. In this work, a LiDAR-centric 3D Gaussian Splatting framework is proposed that explicitly incorporates metric geometric priors into the entire Gaussian optimization process. Instead of treating LiDAR data as a passive initialization source, 3DGS optimization is reformulated as a geometry-conditioned allocation and refinement problem under a fixed representational budget. Specifically, this work introduces (i) a geometry-texture-aware allocation strategy that selectively assigns Gaussian primitives to regions with high structural or appearance complexity, (ii) a curvature-adaptive refinement mechanism that dynamically guides Gaussian splitting toward geometrically complex areas during training, and (iii) a confidence-aware metric depth regularization that anchors the reconstructed geometry to absolute scale using LiDAR measurements while maintaining optimization stability. Extensive experiments on the ScanNet++ dataset and a custom real-world dataset validate the proposed approach. The results demonstrate state-of-the-art performance in metric-scale reconstruction with high geometric fidelity.