LR-SGS: Robust LiDAR-Reflectance-Guided Salient Gaussian Splatting for Self-Driving Scene Reconstruction

2026-03-13

AI Summary

This work addresses the limitations of existing self-supervised scene reconstruction methods under high ego-motion and complex lighting conditions, which struggle to effectively integrate geometric and reflectance information from LiDAR point clouds with RGB images. The authors propose a structure-aware saliency-guided Gaussian representation that, for the first time, incorporates calibrated LiDAR reflectance as an illumination-invariant material channel within the 3D Gaussian Splatting framework. By leveraging saliency-guided Gaussian initialization and density control, the method enhances the reconstruction of edges and planar structures while achieving aligned boundaries across LiDAR and RGB modalities. Evaluated on the Waymo dataset, the approach achieves superior reconstruction quality with fewer Gaussians and shorter training time, yielding a 1.18 dB PSNR improvement over OmniRe under challenging lighting conditions.

Technology Category

• Computer Vision: 3D Computer Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Recent 3D Gaussian Splatting (3DGS) methods have demonstrated the feasibility of self-driving scene reconstruction and novel view synthesis. However, most existing methods either rely solely on cameras or use LiDAR only for Gaussian initialization or depth supervision, while the rich scene information contained in point clouds, such as reflectance, and the complementarity between LiDAR and RGB have not been fully exploited, leading to degradation in challenging self-driving scenes, such as those with high ego-motion and complex lighting. To address these issues, we propose a robust and efficient LiDAR-reflectance-guided Salient Gaussian Splatting method (LR-SGS) for self-driving scenes, which introduces a structure-aware Salient Gaussian representation, initialized from geometric and reflectance feature points extracted from LiDAR and refined through a salient transform and improved density control to capture edge and planar structures. Furthermore, we calibrate LiDAR intensity into reflectance and attach it to each Gaussian as a lighting-invariant material channel, jointly aligned with RGB to enforce boundary consistency. Extensive experiments on the Waymo Open Dataset demonstrate that LR-SGS achieves superior reconstruction performance with fewer Gaussians and shorter training time. In particular, on Complex Lighting scenes, our method surpasses OmniRe by 1.18 dB PSNR.

Problem

• 3D Gaussian Splatting
• LiDAR reflectance
• self-driving scene reconstruction
• complex lighting
• multi-sensor fusion

Innovation

• LiDAR reflectance
• 3D Gaussian Splatting
• salient representation
• multi-modal alignment
• self-driving scene reconstruction