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

arXiv: https://arxiv.org/abs/2603.12647 · HTML: https://mlsanity.com/paper/2603.12647/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 35 references that are in the map.
- First posted on arXiv 13 Mar 2026.

## Builds on (most cited first, 30 of 30)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [4D Gaussian Splatting for Real-Time Dynamic Scene Rendering](https://mlsanity.com/paper/2310.08528/) (2023)
- [Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction](https://mlsanity.com/paper/2309.13101/) (2023)
- [Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting](https://mlsanity.com/paper/2310.10642/) (2023)
- [DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenes](https://mlsanity.com/paper/2312.07920/) (2023)
- [UniSim: A Neural Closed-Loop Sensor Simulator](https://mlsanity.com/paper/2308.01898/) (2023)
- [Urban Radiance Fields](https://mlsanity.com/paper/2111.14643/) (2021)
- [Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splatting](https://mlsanity.com/paper/2401.01339/) (2024)
- [EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision](https://mlsanity.com/paper/2311.02077/) (2023)
- [MARS: An Instance-aware, Modular and Realistic Simulator for Autonomous Driving](https://mlsanity.com/paper/2307.15058/) (2023)
- [OmniRe: Omni Urban Scene Reconstruction](https://mlsanity.com/paper/2408.16760/) (2024)
- [SUDS: Scalable Urban Dynamic Scenes](https://mlsanity.com/paper/2303.14536/) (2023)
- [Periodic Vibration Gaussian: Dynamic Urban Scene Reconstruction and Real-time Rendering](https://mlsanity.com/paper/2311.18561/) (2023)
- [HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting](https://mlsanity.com/paper/2403.12722/) (2024)
- [D2NeRF: Self-Supervised Decoupling of Dynamic and Static Objects from a Monocular Video](https://mlsanity.com/paper/2205.15838/) (2022)
- [Urban Radiance Field Representation with Deformable Neural Mesh Primitives](https://mlsanity.com/paper/2307.10776/) (2023)
- [Neural Point Light Fields](https://mlsanity.com/paper/2112.01473/) (2021)
- [SHINE-Mapping: Large-Scale 3D Mapping Using Sparse Hierarchical Implicit Neural Representations](https://mlsanity.com/paper/2210.02299/) (2022)
- [Nerflets: Local Radiance Fields for Efficient Structure-Aware 3D Scene Representation from 2D Supervision](https://mlsanity.com/paper/2303.03361/) (2023)
- [Real-Time Neural Rasterization for Large Scenes](https://mlsanity.com/paper/2311.05607/) (2023)
- [MG-SLAM: Structure Gaussian Splatting SLAM with Manhattan World Hypothesis](https://mlsanity.com/paper/2405.20031/) (2024)
- [RGB-Only Gaussian Splatting SLAM for Unbounded Outdoor Scenes](https://mlsanity.com/paper/2502.15633/) (2025)
- [TCLC-GS: Tightly Coupled LiDAR-Camera Gaussian Splatting for Autonomous Driving](https://mlsanity.com/paper/2404.02410/) (2024)
- [Large-Scale Gaussian Splatting SLAM](https://mlsanity.com/paper/2505.09915/) (2025)
- [Intensity-SLAM: Intensity Assisted Localization and Mapping for Large Scale Environment](https://mlsanity.com/paper/2102.03798/) (2021)
- [FGO-SLAM: Enhancing Gaussian SLAM with Globally Consistent Opacity Radiance Field](https://mlsanity.com/paper/2509.01547/) (2025)
- [InvRGB+L: Inverse Rendering of Complex Scenes with Unified Color and LiDAR Reflectance Modeling](https://mlsanity.com/paper/2507.17613/) (2025)
- [LiDAR-enhanced 3D Gaussian Splatting Mapping](https://mlsanity.com/paper/2503.05425/) (2025)

## Built on by (most cited first, 1 of 1)

- [F2 SLAM: Turning Feed-Forward Geometry into Persistent Factors for SLAM](https://mlsanity.com/paper/2610.05207/) (2026)

## Abstract (arXiv)

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.