LSADS-Gaussian: Gaussian Splatting for Large-Scale Autonomous Driving Scene Reconstruction
Ping Wang, Ben Li, Bo Qian, Chuan Jin, Can Tian, Yusheng Ji
AI summary
Problem
Reconstructing large-scale autonomous driving scenes with 3D Gaussian Splatting is hindered by sparse camera viewpoints, inadequate geometric detail representation, and complex, varying outdoor lighting conditions.
Approach
LSADS-Gaussian fuses LiDAR and image features to initialize and optimize 3D Gaussians, refines geometry through directed-depth estimation under depth and normal constraints, and applies learnable illumination coefficients during rendering to stabilize appearance.
Key results
- Multimodal Gaussian Network robustly aggregates sparse LiDAR and SfM point clouds
- Directed-depth geometric guidance eliminates Gaussian aliasing and captures fine structural details
- Learnable illumination coefficients maintain cross-view lighting consistency
- Outperforms state-of-the-art methods in novel view synthesis and geometric accuracy
Why it matters
Provides a scalable, high-fidelity 3D reconstruction pipeline essential for realistic autonomous driving simulation and downstream perception tasks.
Abstract
The rapid advancement of 3D scene understanding techniques presents a significant opportunity for enhancing autonomous driving simulation systems. As these systems are increasingly required to operate in complex, large-scale, and unbounded real-world environments, efficient and high-fidelity 3D reconstruction of common outdoor scenes has become a critical prerequisite for realistic and extensible autonomous driving simulation. 3D Gaussian Splatting has achieved state-of-the-art performance in novel view synthesis, coupled with real-time rendering efficiency. However, large-scale reconstruction for autonomous driving scenarios faces several challenges as scenes grow in complexity: (1) limited views with insufficient pose diversity, (2) inadequate representation of geometric structural details, and (3) complex lighting conditions involving saturation and shadow variations. To cope with these challenges, we propose LSADS-Gaussian, a novel model for large-scale autonomous driving scene reconstruction. The model consists of a Multimodal Gaussian Network (MGN) module composed of two Gaussian sub-networks, designed to perform Gaussian aggregation and optimization from multi-sensor data, a Geometric Representation Guidance (GRG) module refines and enhances geometric consistency, and a Lighting Enhancement (LE) module introduces learnable illumination coefficients to maintain illumination consistency. Extensive experiments show that LSADS-Gaussian outperforms the state-of-the-art methods.