FGGS-LiDAR: Ultra-Fast, GPU-Accelerated Simulation from General 3DGS Models to LiDAR

Abstract-- While 3D Gaussian Splatting (3DGS) has revolutionized photorealistic rendering, its vast ecosystem of assets remains incompatible with high-performance LiDAR simulation, a critical tool for robotics and autonomous driving. Our method converts any pretrained 3DGS model into a high-fidelity, watertight mesh without requiring LiDAR-specific supervision or architectural alterations. We pair this with a highly optimized, GPU-accelerated ray-casting module that simulates LiDAR returns at over 500 FPS. We validate our approach on indoor and outdoor scenes, demonstrating exceptional geometric fidelity; By enabling the direct reuse of 3DGS assets for geometrically accurate depth sensing, our framework extends their utility beyond visualization and unlocks new capabilities for scalable, multi-modal simulation. I. INTRODUCTION LiDAR is a cornerstone modality for 3D perception, underpinning autonomous driving, localization, odometry, mapping, and indoor navigation [1], [2], [3], [4], [5]. To mitigate the prohibitive expense and logistical challenges of curating large-scale real-world datasets, simulation offers a controllable and reproducible source of data for training and benchmarking perception algorithms.