LiDAR-RT: Gaussian-based Ray Tracing for Dynamic LiDAR Re-simulation

TL;DR

LiDAR-RT introduces a real-time, physically accurate LiDAR re-simulation framework using Gaussian primitives and hardware-accelerated ray tracing, enabling efficient dynamic scene rendering for autonomous driving applications.

Contribution

The paper presents a novel real-time LiDAR re-simulation method that combines Gaussian primitives with ray tracing, overcoming computational limitations of prior neural radiance field approaches.

Findings

Outperforms state-of-the-art in rendering quality

Achieves real-time performance in dynamic scenes

Supports flexible scene editing and sensor configurations

Abstract

This paper targets the challenge of real-time LiDAR re-simulation in dynamic driving scenarios. Recent approaches utilize neural radiance fields combined with the physical modeling of LiDAR sensors to achieve high-fidelity re-simulation results. Unfortunately, these methods face limitations due to high computational demands in large-scale scenes and cannot perform real-time LiDAR rendering. To overcome these constraints, we propose LiDAR-RT, a novel framework that supports real-time, physically accurate LiDAR re-simulation for driving scenes. Our primary contribution is the development of an efficient and effective rendering pipeline, which integrates Gaussian primitives and hardware-accelerated ray tracing technology. Specifically, we model the physical properties of LiDAR sensors using Gaussian primitives with learnable parameters and incorporate scene graphs to handle scene dynamics. Building upon this scene representation, our framework first constructs a bounding volume hierarchy (BVH), then casts rays for each pixel and generates novel LiDAR views through a differentiable rendering algorithm. Importantly, our framework supports realistic rendering with flexible scene editing operations and various sensor configurations. Extensive experiments across multiple public benchmarks demonstrate that our method outperforms state-of-the-art methods in terms of rendering quality and efficiency. Our project page is at https://zju3dv.github.io/lidar-rt.