LiDAR-GS:Real-time LiDAR Re-Simulation using Gaussian Splatting

TL;DR

LiDAR-GS introduces a real-time, high-fidelity LiDAR re-simulation method using Gaussian Splatting, effectively capturing depth, intensity, and ray-drop characteristics in urban scenes with state-of-the-art performance.

Contribution

The paper adapts Gaussian Splatting for LiDAR data, addressing active sensor challenges and enabling real-time, accurate re-simulation of multiple LiDAR scan channels.

Findings

Achieves state-of-the-art rendering speed and quality.

Successfully re-simulates depth, intensity, and ray-drop channels.

Outperforms mesh-based and NeRF-based methods on large datasets.

Abstract

We present LiDAR-GS, a Gaussian Splatting (GS) method for real-time, high-fidelity re-simulation of LiDAR scans in public urban road scenes. Recent GS methods proposed for cameras have achieved significant advancements in real-time rendering beyond Neural Radiance Fields (NeRF). However, applying GS representation to LiDAR, an active 3D sensor type, poses several challenges that must be addressed to preserve high accuracy and unique characteristics. Specifically, LiDAR-GS designs a differentiable laser beam splatting, using range-view representation for precise surface splatting by projecting lasers onto micro cross-sections, effectively eliminating artifacts associated with local affine approximations. Furthermore, LiDAR-GS leverages Neural Gaussian Representation, which further integrate view-dependent clues, to represent key LiDAR properties that are influenced by the incident direction and external factors. Combining these practices with some essential adaptations, e.g., dynamic instances decomposition, LiDAR-GS succeeds in simultaneously re-simulating depth, intensity, and ray-drop channels, achieving state-of-the-art results in both rendering frame rate and quality on publically available large scene datasets when compared with the methods using explicit mesh or implicit NeRF. Our source code is publicly available at https://www.github.com/cqf7419/LiDAR-GS.