LiHi-GS: LiDAR-Supervised Gaussian Splatting for Highway Driving Scene Reconstruction

TL;DR

This paper introduces LiHi-GS, a Gaussian Splatting method that leverages LiDAR data for high-fidelity, real-time 3D scene reconstruction specifically tailored for highway driving scenarios, addressing limitations of urban-focused methods.

Contribution

LiHi-GS is the first Gaussian Splatting approach to incorporate LiDAR supervision for highway scenes, enabling improved dynamic scene synthesis and LiDAR rendering in sparse, monotone environments.

Findings

Enhanced scene reconstruction accuracy in highway scenarios

Effective LiDAR data synthesis and rendering capabilities

Superior performance over existing urban-focused methods

Abstract

Photorealistic 3D scene reconstruction plays an important role in autonomous driving, enabling the generation of novel data from existing datasets to simulate safety-critical scenarios and expand training data without additional acquisition costs. Gaussian Splatting (GS) facilitates real-time, photorealistic rendering with an explicit 3D Gaussian representation of the scene, providing faster processing and more intuitive scene editing than the implicit Neural Radiance Fields (NeRFs). While extensive GS research has yielded promising advancements in autonomous driving applications, they overlook two critical aspects: First, existing methods mainly focus on low-speed and feature-rich urban scenes and ignore the fact that highway scenarios play a significant role in autonomous driving. Second, while LiDARs are commonplace in autonomous driving platforms, existing methods learn primarily from images and use LiDAR only for initial estimates or without precise sensor modeling, thus missing out on leveraging the rich depth information LiDAR offers and limiting the ability to synthesize LiDAR data. In this paper, we propose a novel GS method for dynamic scene synthesis and editing with improved scene reconstruction through LiDAR supervision and support for LiDAR rendering. Unlike prior works that are tested mostly on urban datasets, to the best of our knowledge, we are the first to focus on the more challenging and highly relevant highway scenes for autonomous driving, with sparse sensor views and monotone backgrounds. Visit our project page at: https://umautobots.github.io/lihi_gs