GSAVS: Gaussian Splatting-based Autonomous Vehicle Simulator

TL;DR

GSAVS is an innovative autonomous vehicle simulator that combines Gaussian splatting for high-fidelity scene rendering with the flexibility of traditional 3D engines, enabling realistic and customizable virtual environments.

Contribution

The paper introduces GSAVS, a novel simulator that integrates Gaussian splatting into a classical 3D engine for real-time, photorealistic autonomous vehicle simulation.

Findings

Supports real-time rendering of Gaussian splats

Enables high-fidelity, customizable virtual environments

Combines Gaussian splatting with traditional 3D engine advantages

Abstract

Modern autonomous vehicle simulators feature an ever-growing library of assets, including vehicles, buildings, roads, pedestrians, and more. While this level of customization proves beneficial when creating virtual urban environments, this process becomes cumbersome when intending to train within a digital twin or a duplicate of a real scene. Gaussian splatting emerged as a powerful technique in scene reconstruction and novel view synthesis, boasting high fidelity and rendering speeds. In this paper, we introduce GSAVS, an autonomous vehicle simulator that supports the creation and development of autonomous vehicle models. Every asset within the simulator is a 3D Gaussian splat, including the vehicles and the environment. However, the simulator runs within a classical 3D engine, rendering 3D Gaussian splats in real-time. This allows the simulator to utilize the photorealism that 3D Gaussian splatting boasts while providing the customization and ease of use of a classical 3D engine.