GSAVS: Gaussian Splatting-based Autonomous Vehicle Simulator
This addresses the need for efficient and realistic simulation for autonomous vehicle developers, though it appears incremental by combining existing techniques.
The paper tackles the problem of cumbersome asset creation in autonomous vehicle simulators for digital twins by introducing GSAVS, a simulator that uses 3D Gaussian splats for all assets, enabling photorealism and real-time rendering within a classical 3D engine.
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.