Physics-Aware 3D Gaussian Editing for Driving Scene Generation

2026-05-24

AI Summary

Existing 3D Gaussian splatting methods struggle to edit road geometry—such as speed bumps or potholes—and lack physical consistency in vehicle–road interactions, limiting their utility for generating extreme driving scenarios. This work proposes RoVES, the first system to jointly couple editable road geometry with vehicle dynamics within a 3D Gaussian splatting framework. RoVES enables one-click, optimization-free insertion of road elements from a single image and integrates a 4-degree-of-freedom half-car dynamics model to physically correct vehicle vertical displacement and pitch姿态. Evaluated on the Waymo dataset, the full editing pipeline runs in just 6.24 seconds (1.84 seconds for road insertion), achieving high efficiency while preserving visual consistency and dynamic realism, making it well-suited for data augmentation in autonomous driving training.

Abstract

3D Gaussian Splatting (3DGS) has shown great potential in autonomous driving simulation and data generation, enabling photorealistic reconstruction and flexible scene manipulation. However, existing 3DGS scene editing methods have limited support for road geometry editing (e.g., inserting speed humps or sunken roads), and generally do not couple such edits with plausible vehicle-road interaction dynamics. Such editing is essential for generating training data under extreme driving scenarios or evaluating system reliability under these road irregularities. Moreover, many optimization-based methods require minutes of per-edit refinement, while existing efficient alternatives mainly focus on appearance-level or object-level manipulation rather than physics-aware road irregularity editing. To address these limitations, we propose RoVES, a Road-and-Vehicle Editing System for physics-aware 3D Gaussian editing in driving scenes. RoVES enables single-image-driven road geometry insertion and couples the edited road profile with a 4-DOF half-car vehicle dynamics model to achieve physics-aware vehicle pose correction in vertical displacement and pitch. RoVES inserts road elements in a one-shot, optimization-free pipeline (1.84s), and the full pipeline (including color transfer and vehicle-dynamics-based pose correction) completes in 6.24s; it edits dynamic vehicles via pose editing and corrects poses frame-by-frame to approximate dynamics-consistent vertical displacement and pitch responses. Experiments on the Waymo dataset show that RoVES provides practical efficiency and competitive visual consistency for physics-aware driving scene generation.

Problem

• 3D Gaussian Splatting
• road geometry editing
• vehicle-road interaction
• physics-aware editing
• driving scene generation

Innovation

• Physics-aware editing
• 3D Gaussian Splatting
• Vehicle dynamics
• Road geometry manipulation
• Autonomous driving simulation