SymDrive: Realistic and Controllable Driving Simulator via Symmetric Auto-regressive Online Restoration
This addresses data scarcity in autonomous driving by improving simulation realism and controllability, representing a novel method for a known bottleneck.
The paper tackles the problem of achieving photorealistic rendering and interactive traffic editing in autonomous driving simulation, proposing SymDrive, which demonstrates state-of-the-art performance in novel-view enhancement and realistic 3D vehicle insertion.
High-fidelity and controllable 3D simulation is essential for addressing the long-tail data scarcity in Autonomous Driving (AD), yet existing methods struggle to simultaneously achieve photorealistic rendering and interactive traffic editing. Current approaches often falter in large-angle novel view synthesis and suffer from geometric or lighting artifacts during asset manipulation. To address these challenges, we propose SymDrive, a unified diffusion-based framework capable of joint high-quality rendering and scene editing. We introduce a Symmetric Auto-regressive Online Restoration paradigm, which constructs paired symmetric views to recover fine-grained details via a ground-truth-guided dual-view formulation and utilizes an auto-regressive strategy for consistent lateral view generation. Furthermore, we leverage this restoration capability to enable a training-free harmonization mechanism, treating vehicle insertion as context-aware inpainting to ensure seamless lighting and shadow consistency. Extensive experiments demonstrate that SymDrive achieves state-of-the-art performance in both novel-view enhancement and realistic 3D vehicle insertion.