SymDrive: Realistic and Controllable Driving Simulator via Symmetric Auto-regressive Online Restoration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Zhiyuan, Fu, Daocheng, Cai, Pinlong, Wang, Lening, Liu, Ying, Ren, Yilong, Shi, Botian, Wang, Jianqiang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914220374753280
author Liu, Zhiyuan
Fu, Daocheng
Cai, Pinlong
Wang, Lening
Liu, Ying
Ren, Yilong
Shi, Botian
Wang, Jianqiang
author_facet Liu, Zhiyuan
Fu, Daocheng
Cai, Pinlong
Wang, Lening
Liu, Ying
Ren, Yilong
Shi, Botian
Wang, Jianqiang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_21618
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SymDrive: Realistic and Controllable Driving Simulator via Symmetric Auto-regressive Online Restoration
Liu, Zhiyuan
Fu, Daocheng
Cai, Pinlong
Wang, Lening
Liu, Ying
Ren, Yilong
Shi, Botian
Wang, Jianqiang
Computer Vision and Pattern Recognition
Robotics
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.
title SymDrive: Realistic and Controllable Driving Simulator via Symmetric Auto-regressive Online Restoration
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2512.21618