DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Guosheng, Ni, Chaojun, Wang, Xiaofeng, Zhu, Zheng, Zhang, Xueyang, Wang, Yida, Huang, Guan, Chen, Xinze, Wang, Boyuan, Zhang, Youyi, Mei, Wenjun, Wang, Xingang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913584337911808
author Zhao, Guosheng
Ni, Chaojun
Wang, Xiaofeng
Zhu, Zheng
Zhang, Xueyang
Wang, Yida
Huang, Guan
Chen, Xinze
Wang, Boyuan
Zhang, Youyi
Mei, Wenjun
Wang, Xingang
author_facet Zhao, Guosheng
Ni, Chaojun
Wang, Xiaofeng
Zhu, Zheng
Zhang, Xueyang
Wang, Yida
Huang, Guan
Chen, Xinze
Wang, Boyuan
Zhang, Youyi
Mei, Wenjun
Wang, Xingang
contents Closed-loop simulation is essential for advancing end-to-end autonomous driving systems. Contemporary sensor simulation methods, such as NeRF and 3DGS, rely predominantly on conditions closely aligned with training data distributions, which are largely confined to forward-driving scenarios. Consequently, these methods face limitations when rendering complex maneuvers (e.g., lane change, acceleration, deceleration). Recent advancements in autonomous-driving world models have demonstrated the potential to generate diverse driving videos. However, these approaches remain constrained to 2D video generation, inherently lacking the spatiotemporal coherence required to capture intricacies of dynamic driving environments. In this paper, we introduce DriveDreamer4D, which enhances 4D driving scene representation leveraging world model priors. Specifically, we utilize the world model as a data machine to synthesize novel trajectory videos, where structured conditions are explicitly leveraged to control the spatial-temporal consistency of traffic elements. Besides, the cousin data training strategy is proposed to facilitate merging real and synthetic data for optimizing 4DGS. To our knowledge, DriveDreamer4D is the first to utilize video generation models for improving 4D reconstruction in driving scenarios. Experimental results reveal that DriveDreamer4D significantly enhances generation quality under novel trajectory views, achieving a relative improvement in FID by 32.1%, 46.4%, and 16.3% compared to PVG, S3Gaussian, and Deformable-GS. Moreover, DriveDreamer4D markedly enhances the spatiotemporal coherence of driving agents, which is verified by a comprehensive user study and the relative increases of 22.6%, 43.5%, and 15.6% in the NTA-IoU metric.
format Preprint
id arxiv_https___arxiv_org_abs_2410_13571
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation
Zhao, Guosheng
Ni, Chaojun
Wang, Xiaofeng
Zhu, Zheng
Zhang, Xueyang
Wang, Yida
Huang, Guan
Chen, Xinze
Wang, Boyuan
Zhang, Youyi
Mei, Wenjun
Wang, Xingang
Computer Vision and Pattern Recognition
Closed-loop simulation is essential for advancing end-to-end autonomous driving systems. Contemporary sensor simulation methods, such as NeRF and 3DGS, rely predominantly on conditions closely aligned with training data distributions, which are largely confined to forward-driving scenarios. Consequently, these methods face limitations when rendering complex maneuvers (e.g., lane change, acceleration, deceleration). Recent advancements in autonomous-driving world models have demonstrated the potential to generate diverse driving videos. However, these approaches remain constrained to 2D video generation, inherently lacking the spatiotemporal coherence required to capture intricacies of dynamic driving environments. In this paper, we introduce DriveDreamer4D, which enhances 4D driving scene representation leveraging world model priors. Specifically, we utilize the world model as a data machine to synthesize novel trajectory videos, where structured conditions are explicitly leveraged to control the spatial-temporal consistency of traffic elements. Besides, the cousin data training strategy is proposed to facilitate merging real and synthetic data for optimizing 4DGS. To our knowledge, DriveDreamer4D is the first to utilize video generation models for improving 4D reconstruction in driving scenarios. Experimental results reveal that DriveDreamer4D significantly enhances generation quality under novel trajectory views, achieving a relative improvement in FID by 32.1%, 46.4%, and 16.3% compared to PVG, S3Gaussian, and Deformable-GS. Moreover, DriveDreamer4D markedly enhances the spatiotemporal coherence of driving agents, which is verified by a comprehensive user study and the relative increases of 22.6%, 43.5%, and 15.6% in the NTA-IoU metric.
title DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.13571