DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Driving

arXiv:2405.04390v1 Announce Type: new
Abstract: Vision-centric autonomous driving has recently raised wide attention due to its lower cost. Pre-training is essential for extracting a universal representation. However, current vision-centric pre-training typically relies on either 2D or 3D pre-text tasks, overlooking the temporal characteristics of autonomous driving as a 4D scene understanding task. In this paper, we address this challenge by introducing a world model-based autonomous driving 4D representation learning framework, dubbed \emph{DriveWorld}, which is capable of pre-training from multi-camera driving …

abstract arxiv attention autonomous autonomous driving cost cs.cv current driving however pre-training representation tasks temporal text training type understanding universal via vision world world models