OccSim:多公里级占据世界模型仿真

Arxiv cs.CV2026-04-01🔗 查看原文
提出OccSim——首个基于占据世界模型的3D仿真器,无需连续驾驶日志或HD地图,仅用单帧初始视图与未来自车动作即可稳定生成>3000帧、超4公里占据地图(稳定生成长度提升>80倍)。系统由引入刚性变换的W-DiT静态占据模型和用于合成道路及动态前景智能体的Layout Generator构成,能合成大规模多样化仿真流,生成数据可用于预训练4D语义占据预测等下游任务,显著提升可扩展性与数据效率。
原文内容
arXiv:2603.28887v1 Announce Type: new
Abstract: Data-driven autonomous driving simulation has long been constrained by its heavy reliance on pre-recorded driving logs or spatial priors, such as HD maps. This fundamental dependency severely limits scalability, restricting open-ended generation capabilities to the finite scale of existing collected datasets. To break this bottleneck, we present OccSim, the first occupancy world model-driven 3D simulator. OccSim obviates the requirement for continuous logs or HD maps; conditioned only on a single initial frame and a sequence of future ego-actions, it can stably generate over 3,000 continuous frames, enabling the continuous construction of large-scale 3D occupancy maps spanning over 4 kilometers for simulation. This represents an >80x improvement in stable generation length over previous state-of-the-art occupancy world models. OccSim is powered by two modules: W-DiT based static occupancy world model and the Layout Generator. W-DiT handl