AnyScene: 迈向高度可控的任意位置驾驶场景生成及超越
AnyScene: Towards Highly Controllable Driving Scene Generation at Anywhere and Beyond
AI总结：
提出AnyScene框架，通过时空占用扩散Transformer和几何引导视图扩展模块，实现从BEV布局生成语义占用序列和参考无关的多视角驾驶视频，支持精确可控和长时生成。
摘要：
生成高保真且可控的合成数据对于推进端到端自动驾驶至关重要，特别是解决罕见安全关键场景的长尾问题。现有的占用引导方法通常依赖于浅层条件机制和参考帧相关的视频合成，这限制了从任意BEV布局进行细粒度可控性，并限制了其在可扩展模拟中的适用性。在本文中，我们提出了AnyScene，一个统一的以占用为中心的驾驶场景生成框架。AnyScene通过时空占用扩散Transformer从BEV布局生成语义占用序列，该Transformer以自回归方式联合标记BEV和占用特征。这种设计使得从跨数据集和用户定义的BEV输入实现精确可控性，同时自然支持长时生成。基于生成的占用，几何引导视图扩展模块将占用视为规范空间表示，并以无参考和自回归方式合成时间一致的多视角驾驶视频，支持推理时的灵活相机配置。大量实验表明，AnyScene在占用和视频生成方面均达到最先进性能。它展现出对未见和定制布局的强大泛化能力，并为下游任务（如稀疏视图3D重建）提供可衡量的益处。
英文摘要：
Generating high-fidelity and controllable synthetic data is critical for advancing end-to-end autonomous driving, particularly for addressing the long tail of rare safety-critical scenarios. Existing occupancy-guided methods typically rely on shallow conditioning mechanisms and reference-frame-dependent video synthesis, which limits fine-grained controllability from arbitrary BEV layouts and restricts their applicability for scalable simulation. In this paper, we propose AnyScene, a unified occupancy-centric framework for driving scene generation. AnyScene generates semantic occupancy sequences from BEV layouts through a Spatial-Temporal Occupancy Diffusion Transformer that jointly tokenizes BEV and occupancy features in an autoregressive manner. This design enables precise controllability from cross-dataset and user-defined BEV inputs while naturally supporting long-horizon generation. Building upon the generated occupancy, a Geometry-Grounded View Expansion module treats occupancy as the canonical spatial representation and synthesizes temporally consistent multi-view driving videos in a reference-free and autoregressive fashion, supporting flexible camera configurations at inference time. Extensive experiments demonstrate that AnyScene achieves state-of-the-art performance in both occupancy and video generation. It exhibits strong generalization to unseen and customized layouts, and provides measurable benefits for downstream tasks such as sparse-view 3D reconstruction.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
