AnyScene: Towards Highly Controllable Driving Scene Generation at Anywhere and Beyond 事件

AnyScene: Towards Highly Controllable Driving Scene Generation at Anywhere and Beyond arXiv:2605.26113v1 Announce Type: cross Abstract: 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