AI RESEARCH
Risk-Controllable Multi-View Diffusion for Driving Scenario Generation
arXiv CS.CV
•
ArXi:2603.11534v1 Announce Type: new Generating safety-critical driving scenarios is crucial for evaluating and improving autonomous driving systems, but long-tail risky situations are rarely observed in real-world data and difficult to specify through manual scenario design. Existing generative approaches typically treat risk as an after-the-fact label and struggle to maintain geometric consistency in multi-view driving scenes. We present RiskMV-DPO, a general and systematic pipeline for physically-informed, risk-controllable multi-view scenario generation.