# Risk-Controllable Multi-View Diffusion for Driving Scenario Generation

arXiv: https://arxiv.org/abs/2603.11534 · HTML: https://mlsanity.com/paper/2603.11534/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Generative simulation for driving, one of 9 directions in End-to-end autonomous driving.
- Builds on 25 of its 48 references that are in the map.
- First posted on arXiv 12 Mar 2026.

## Placed in

- End-to-end autonomous driving / [Generative simulation for driving](https://mlsanity.com/driving/generative-simulation-for-driving/)

## Builds on (most cited first, 25 of 25)

- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [Diffusion Model Alignment Using Direct Preference Optimization](https://mlsanity.com/paper/2311.12908/) (2023)
- [GAIA-1: A Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2309.17080/) (2023)
- [MagicDrive: Street View Generation with Diverse 3D Geometry Control](https://mlsanity.com/paper/2310.02601/) (2023)
- [GenAD: Generative End-to-End Autonomous Driving](https://mlsanity.com/paper/2402.11502/) (2024)
- [DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation](https://mlsanity.com/paper/2403.06845/) (2024)
- [Panacea: Panoramic and Controllable Video Generation for Autonomous Driving](https://mlsanity.com/paper/2311.16813/) (2023)
- [On a Formal Model of Safe and Scalable Self-driving Cars](https://mlsanity.com/paper/1708.06374/) (2017)
- [DriveGAN: Towards a Controllable High-Quality Neural Simulation](https://mlsanity.com/paper/2104.15060/) (2021)
- [ChatScene: Knowledge-Enabled Safety-Critical Scenario Generation for Autonomous Vehicles](https://mlsanity.com/paper/2405.14062/) (2024)
- [MagicDrive-V2: High-Resolution Long Video Generation for Autonomous Driving with Adaptive Control](https://mlsanity.com/paper/2411.13807/) (2024)
- [Scenic: A Language for Scenario Specification and Scene Generation](https://mlsanity.com/paper/1809.09310/) (2018)
- [Adaptive Stress Testing for Autonomous Vehicles](https://mlsanity.com/paper/1902.01909/) (2019)
- [DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models](https://mlsanity.com/paper/2506.03517/) (2025)
- [Criticality Metrics for Automated Driving: A Review and Suitability Analysis of the State of the Art](https://mlsanity.com/paper/2108.02403/) (2021)
- [DGGT: Feedforward 4D Reconstruction of Dynamic Driving Scenes using Unposed Images](https://mlsanity.com/paper/2512.03004/) (2025)
- [VGGDrive: Empowering Vision-Language Models with Cross-View Geometric Grounding for Autonomous Driving](https://mlsanity.com/paper/2602.20794/) (2026)
- [LLM-attacker: Enhancing Closed-loop Adversarial Scenario Generation for Autonomous Driving with Large Language Models](https://mlsanity.com/paper/2501.15850/) (2025)
- [Text2Scenario: Text-Driven Scenario Generation for Autonomous Driving Test](https://mlsanity.com/paper/2503.02911/) (2025)
- [Seeing Beyond Views: Multi-View Driving Scene Video Generation with Holistic Attention](https://mlsanity.com/paper/2412.03520/) (2024)
- [SafeDrive: Knowledge- and Data-Driven Risk-Sensitive Decision-Making for Autonomous Vehicles with Large Language Models](https://mlsanity.com/paper/2412.13238/) (2024)
- [RiskNet: Interaction-Aware Risk Forecasting for Autonomous Driving in Long-Tail Scenarios](https://mlsanity.com/paper/2504.15541/) (2025)
- [Mind the Generative Details: Direct Localized Detail Preference Optimization for Video Diffusion Models](https://mlsanity.com/paper/2601.04068/) (2026)
- [PriorFusion: Unified Integration of Priors for Robust Road Perception in Autonomous Driving](https://mlsanity.com/paper/2507.23309/) (2025)

## Built on by (most cited first, 1 of 1)

- [Rethinking Foundation Model Collaboration: Enhancing Specialized Models through Proxy Task Reasoning](https://mlsanity.com/paper/2606.31157/) (2026)

## Abstract (arXiv)

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. By integrating target risk levels with physically-grounded risk modeling, we synthesize diverse and high-stakes dynamic trajectories that serve as explicit geometric anchors for a diffusion-based video generator. To ensure spatial-temporal coherence and geometric fidelity, we introduce a geometry-appearance alignment module and a region-aware direct preference optimization (RA-DPO) strategy with motion-aware masking to focus learning on localized dynamic regions. Experiments on the nuScenes dataset show that RiskMV-DPO can freely generate a wide spectrum of diverse scenarios while maintaining visual quality, improving 3D detection mAP from 18.17 to 30.50 and reducing FID to 15.70. Our work shifts the role of world models from passive environment prediction to proactive, risk-controllable synthesis, providing a scalable toolchain for the development of embodied intelligence.