# Ctrl-Crash: Controllable Diffusion for Realistic Car Crashes

arXiv: https://arxiv.org/abs/2506.00227 · HTML: https://mlsanity.com/paper/2506.00227/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models.
- Builds on 29 of its 59 references that are in the map.
- First posted on arXiv 30 May 2025.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)

## Builds on (most cited first, 29 of 29)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning](https://mlsanity.com/paper/1805.04687/) (2018)
- [Cosmos World Foundation Model Platform for Physical AI](https://mlsanity.com/paper/2501.03575/) (2025)
- [Compositional Visual Generation with Composable Diffusion Models](https://mlsanity.com/paper/2206.01714/) (2022)
- [Latent Video Diffusion Models for High-Fidelity Long Video Generation](https://mlsanity.com/paper/2211.13221/) (2022)
- [DriveDreamer-2: LLM-Enhanced World Models for Diverse Driving Video Generation](https://mlsanity.com/paper/2403.06845/) (2024)
- [Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic Prior](https://mlsanity.com/paper/2112.05077/) (2021)
- [DriveGAN: Towards a Controllable High-Quality Neural Simulation](https://mlsanity.com/paper/2104.15060/) (2021)
- [GeoSim: Realistic Video Simulation via Geometry-Aware Composition for Self-Driving](https://mlsanity.com/paper/2101.06543/) (2021)
- [DeepAccident: A Motion and Accident Prediction Benchmark for V2X Autonomous Driving](https://mlsanity.com/paper/2304.01168/) (2023)
- [DADA: Driver Attention Prediction in Driving Accident Scenarios](https://mlsanity.com/paper/1912.12148/) (2019)
- [3D-VField: Adversarial Augmentation of Point Clouds for Domain Generalization in 3D Object Detection](https://mlsanity.com/paper/2112.04764/) (2021)
- [Abductive Ego-View Accident Video Understanding for Safe Driving Perception](https://mlsanity.com/paper/2403.00436/) (2024)
- [CtRL-Sim: Reactive and Controllable Driving Agents with Offline Reinforcement Learning](https://mlsanity.com/paper/2403.19918/) (2024)
- [DriveScape: Towards High-Resolution Controllable Multi-View Driving Video Generation](https://mlsanity.com/paper/2409.05463/) (2024)
- [AVD2: Accident Video Diffusion for Accident Video Description](https://mlsanity.com/paper/2502.14801/) (2025)
- [VIENA2: A Driving Anticipation Dataset](https://mlsanity.com/paper/1810.09044/) (2018)
- [Unconditional Priors Matter! Improving Conditional Generation of Fine-Tuned Diffusion Models](https://mlsanity.com/paper/2503.20240/) (2025)
- [Safety-Critical Traffic Simulation with Adversarial Transfer of Driving Intentions](https://mlsanity.com/paper/2503.05180/) (2025)

## Built on by (most cited first, 5 of 5)

- [Self-Refining Video Sampling](https://mlsanity.com/paper/2601.18577/) (2026)
- [Toward Physically Consistent Driving Video World Models under Challenging Trajectories](https://mlsanity.com/paper/2603.24506/) (2026)
- [Cloning Deterministic Worlds: The Critical Role of Latent Geometry in Long-Horizon World Models](https://mlsanity.com/paper/2510.26782/) (2025)
- [A Physics-Grounded Benchmark for Multi-Agent Dynamics in World Models](https://mlsanity.com/paper/2606.28757/) (2026)
- [OpenTwinMap: An Open-Source Digital Twin Generator for Urban Autonomous Driving](https://mlsanity.com/paper/2511.21925/) (2025)

## Abstract (arXiv)

Video diffusion techniques have advanced significantly in recent years; however, they struggle to generate realistic imagery of car crashes due to the scarcity of accident events in most driving datasets. Improving traffic safety requires realistic and controllable accident simulations. To tackle the problem, we propose Ctrl-Crash, a controllable car crash video generation model that conditions on signals such as bounding boxes, crash types, and an initial image frame. Our approach enables counterfactual scenario generation where minor variations in input can lead to dramatically different crash outcomes. To support fine-grained control at inference time, we leverage classifier-free guidance with independently tunable scales for each conditioning signal. Ctrl-Crash achieves state-of-the-art performance across quantitative video quality metrics (e.g., FVD and JEDi) and qualitative measurements based on a human-evaluation of physical realism and video quality compared to prior diffusion-based methods.