Ctrl-Crash: Controllable Diffusion for Realistic Car Crashes
This work addresses the need for realistic and controllable accident simulations to improve traffic safety, representing a domain-specific advancement in video generation.
The paper tackles the problem of generating realistic car crash videos, which is challenging due to scarce accident data in driving datasets, and proposes Ctrl-Crash, a controllable diffusion model that achieves state-of-the-art performance in video quality metrics and human evaluations of realism.
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.