Ctrl-Crash: Controllable Diffusion for Realistic Car Crashes

TL;DR

Ctrl-Crash is a novel controllable diffusion model that generates realistic car crash videos conditioned on various signals, enabling detailed accident simulations for improved traffic safety analysis.

Contribution

It introduces a controllable diffusion framework for realistic car crash video generation with fine-grained input control and state-of-the-art performance.

Findings

Achieves superior quantitative metrics like FVD and JEDi.

Outperforms prior methods in human evaluations of realism.

Enables counterfactual scenario generation with input variations.

Abstract

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.