Ctrl-Crash: Controllable Diffusion for Realistic Car Crashes

• URL: http://arxiv.org/abs/2506.00227v1
• Date: Fri, 30 May 2025 21:04:38 GMT
• Title: Ctrl-Crash: Controllable Diffusion for Realistic Car Crashes
• Authors: Anthony Gosselin, Ge Ya Luo, Luis Lara, Florian Golemo, Derek Nowrouzezahrai, Liam Paull, Alexia Jolicoeur-Martineau, Christopher Pal,
• Abstract summary: Ctrl-Crash is a controllable car crash video generation model that conditions on signals such as bounding boxes, crash types, and an initial image frame.<n>Our approach enables counterfactual scenario generation where minor variations in input can lead to dramatically different crash outcomes.
• Score: 26.71659319735027
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Causal-Entity Reflected Egocentric Traffic Accident Video Synthesis [78.14763828578904]
  Egocentricly comprehending the causes and effects of car accidents is crucial for the safety of self-driving cars.<n>This work argues that precisely identifying the accident participants and capturing their related behaviors are of critical importance.<n>We propose a novel diffusion model, Causal-VidSyn, for synthesizing egocentric traffic accident videos.
  arXiv  Detail & Related papers  (2025-06-29T14:37:48Z)
• Simulating the Unseen: Crash Prediction Must Learn from What Did Not Happen [41.21764593956842]
  Traffic safety science has long been hindered by a fundamental data paradox: the crashes we most wish to prevent are precisely those events we rarely observe.<n>Existing crash-frequency models and surrogate safety metrics rely heavily on sparse, noisy, and under-reported records.<n>We argue that the path to achieving Vision Zero requires a paradigm shift from traditional crash-only learning to a new form of counterfactual safety learning.
  arXiv  Detail & Related papers  (2025-05-27T20:33:07Z)
• AccidentSim: Generating Physically Realistic Vehicle Collision Videos from Real-World Accident Reports [12.774506031982154]
  AccidentSim is a novel framework that generates physically realistic vehicle collision videos.<n> AccidentSim replicates post-collision vehicle trajectories from the physical and contextual information in the accident reports.
  arXiv  Detail & Related papers  (2025-03-26T15:50:42Z)
• EQ-TAA: Equivariant Traffic Accident Anticipation via Diffusion-Based Accident Video Synthesis [79.25588905883191]
  Traffic Accident Anticipation (TAA) in traffic scenes is a challenging problem for achieving zero fatalities in the future.<n>We propose an Attentive Video Diffusion (AVD) model that synthesizes additional accident video clips.
  arXiv  Detail & Related papers  (2025-03-16T01:56:38Z)
• NsBM-GAT: A Non-stationary Block Maximum and Graph Attention Framework for General Traffic Crash Risk Prediction [11.444259609536164]
  Existing crash risk prediction models rely on hypothetical scenarios deemed dangerous by researchers.<n>Dashcam videos capture the pre-crash behavior of individual vehicles, but they often lack critical information about the movements of surrounding vehicles.<n>We propose a novel non-stationary extreme value theory (EVT) to capture the interactive behavior between a vehicle and its surrounding vehicles.
  arXiv  Detail & Related papers  (2025-03-06T02:12:40Z)
• Mitigating Covariate Shift in Imitation Learning for Autonomous Vehicles Using Latent Space Generative World Models [60.87795376541144]
  A world model is a neural network capable of predicting an agent's next state given past states and actions.<n>During end-to-end training, our policy learns how to recover from errors by aligning with states observed in human demonstrations.<n>We present qualitative and quantitative results, demonstrating significant improvements upon prior state of the art in closed-loop testing.
  arXiv  Detail & Related papers  (2024-09-25T06:48:25Z)
• SAFE-SIM: Safety-Critical Closed-Loop Traffic Simulation with Diffusion-Controllable Adversaries [94.84458417662407]
  We introduce SAFE-SIM, a controllable closed-loop safety-critical simulation framework. Our approach yields two distinct advantages: 1) generating realistic long-tail safety-critical scenarios that closely reflect real-world conditions, and 2) providing controllable adversarial behavior for more comprehensive and interactive evaluations. We validate our framework empirically using the nuScenes and nuPlan datasets across multiple planners, demonstrating improvements in both realism and controllability.
  arXiv  Detail & Related papers  (2023-12-31T04:14:43Z)
• Augmenting Ego-Vehicle for Traffic Near-Miss and Accident Classification Dataset using Manipulating Conditional Style Translation [0.3441021278275805]
  There is no difference between accident and near-miss at the time before the accident happened. Our contribution is to redefine the accident definition and re-annotate the accident inconsistency on DADA-2000 dataset together with near-miss. The proposed method integrates two different components: conditional style translation (CST) and separable 3-dimensional convolutional neural network (S3D)
  arXiv  Detail & Related papers  (2023-01-06T22:04:47Z)
• Driving-Signal Aware Full-Body Avatars [49.89791440532946]
  We present a learning-based method for building driving-signal aware full-body avatars. Our model is a conditional variational autoencoder that can be animated with incomplete driving signals. We demonstrate the efficacy of our approach on the challenging problem of full-body animation for virtual telepresence.
  arXiv  Detail & Related papers  (2021-05-21T16:22:38Z)
• Generating and Characterizing Scenarios for Safety Testing of Autonomous Vehicles [86.9067793493874]
  We propose efficient mechanisms to characterize and generate testing scenarios using a state-of-the-art driving simulator. We use our method to characterize real driving data from the Next Generation Simulation (NGSIM) project. We rank the scenarios by defining metrics based on the complexity of avoiding accidents and provide insights into how the AV could have minimized the probability of incurring an accident.
  arXiv  Detail & Related papers  (2021-03-12T17:00:23Z)
• A model for traffic incident prediction using emergency braking data [77.34726150561087]
  We address the fundamental problem of data scarcity in road traffic accident prediction by training our model on emergency braking events instead of accidents. We present a prototype implementing a traffic incident prediction model for Germany based on emergency braking data from Mercedes-Benz vehicles.
  arXiv  Detail & Related papers  (2021-02-12T18:17:12Z)
• Enhanced Transfer Learning for Autonomous Driving with Systematic Accident Simulation [3.2456691142503256]
  We show that transfer learning on simulated data sets provide better generalization and collision avoidance. Our results illustrate that information from a model trained on simulated data can be inferred to a model trained on real-world data.
  arXiv  Detail & Related papers  (2020-07-23T17:27:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.