paper-with-me

Papers

Ctrl-Crash: Controllable Diffusion for Realistic Car Crashes

2025-05-30 · Anthony Gosselin, Ge Ya Luo, Luis Lara, Florian Golemo, Derek Nowrouzezahrai, Liam Paull, Alexia Jolicoeur-Martineau, Christopher Pal

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.

📄 PDF Abstract BibTeX arXiv:2506.00227

Code (0)

등록된 구현이 없습니다.

Tasks

counterfactualVideo Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

A Trajectory-free Crash Detection Framework with Generative Approach and Segment Map Diffusion

2025-11-17 · Weiying Shen, Hao Yu, Yu Dong, Pan Liu 외 arxiv

Real-time crash detection is essential for developing proactive safety management strategy and enhancing overall traffic efficiency. To address the limitations associated with trajectory acquisition and vehicle tracking,…

PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation

2025-09-24 · Chen Wang, Chuhao Chen, Yiming Huang, Zhiyang Dou 외 arxiv

Existing video generation models excel at producing photo-realistic videos from text or images, but often lack physical plausibility and 3D controllability. To overcome these limitations, we introduce PhysCtrl, a novel f…

Video Generation

Assessing the Role of Intersection Proximity in Pedestrian Crashes: Insights from Data Mining Approach

2026-04-30 · Ahmed Hossain, Xiaoduan Sun, Subasish Das arxiv

Although intersections are the most complex parts of the roadway network, pedestrian crashes at non-intersection locations are disproportionately frequent, highlighting a serious traffic safety concern. This study invest…

Complex network analysis of cryptocurrency market during crashes

2024-05-09 · Kundan Mukhia, Anish rai, SR Luwang, Md Nurujjaman 외

This paper identifies the cryptocurrency market crashes and analyses its dynamics using the complex network. We identify three distinct crashes during 2017-20, and the analysis is carried out by dividing the time series …

DeepAnalyze: Learning to Localize Crashes at Scale

2021-09-29 · Manish Shetty, Chetan Bansal, Suman Nath, Sean Bowles 외

Crash localization, an important step in debugging crashes, is challenging when dealing with an extremely large number of diverse applications and platforms and underlying root causes. Large-scale error reporting systems…

Multi-Task Learning