AVD2: Accident Video Diffusion for Accident Video Description

Cheng Li, Keyuan Zhou, Tong Liu, Yu Wang, Mingqiao Zhuang +3 more
2/20/2025
cs.CV

No official code found. Best implementation: An-Answer-tree/AVD2 (90 stars, MIT, last commit 2025-11-18).

Abstract

Traffic accidents present complex challenges for autonomous driving, often featuring unpredictable scenarios that hinder accurate system interpretation and responses. Nonetheless, prevailing methodologies fall short in elucidating the causes of accidents and proposing preventive measures due to the paucity of training data specific to accident scenarios. In this work, we introduce AVD2 (Accident Video Diffusion for Accident Video Description), a novel framework that enhances accident scene understanding by generating accident videos that aligned with detailed natural language descriptions and reasoning, resulting in the contributed EMM-AU (Enhanced Multi-Modal Accident Video Understanding) dataset. Empirical results reveal that the integration of the EMM-AU dataset establishes state-of-the-art performance across both automated metrics and human evaluations, markedly advancing the domains of accident analysis and prevention. Project resources are available at https://an-answer-tree.github.io

View on arXivView PDF

Code Implementations(1)

An-Answer-tree/AVD2Community76%
MIT

[ICRA 2025]AVD2: Accident Video Diffusion for Accident Video Description

900Shell, PythonMay 15, 202411 months agoMIT

Similar Papers

Using Multimodal Large Language Models for Automated Detection of Traffic Safety Critical Events

90% match2024

Abductive Ego-View Accident Video Understanding for Safe Driving Perception

90% match1 repo732026

Hierarchical Reasoning with Vision-Language Models for Incident Reports from Dashcam Videos

89% match1 repo52025

AccidentSim: Generating Vehicle Collision Videos with Physically Realistic Collision Trajectories from Real-World Accident Reports

88% match2025

VRU-Accident: A Vision-Language Benchmark for Video Question Answering and Dense Captioning for Accident Scene Understanding

88% match2025

ScVLM: Enhancing Vision-Language Model for Safety-Critical Event Understanding

88% match1 repo72024

Cite this paper

@article{li2025avd,
  title  = {AVD2: Accident Video Diffusion for Accident Video Description},
  author = {Cheng Li and Keyuan Zhou and Tong Liu and Yu Wang and Mingqiao Zhuang and Huan-ang Gao and Bu Jin and Hao Zhao},
  year   = {2025},
  eprint = {2502.14801},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2502.14801v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2502.14801.svg)](https://codeofpaper.com/paper/2502.14801)

Discussion