Learning from the Unseen: Generative Data Augmentation for Geometric-Semantic Accident Anticipation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Guan, Yanchen, Liao, Haicheng, Wang, Chengyue, Liu, Xingcheng, Zhang, Jiaxun, Li, Keqiang, Li, Zhenning
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910182932480000
author Guan, Yanchen
Liao, Haicheng
Wang, Chengyue
Liu, Xingcheng
Zhang, Jiaxun
Li, Keqiang
Li, Zhenning
author_facet Guan, Yanchen
Liao, Haicheng
Wang, Chengyue
Liu, Xingcheng
Zhang, Jiaxun
Li, Keqiang
Li, Zhenning
contents Anticipating traffic accidents is a critical yet unresolved problem for autonomous driving, hindered by the inherent complexity of modeling interactions between road users and the limited availability of diverse, large-scale datasets. To address these issues, we propose a dual-path framework. On the one hand, we employ a video synthesis pipeline that, guided by structured prompts, derives feature distributions from existing corpora and produces high-fidelity synthetic driving scenes consistent with the statistical patterns of real data. On the other hand, we design a graph neural network enriched with semantic cues, enabling dynamic reasoning over both spatial and semantic relations among participants. To validate the effectiveness of our approach, we release a new benchmark dataset containing standardized, finely annotated video sequences that cover a broad spectrum of regions, weather, and traffic conditions. Evaluations across existing datasets and our new benchmark confirm notable gains in both accuracy and anticipation lead time, highlighting the capacity of the proposed framework to mitigate current data bottlenecks and enhance the reliability of autonomous driving systems.
format Preprint
id arxiv_https___arxiv_org_abs_2605_00051
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Learning from the Unseen: Generative Data Augmentation for Geometric-Semantic Accident Anticipation
Guan, Yanchen
Liao, Haicheng
Wang, Chengyue
Liu, Xingcheng
Zhang, Jiaxun
Li, Keqiang
Li, Zhenning
Computer Vision and Pattern Recognition
Machine Learning
Anticipating traffic accidents is a critical yet unresolved problem for autonomous driving, hindered by the inherent complexity of modeling interactions between road users and the limited availability of diverse, large-scale datasets. To address these issues, we propose a dual-path framework. On the one hand, we employ a video synthesis pipeline that, guided by structured prompts, derives feature distributions from existing corpora and produces high-fidelity synthetic driving scenes consistent with the statistical patterns of real data. On the other hand, we design a graph neural network enriched with semantic cues, enabling dynamic reasoning over both spatial and semantic relations among participants. To validate the effectiveness of our approach, we release a new benchmark dataset containing standardized, finely annotated video sequences that cover a broad spectrum of regions, weather, and traffic conditions. Evaluations across existing datasets and our new benchmark confirm notable gains in both accuracy and anticipation lead time, highlighting the capacity of the proposed framework to mitigate current data bottlenecks and enhance the reliability of autonomous driving systems.
title Learning from the Unseen: Generative Data Augmentation for Geometric-Semantic Accident Anticipation
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2605.00051