用合成数据提升自动驾驶事故预判能力，解决真实数据不足问题。
Learning from the Unseen: Generative Data Augmentation for Geometric-Semantic Accident Anticipation
- 通过结构化提示生成符合真实数据统计特征的高保真驾驶场景。
- 结合图神经网络与语义信息，动态建模道路参与者空间与语义关系。
- 构建新基准数据集，验证方法在多场景下显著提升预判准确率与提前量。
交通事故预判是自动驾驶中的关键挑战，受限于道路使用者交互建模的复杂性及多样、大规模数据集的稀缺。为此，我们提出一种双路径框架：一方面，采用由结构化提示引导的视频生成流程，从现有数据中提取特征分布，生成与真实数据统计模式一致的高保真合成驾驶场景；另一方面，设计融合语义线索的图神经网络，实现对参与者之间空间与语义关系的动态推理。为验证方法有效性，我们发布了包含标准化精细标注视频序列的新基准数据集，覆盖广泛区域、天气与交通条件。在现有数据集及新基准上的评估均显示准确率和预判提前时间显著提升，表明该框架能有效缓解数据瓶颈，增强自动驾驶系统的可靠性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。