Lane detection is a vital task for vehicles to navigate and localize their position on the road. To ensure reliable driving, lane detection models must have robust generalization performance in various road environments. However, despite the advanced performance in the trained domain, their generalization performance still falls short of expectations due to the domain discrepancy. To bridge this gap, we propose a novel generative framework using HD Maps for Single-Source Domain Generalization (SSDG) in lane detection. We first generate numerous front-view images from lane markings of HD Maps. Next, we strategically select a core subset among the generated images using (i) lane structure and (ii) road surrounding criteria to maximize their diversity. In the end, utilizing this core set, we train lane detection models to boost their generalization performance. We validate that our generative framework from HD Maps outperforms the Domain Adaptation model MLDA with +3.01%p accuracy improvement, even though we do not access the target domain images.

翻译：车道检测是车辆在道路上导航与定位的关键任务。为确保可靠驾驶，车道检测模型必须在多样道路环境中具备稳健的泛化性能。然而，尽管在训练域中表现出先进性能，由于域差异的存在，其泛化能力仍未能达到预期。为弥合这一差距，我们提出一种基于高精地图的新型生成框架，用于车道检测中的单源域泛化。我们首先从高精地图的车道标线生成大量前视图像；随后，通过（i）车道结构与（ii）道路环境双重准则，在生成图像中策略性选取核心子集以最大化其多样性；最终，利用该核心集训练车道检测模型以提升其泛化性能。实验验证表明，即使未接触目标域图像，本框架生成的高精地图数据仍超越域适应模型MLDA，实现+3.01%的准确率提升。