无需重新标注即可生成恶劣天气下的高保真车道图像，提升检测模型鲁棒性。
HG-Lane: High-Fidelity Generation of Lane Scenes under Adverse Weather and Lighting Conditions without Re-annotation
- 基于无重标注的生成框架，模拟雨雪雾等极端场景。
- 在3万张图像的新基准上，模型性能平均提升20.87%。
- 适合自动驾驶感知系统在复杂环境下的可靠性验证。
车道检测是自动驾驶中的关键任务，有助于保障车辆安全运行。然而，现有数据集如CULane和TuSimple在极端天气条件（如雨、雪、雾）下的数据较为有限，导致训练出的检测模型在这些环境中不可靠，可能引发严重安全事故。为此，我们提出HG-Lane——一种无需重标注即可生成恶劣天气与光照条件下高保真车道场景的框架。基于该框架，我们构建了一个包含30,000张图像的新基准，涵盖多种恶劣场景。实验结果表明，该方法显著提升了现有车道检测网络的性能。例如，使用最先进模型CLRNet，新基准上的整体mF1得分提升20.87%；各子类别（整体、正常、雪、雨、雾、夜、暮色）的F1@50分别提升19.75%、8.63%、38.8%、14.96%、26.84%、21.5%和12.04%。代码与数据集已公开于https://github.com/zdc233/HG-Lane。
原文摘要 · Abstract (English)
Lane detection is a crucial task in autonomous driving, as it helps ensure the safe operation of vehicles. However, existing datasets such as CULane and TuSimple contain relatively limited data under extreme weather conditions, including rain, snow, and fog. As a result, detection models trained on these datasets often become unreliable in such environments, which may lead to serious safety-critical failures on the road. To address this issue, we propose HG-Lane, a High-fidelity Generation framework for Lane Scenes under adverse weather and lighting conditions without requiring re-annotation. Based on this framework, we further construct a benchmark that includes adverse weather and lighting scenarios, containing 30,000 images. Experimental results demonstrate that our method consistently and significantly improves the performance of existing lane detection networks. For example, using the state-of-the-art CLRNet, the overall mF1 score on our benchmark increases by 20.87 percent. The F1@50 score for the overall, normal, snow, rain, fog, night, and dusk categories increases by 19.75 percent, 8.63 percent, 38.8 percent, 14.96 percent, 26.84 percent, 21.5 percent, and 12.04 percent, respectively. The code and dataset are available at: https://github.com/zdc233/HG-Lane.
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。