HG-Lane：无需重新标注的恶劣天气与光照条件下高保真车道场景生成
HG-Lane: High-Fidelity Generation of Lane Scenes under Adverse Weather and Lighting Conditions without Re-annotation
无需重新标注即可在雨雪雾与夜间/黄昏条件下合成高保真车道场景图像，可直接作为车道线检测等下游任务的数据增广手段，缓解极端条件数据稀缺导致的模型失效。
原文依据 we propose HG-Lane, a High-fidelity Generation framework for Lane Scenes under adverse weather and lighting conditions, without the need for re-annotation
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论车道线检测是自动驾驶中的一项关键任务，有助于保障车辆的安全运行。然而，现有数据集如 CULane 和 TuSimple 在雨、雪、雾等极端天气条件下的数据相对有限，这使得检测模型在极端条件下不可靠，可能导致道路上严重的安全关键性失效。针对这一方向，我们提出了 HG-Lane，一个面向恶劣天气与光照条件的车道场景高保真生成框架，且无需重新标注。基于该框架，我们进一步提出了一个包含恶劣天气与光照条件的基准，共 30,000 张图像。实验结果表明，我们的方法持续且显著地提升了所有相关车道线检测网络的性能。以最优的 CLRNet 为例，其在我们基准上的整体 mF1 提升了 20.87%。整体、正常、雪、雨、雾、夜间和黄昏类别的 F1@50 分别提升了 19.75%、8.63%、38.8%、14.96%、26.84%、21.5% 和 12.04%。代码与数据集见 https://github.com/zdc233/HG-Lane。
英文原文摘要 1182 字符
Lane detection is a crucial task in autonomous driving, which is conducive to ensuring the safe operation of vehicles. However, current datasets like CULane and TuSimple have relatively limited data under extreme weather conditions, such as rain, snow and fog, which makes detection models unreliable in extreme conditions, potentially leading to serious safety-critical failures on the road. In this direction, we propose HG-Lane, a High-fidelity Generation framework for Lane Scenes under adverse weather and lighting conditions, without the need for re-annotation. Based on our framework, we further propose a benchmark that includes adverse weather and lighting conditions, with 30,000 images. Experiment results demonstrate that our method constantly and significantly improves the performance of all the related lane detection networks. Taking the state-of-the-art CLRNet as an example, the overall mF1 on our benchmark increases by 20.87%. The F1@50 for the overall, normal, snow, rain, fog, night, and dusk categories increases by 19.75%, 8.63%, 38.8%, 14.96%, 26.84%, 21.5%, and 12.04%, respectively. The Code and dataset are available at https://github.com/zdc233/HG-Lane.