论文标题
GPS玻璃：使用白天视频和GPS数据学习夜间语义细分
GPS-GLASS: Learning Nighttime Semantic Segmentation Using Daytime Video and GPS data
论文作者
论文摘要
自主驾驶的语义细分应在各种野外环境中具有鲁棒性。由于缺乏带注释的夜间图像和白天图像的较大域间隙，夜间语义细分尤其具有挑战性。在本文中，我们为夜间语义细分提出了一个新颖的基于GPS的培训框架。给定白天和夜间图像的GPS对齐，我们执行跨域对应关系匹配以获得像素级伪监督。此外，我们在白天视频帧之间进行流量估计，并应用基于GPS的缩放量表以获取另一个像素级伪监督。使用信心图的这些伪监督，我们训练一个夜间语义分割网络，而无需夜间图像的任何注释。实验结果证明了该方法对几个夜间语义分割数据集的有效性。我们的源代码可在https://github.com/jimmy9704/gps-glass上找到。
Semantic segmentation for autonomous driving should be robust against various in-the-wild environments. Nighttime semantic segmentation is especially challenging due to a lack of annotated nighttime images and a large domain gap from daytime images with sufficient annotation. In this paper, we propose a novel GPS-based training framework for nighttime semantic segmentation. Given GPS-aligned pairs of daytime and nighttime images, we perform cross-domain correspondence matching to obtain pixel-level pseudo supervision. Moreover, we conduct flow estimation between daytime video frames and apply GPS-based scaling to acquire another pixel-level pseudo supervision. Using these pseudo supervisions with a confidence map, we train a nighttime semantic segmentation network without any annotation from nighttime images. Experimental results demonstrate the effectiveness of the proposed method on several nighttime semantic segmentation datasets. Our source code is available at https://github.com/jimmy9704/GPS-GLASS.
