论文标题
夜间场景与大型真实数据集解析
Night-time Scene Parsing with a Large Real Dataset
论文作者
论文摘要
尽管近年来在场景分析上取得了巨大进展，但大多数现有作品都假设输入图像是在白天的照明条件良好。在这项工作中，我们旨在解决夜间场景解析（NTSP）问题，该问题有两个主要的挑战：1）标记的夜间数据稀缺，2）过度和不足的访问可能会在输入夜间图像中共发生，并且在现有管道中没有明确建模。为了解决夜间数据的稀缺性，我们收集了一个名为{\ it Nightcity}的小说标签数据集，其4,297个真实的夜间图像，带有地面真相像素级的语义注释。据我们所知，Nightcity是NTSP最大的数据集。此外，我们还提出了一个曝光感知框架，以通过明确学习的曝光功能来扩大分割过程来解决NTSP问题。广泛的实验表明，对夜城的培训可以显着改善NTSP的性能，并且我们的曝光感知模型优于最新方法，从而在我们的数据集和现有数据集中产生了最佳性能。
Although huge progress has been made on scene analysis in recent years, most existing works assume the input images to be in day-time with good lighting conditions. In this work, we aim to address the night-time scene parsing (NTSP) problem, which has two main challenges: 1) labeled night-time data are scarce, and 2) over- and under-exposures may co-occur in the input night-time images and are not explicitly modeled in existing pipelines. To tackle the scarcity of night-time data, we collect a novel labeled dataset, named {\it NightCity}, of 4,297 real night-time images with ground truth pixel-level semantic annotations. To our knowledge, NightCity is the largest dataset for NTSP. In addition, we also propose an exposure-aware framework to address the NTSP problem through augmenting the segmentation process with explicitly learned exposure features. Extensive experiments show that training on NightCity can significantly improve NTSP performances and that our exposure-aware model outperforms the state-of-the-art methods, yielding top performances on our dataset as well as existing datasets.
