Disentangled Bad Weather Removal GAN for Pedestrian Detection
Disentangled Bad Weather Removal GAN for Pedestrian Detection
复制标题
DOI：
10.1109/vtc2022-spring54318.2022.9860865
复制
发表时间：
2022-06
期刊：
影响因子：
--
通讯作者：
Hanting Yang;Alexander Carballo;K. Takeda
中科院分区：
文献类型：
--
作者：
Hanting Yang;Alexander Carballo;K. Takeda
恶劣的天气，如下雨和雾霾，会降低拍摄图像的能见度和对比度，并且经常同时发生，这使得情况变得更糟。现有的基于CNN的方法在单独处理每个条件时可以取得令人印象深刻的结果。但很少有著作将除雨除霾放在一个统一的框架下来考虑。此外，当数据分布发生变化时，这些模型的性能会下降。在这项工作中，我们试图找到一种方法，可以消除所有恶劣天气，而无需在单个任务模型和成对的训练数据之间切换，用于行人检测等驾驶场景应用。具体地说，我们采用了一种解纠缠策略，从减法中获得天气层。计算每条管线的两个天气层之间的统计距离。此外，天气层作为信息引导和输入到重建生成器。在RainCityscapes和FoggyCityscapes混合数据集上的实验表明，该方法提高了行人检测器的有效性。最后，我们贡献了一个新的数据集，称为恶劣天气下的真实驾驶场景（RDSBW），其中包含超过70K的真实的恶劣天气图像。
Bad weather such as rain and haze will lower the visibility and contrast of captured images and often occur at the same time, which makes the situation worse. Existing CNN-based methods can achieve impressive results when processing each condition individually. But few works consider removing rain and haze under a unified framework. Besides, these models will experience degraded performance when the distribution of the data changes. In this work, we attempt to find a method that can remove all bad weather without switching between single task models and paired training data for driving scene applications like pedestrian detection. In specific, we adopt a disentanglement strategy to obtain weather layer from subtraction. The statistic distance is calculated between two weather layers from each pipeline. In addition, the weather layer serves as information guidance and input to the reconstruct generator. Experiments on mixed dataset from RainCityscapes and Foggy Cityscapes show that the effectiveness of pedestrian detector is improved. Finally, we contribute a new dataset called Realistic Driving Scene under Bad Weather (RDSBW), which contains over 70K real bad weather images.