论文标题
请参阅蓝天：使用配对和未配对的训练图像的深度图像脱去
See Blue Sky: Deep Image Dehaze Using Paired and Unpaired Training Images
论文作者
论文摘要
近年来，消除图像雾化的问题引起了广泛的关注。但是，大多数现有的雾霾去除方法无法用透明的蓝天恢复场景，因为原始雾兹图像中对象的颜色和纹理信息不足。为了解决这个问题，我们提出了一个循环生成的对抗网络，以构建一种新型的端到端图像狂热模型。我们采用户外图像数据集来训练我们的模型，其中包括一组现实世界中未配对的图像数据集和一组配对的图像数据集，以确保生成的图像靠近真实场景。基于循环结构，我们的模型添加了四种不同类型的损耗函数，以限制效果，包括对抗性损失，周期一致性损失，光真实损失和配对的L1损失。这四个约束可以提高此类降级图像的总体质量，以更好地视觉吸引力，并确保图像重建以防止失真。提出的模型可以消除图像的阴霾，还可以恢复图像的天空干净和蓝色（例如在阳光明媚的天气中捕获的）。
The issue of image haze removal has attracted wide attention in recent years. However, most existing haze removal methods cannot restore the scene with clear blue sky, since the color and texture information of the object in the original haze image is insufficient. To remedy this, we propose a cycle generative adversarial network to construct a novel end-to-end image dehaze model. We adopt outdoor image datasets to train our model, which includes a set of real-world unpaired image dataset and a set of paired image dataset to ensure that the generated images are close to the real scene. Based on the cycle structure, our model adds four different kinds of loss function to constrain the effect including adversarial loss, cycle consistency loss, photorealism loss and paired L1 loss. These four constraints can improve the overall quality of such degraded images for better visual appeal and ensure reconstruction of images to keep from distortion. The proposed model could remove the haze of images and also restore the sky of images to be clean and blue (like captured in a sunny weather).
