IEEE Trans Image Process. 2017 Jun;26(6):2944-2956. doi: 10.1109/TIP.2017.2691802. Epub 2017 Apr 6.
We introduce a deep network architecture called DerainNet for removing rain streaks from an image. Based on the deep convolutional neural network (CNN), we directly learn the mapping relationship between rainy and clean image detail layers from data. Because we do not possess the ground truth corresponding to real-world rainy images, we synthesize images with rain for training. In contrast to other common strategies that increase depth or breadth of the network, we use image processing domain knowledge to modify the objective function and improve deraining with a modestly sized CNN. Specifically, we train our DerainNet on the detail (high-pass) layer rather than in the image domain. Though DerainNet is trained on synthetic data, we find that the learned network translates very effectively to real-world images for testing. Moreover, we augment the CNN framework with image enhancement to improve the visual results. Compared with the state-of-the-art single image de-raining methods, our method has improved rain removal and much faster computation time after network training.
我们引入了一种名为 DerainNet 的深度网络架构，用于从图像中去除雨条纹。基于深度卷积神经网络（CNN），我们直接从数据中学习雨和干净图像细节层之间的映射关系。由于我们没有与真实世界的雨图像相对应的真实数据，我们使用合成图像进行训练。与其他常见的增加网络深度或宽度的策略不同，我们使用图像处理领域的知识来修改目标函数，并使用大小适中的 CNN 来改进去雨效果。具体来说，我们在细节（高通）层而不是在图像域中训练我们的 DerainNet。尽管 DerainNet 是在合成数据上进行训练的，但我们发现经过训练的网络可以非常有效地转换为真实世界的图像进行测试。此外，我们使用图像增强来扩充 CNN 框架，以提高视觉效果。与最先进的单图像去雨方法相比，我们的方法在网络训练后提高了去雨效果，并且计算时间大大缩短。
