See Blue Sky: Deep Image Dehaze Using Paired and Unpaired Training Images
This work addresses image dehazing for computer vision applications, offering incremental improvements in sky restoration using paired and unpaired training data.
The paper tackled the problem of image haze removal, particularly the inability to restore clear blue skies, by proposing a cycle generative adversarial network with four loss functions, achieving improved visual quality and realistic sky restoration.
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).