Domain Adaptation for Image Dehazing
This addresses the generalization issue in image dehazing for computer vision applications, but it is incremental as it builds on existing domain adaptation and dehazing techniques.
The paper tackles the problem of domain shift in image dehazing, where models trained on synthetic hazy images fail to generalize to real ones, by proposing a domain adaptation method that combines image translation and dehazing modules, achieving favorable performance against state-of-the-art algorithms on both synthetic and real-world images.
Image dehazing using learning-based methods has achieved state-of-the-art performance in recent years. However, most existing methods train a dehazing model on synthetic hazy images, which are less able to generalize well to real hazy images due to domain shift. To address this issue, we propose a domain adaptation paradigm, which consists of an image translation module and two image dehazing modules. Specifically, we first apply a bidirectional translation network to bridge the gap between the synthetic and real domains by translating images from one domain to another. And then, we use images before and after translation to train the proposed two image dehazing networks with a consistency constraint. In this phase, we incorporate the real hazy image into the dehazing training via exploiting the properties of the clear image (e.g., dark channel prior and image gradient smoothing) to further improve the domain adaptivity. By training image translation and dehazing network in an end-to-end manner, we can obtain better effects of both image translation and dehazing. Experimental results on both synthetic and real-world images demonstrate that our model performs favorably against the state-of-the-art dehazing algorithms.