Contrastive Haze-Aware Learning for Dynamic Remote Sensing Image Dehazing

Image dehazing methods aim to recover a clear image from its hazy counterpart. While various dehazing methods have been proposed, their performance on real-world remote sensing (RS) images remains unsatisfying. A key reason is that the complex weather and imaging conditions (e.g., large fields of view) cause the haze condition to dramatically change in different images, while most of the existing methods fail to flexibly adapt their dehazing model to the specific haze condition in each image. To mitigate this problem, we present a contrastive haze-aware learning-based dynamic dehazing method that demonstrates two aspects of advantage. On one hand, a contrastive clustering scheme is used to learn the imagewise haze representation using a set of real-world hazy images in an unsupervised manner, which enables identifying and discriminating the specific haze condition in each given hazy image. On the other hand, with the learned haze representation, a parameter generator can produce haze-aware parameters to dynamically construct a dehazing model for the given hazy image, which empowers us to adaptively dehaze the image based on its specific haze condition and thus improves the generalization ability. In addition, a new contrastive loss defined based on the learned haze representation is further used for model training and leads to better performance. To demonstrate the effectiveness of the proposed method, we evaluate it on two benchmark RS image datasets including various real-world hazy images and observe obvious superiority over other state-of-the-art (SOTA) competitors.