English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Deep learning-based methods have achieved significant performance for imagedefogging. However, existing methods are mainly developed for land scenes andperform poorly when dealing with overwater foggy images, since overwater scenestypically contain large expanses of sky and water. In this work, we propose aPrior map Guided CycleGAN (PG-CycleGAN) for defogging of images with overwaterscenes. To promote the recovery of the objects on water in the image, two lossfunctions are exploited for the network where a prior map is designed to invertthe dark channel and the min-max normalization is used to suppress the sky andemphasize objects. However, due to the unpaired training set, the network maylearn an under-constrained domain mapping from foggy to fog-free image, leadingto artifacts and loss of details. Thus, we propose an intuitive UpscalingInception Module (UIM) and a Long-range Residual Coarse-to-fine framework (LRC)to mitigate this issue. Extensive experiments on qualitative and quantitativecomparisons demonstrate that the proposed method outperforms thestate-of-the-art supervised, semi-supervised, and unsupervised defoggingapproaches.

Unpaired Overwater Image Defogging Using Prior Map Guided CycleGAN