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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Thriving underwater applications demand efficient extreme compressiontechnology to realize the transmission of underwater images (UWIs) in verynarrow underwater bandwidth. However, existing image compression methodsachieve inferior performance on UWIs because they do not consider thecharacteristics of UWIs: (1) Multifarious underwater styles of color shift anddistance-dependent clarity, caused by the unique underwater physical imaging;(2) Massive redundancy between different UWIs, caused by the fact thatdifferent UWIs contain several common ocean objects, which have plenty ofsimilarities in structures and semantics. To remove redundancy among UWIs, wefirst construct an exhaustive underwater multi-scale feature dictionary toprovide coarse-to-fine reference features for UWI compression. Subsequently, anextreme UWI compression network with reference to the feature dictionary(RFD-ECNet) is creatively proposed, which utilizes feature match and referencefeature variant to significantly remove redundancy among UWIs. To align themultifarious underwater styles and improve the accuracy of feature match, anunderwater style normalized block (USNB) is proposed, which utilizes underwaterphysical priors extracted from the underwater physical imaging model tonormalize the underwater styles of dictionary features toward the input.Moreover, a reference feature variant module (RFVM) is designed to adaptivelymorph the reference features, improving the similarity between the referenceand input features. Experimental results on four UWI datasets show that ourRFD-ECNet is the first work that achieves a significant BD-rate saving of 31%over the most advanced VVC.

RFD-ECNet: Extreme Underwater Image Compression with Reference to Feature Dictionar