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

Underwater visual perception is essentially important for underwaterexploration, archeology, ecosystem and so on. The low illumination, lightreflections, scattering, absorption and suspended particles inevitably lead tothe critically degraded underwater image quality, which causes great challengeson recognizing the objects from the underwater images. The existing underwaterenhancement methods that aim to promote the underwater visibility, heavilysuffer from the poor image restoration performance and generalization ability.To reduce the difficulty of underwater image enhancement, we introduce themedia transmission map as guidance to assist in image enhancement. We formulatethe interaction between the underwater visual images and the transmission mapto obtain better enhancement results. Even with simple and lightweight networkconfiguration, the proposed method can achieve advanced results of 22.6 dB onthe challenging Test-R90 with an impressive 30 times faster than the existingmodels. Comprehensive experimental results have demonstrated the superiorityand potential on underwater perception. Paper's code is offered on:https://github.com/GroupG-yk/MTUR-Net.

Medium Transmission Map Matters for Learning to Restore Real-World Underwater Images