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

Marine snow, the floating particles in underwater images, severely degradesthe visibility and performance of human and machine vision systems. This paperproposes a novel method to reduce the marine snow interference using deeplearning techniques. We first synthesize realistic marine snow samples bytraining a Generative Adversarial Network (GAN) model and combine them withnatural underwater images to create a paired dataset. We then train a U-Netmodel to perform marine snow removal as an image to image translation task. Ourexperiments show that the U-Net model can effectively remove both synthetic andnatural marine snow with high accuracy, outperforming state-of-the-art methodssuch as the Median filter and its adaptive variant. We also demonstrate therobustness of our method by testing it on the MSRB dataset, which containssynthetic artifacts that our model has not seen during training. Our method isa practical and efficient solution for enhancing underwater images affected bymarine snow.

A deep learning approach for marine snow synthesis and removal