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

Despeckling is a crucial noise reduction task in improving the quality ofsynthetic aperture radar (SAR) images. Directly obtaining noise-free SAR imagesis a challenging task that has hindered the development of accurate despecklingalgorithms. The advent of deep learning has facilitated the study of denoisingmodels that learn from only noisy SAR images. However, existing methods dealsolely with single-polarization images and cannot handle the multi-polarizationimages captured by modern satellites. In this work, we present an extension ofthe existing model for generating single-polarization SAR images to handlemulti-polarization SAR images. Specifically, we propose a novel self-superviseddespeckling approach called channel masking, which exploits the relationshipbetween polarizations. Additionally, we utilize a spatial masking method thataddresses pixel-to-pixel correlations to further enhance the performance of ourapproach. By effectively incorporating multiple polarization information, ourmethod surpasses current state-of-the-art methods in quantitative evaluation inboth synthetic and real-world scenarios.

PolMERLIN: Self-Supervised Polarimetric Complex SAR Image Despeckling with Masked Networks