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

Remote sensing images are essential for many earth science applications, buttheir quality can be degraded due to limitations in sensor technology andcomplex imaging environments. To address this, various remote sensing imagedeblurring methods have been developed to restore sharp, high-quality imagesfrom degraded observational data. However, most traditional model-baseddeblurring methods usually require predefined hand-craft prior assumptions,which are difficult to handle in complex applications, and most deeplearning-based deblurring methods are designed as a black box, lackingtransparency and interpretability. In this work, we propose a novel blinddeblurring learning framework based on alternating iterations of shrinkagethresholds, alternately updating blurring kernels and images, with thetheoretical foundation of network design. Additionally, we propose a learnableblur kernel proximal mapping module to improve the blur kernel evaluation inthe kernel domain. Then, we proposed a deep proximal mapping module in theimage domain, which combines a generalized shrinkage threshold operator and amulti-scale prior feature extraction block. This module also introduces anattention mechanism to adaptively adjust the prior importance, thus avoidingthe drawbacks of hand-crafted image prior terms. Thus, a novel multi-scalegeneralized shrinkage threshold network (MGSTNet) is designed to specificallyfocus on learning deep geometric prior features to enhance image restoration.Experiments demonstrate the superiority of our MGSTNet framework on remotesensing image datasets compared to existing deblurring methods.

A Multi-scale Generalized Shrinkage Threshold Network for Image Blind Deblurring in Remote Sensing