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

Information extraction from synthetic aperture radar (SAR) images is heavilyimpaired by speckle noise, hence despeckling is a crucial preliminary step inscene analysis algorithms. The recent success of deep learning envisions a newgeneration of despeckling techniques that could outperform classicalmodel-based methods. However, current deep learning approaches to despecklingrequire supervision for training, whereas clean SAR images are impossible toobtain. In the literature, this issue is tackled by resorting to eithersynthetically speckled optical images, which exhibit different properties withrespect to true SAR images, or multi-temporal SAR images, which are difficultto acquire or fuse accurately. In this paper, inspired by recent works onblind-spot denoising networks, we propose a self-supervised Bayesiandespeckling method. The proposed method is trained employing only noisy SARimages and can therefore learn features of real SAR images rather thansynthetic data. Experiments show that the performance of the proposed approachis very close to the supervised training approach on synthetic data andsuperior on real data in both quantitative and visual assessments.

Speckle2Void: Deep Self-Supervised SAR Despeckling with Blind-Spot Convolutional Neural Networks