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

High-resolution satellite imagery is a key element for many Earth monitoringapplications. Satellites such as Sentinel-2 feature characteristics that arefavorable for super-resolution algorithms such as aliasing andband-misalignment. Unfortunately the lack of reliable high-resolution (HR)ground truth limits the application of deep learning methods to this task. Inthis work we propose L1BSR, a deep learning-based method for single-imagesuper-resolution and band alignment of Sentinel-2 L1B 10m bands. The method istrained with self-supervision directly on real L1B data by leveragingoverlapping areas in L1B images produced by adjacent CMOS detectors, thus notrequiring HR ground truth. Our self-supervised loss is designed to enforce thesuper-resolved output image to have all the bands correctly aligned. This isachieved via a novel cross-spectral registration network (CSR) which computesan optical flow between images of different spectral bands. The CSR network isalso trained with self-supervision using an Anchor-Consistency loss, which wealso introduce in this work. We demonstrate the performance of the proposedapproach on synthetic and real L1B data, where we show that it obtainscomparable results to supervised methods.

L1BSR: Exploiting Detector Overlap for Self-Supervised Single-Image Super-Resolution of Sentinel-2 L1B Imagery