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

Single Image Super-resolution (SISR) produces high-resolution images withfine spatial resolutions from aremotely sensed image with low spatialresolution. Recently, deep learning and generative adversarial networks(GANs)have made breakthroughs for the challenging task of single imagesuper-resolution (SISR). However, thegenerated image still suffers fromundesirable artifacts such as, the absence of texture-feature representationandhigh-frequency information. We propose a frequency domain-based spatio-temporalremote sensingsingle image super-resolution technique to reconstruct the HRimage combined with generative adversarialnetworks (GANs) on various frequencybands (TWIST-GAN). We have introduced a new method incorporatingWaveletTransform (WT) characteristics and transferred generative adversarial network.The LR image hasbeen split into various frequency bands by using the WT,whereas, the transfer generative adversarial networkpredicts high-frequencycomponents via a proposed architecture. Finally, the inverse transfer ofwaveletsproduces a reconstructed image with super-resolution. The model isfirst trained on an external DIV2 Kdataset and validated with the UC MerceedLandsat remote sensing dataset and Set14 with each image sizeof 256x256.Following that, transferred GANs are used to process spatio-temporal remotesensing images inorder to minimize computation cost differences and improvetexture information. The findings are comparedqualitatively and qualitativelywith the current state-of-art approaches. In addition, we saved about 43% oftheGPU memory during training and accelerated the execution of our simplifiedversion by eliminating batchnormalization layers.

TWIST-GAN: Towards Wavelet Transform and Transferred GAN for Spatio-Temporal Single Image Super Resolution