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

Convolutional neural networks (CNNs) have recently achieved great success insingle-image super-resolution (SISR). However, these methods tend to produceover-smoothed outputs and miss some textural details. To solve these problems,we propose the Super-Resolution CliqueNet (SRCliqueNet) to reconstruct the highresolution (HR) image with better textural details in the wavelet domain. Theproposed SRCliqueNet firstly extracts a set of feature maps from the lowresolution (LR) image by the clique blocks group. Then we send the set offeature maps to the clique up-sampling module to reconstruct the HR image. Theclique up-sampling module consists of four sub-nets which predict the highresolution wavelet coefficients of four sub-bands. Since we consider the edgefeature properties of four sub-bands, the four sub-nets are connected to theothers so that they can learn the coefficients of four sub-bands jointly.Finally we apply inverse discrete wavelet transform (IDWT) to the output offour sub-nets at the end of the clique up-sampling module to increase theresolution and reconstruct the HR image. Extensive quantitative and qualitativeexperiments on benchmark datasets show that our method achieves superiorperformance over the state-of-the-art methods.

Joint Sub-bands Learning with Clique Structures for Wavelet Domain Super-Resolution