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

It is well-known that a number of excellent super-resolution (SR) methodsusing convolutional neural networks (CNNs) generate checkerboard artifacts. Acondition to avoid the checkerboard artifacts is proposed in this paper. Sofar, checkerboard artifacts have been mainly studied for linear multiratesystems, but the condition to avoid checkerboard artifacts can not be appliedto CNNs due to the non-linearity of CNNs. We extend the avoiding condition forCNNs, and apply the proposed structure to some typical SR methods to confirmthe effectiveness of the new scheme. Experiment results demonstrate that theproposed structure can perfectly avoid to generate checkerboard artifacts undertwo loss conditions: mean square error and perceptual loss, while keepingexcellent properties that the SR methods have.

Super-Resolution using Convolutional Neural Networks without Any Checkerboard Artifacts