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

To support the application scenarios where high-resolution (HR) images areurgently needed, various single image super-resolution (SISR) algorithms aredeveloped. However, SISR is an ill-posed inverse problem, which may bringartifacts like texture shift, blur, etc. to the reconstructed images, thus itis necessary to evaluate the quality of super-resolution images (SRIs). Notethat most existing image quality assessment (IQA) methods were developed forsynthetically distorted images, which may not work for SRIs since theirdistortions are more diverse and complicated. Therefore, in this paper, wepropose a no-reference deep-learning image quality assessment method based onfrequency maps because the artifacts caused by SISR algorithms are quitesensitive to frequency information. Specifically, we first obtain thehigh-frequency map (HM) and low-frequency map (LM) of SRI by using Sobeloperator and piecewise smooth image approximation. Then, a two-stream networkis employed to extract the quality-aware features of both frequency maps.Finally, the features are regressed into a single quality value using fullyconnected layers. The experimental results show that our method outperforms allcompared IQA models on the selected three super-resolution quality assessment(SRQA) databases.

A No-Reference Deep Learning Quality Assessment Method for Super-resolution Images Based on Frequency Maps