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

Deep learning based single image super-resolution (SR) methods have beenrapidly evolved over the past few years and have yielded state-of-the-artperformances over conventional methods. Since these methods usually minimizedl1 loss between the output SR image and the ground truth image, they yieldedvery high peak signal-to-noise ratio (PSNR) that is inversely proportional tothese losses. Unfortunately, minimizing these losses inevitably lead to blurrededges due to averaging of plausible solutions. Recently, SRGAN was proposed toavoid this average effect by minimizing perceptual losses instead of l1 lossand it yielded perceptually better SR images (or images with sharp edges) atthe price of lowering PSNR. In this paper, we propose SREdgeNet, edge enhancedsingle image SR network, that was inspired by conventional SR theories so thataverage effect could be avoided not by changing the loss, but by changing theSR network property with the same l1 loss. Our SREdgeNet consists of 3sequential deep neural network modules: the first module is anystate-of-the-art SR network and we selected a variant of EDSR. The secondmodule is any edge detection network taking the output of the first SR moduleas an input and we propose DenseEdgeNet for this module. Lastly, the thirdmodule is merging the outputs of the first and second modules to yield edgeenhanced SR image and we propose MergeNet for this module. Qualitatively, ourproposed method yielded images with sharp edges compared to otherstate-of-the-art SR methods. Quantitatively, our SREdgeNet yieldedstate-of-the-art performance in terms of structural similarity (SSIM) whilemaintained comparable PSNR for x8 enlargement.

SREdgeNet: Edge Enhanced Single Image Super Resolution using Dense Edge Detection Network and Feature Merge Network