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

Recently, several models based on deep neural networks have achieved greatsuccess in terms of both reconstruction accuracy and computational performancefor single image super-resolution. In these methods, the low resolution (LR)input image is upscaled to the high resolution (HR) space using a singlefilter, commonly bicubic interpolation, before reconstruction. This means thatthe super-resolution (SR) operation is performed in HR space. We demonstratethat this is sub-optimal and adds computational complexity. In this paper, wepresent the first convolutional neural network (CNN) capable of real-time SR of1080p videos on a single K2 GPU. To achieve this, we propose a novel CNNarchitecture where the feature maps are extracted in the LR space. In addition,we introduce an efficient sub-pixel convolution layer which learns an array ofupscaling filters to upscale the final LR feature maps into the HR output. Bydoing so, we effectively replace the handcrafted bicubic filter in the SRpipeline with more complex upscaling filters specifically trained for eachfeature map, whilst also reducing the computational complexity of the overallSR operation. We evaluate the proposed approach using images and videos frompublicly available datasets and show that it performs significantly better(+0.15dB on Images and +0.39dB on Videos) and is an order of magnitude fasterthan previous CNN-based methods.

Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network