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

Video super-resolution aims at generating a high-resolution video from itslow-resolution counterpart. With the rapid rise of deep learning, many recentlyproposed video super-resolution methods use convolutional neural networks inconjunction with explicit motion compensation to capitalize on statisticaldependencies within and across low-resolution frames. Two common issues of suchmethods are noteworthy. Firstly, the quality of the final reconstructed HRvideo is often very sensitive to the accuracy of motion estimation. Secondly,the warp grid needed for motion compensation, which is specified by the twoflow maps delineating pixel displacements in horizontal and verticaldirections, tends to introduce additional errors and jeopardize the temporalconsistency across video frames. To address these issues, we propose a noveldynamic local filter network to perform implicit motion estimation andcompensation by employing, via locally connected layers, sample-specific andposition-specific dynamic local filters that are tailored to the target pixels.We also propose a global refinement network based on ResBlock and autoencoderstructures to exploit non-local correlations and enhance the spatialconsistency of super-resolved frames. The experimental results demonstrate thatthe proposed method outperforms the state-of-the-art, and validate its strengthin terms of local transformation handling, temporal consistency as well as edgesharpness.

End-To-End Trainable Video Super-Resolution Based on a New Mechanism for Implicit Motion Estimation and Compensation