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

Motion estimation and motion compensation are indispensable parts of interprediction in video coding. Since the motion vector of objects is mostly infractional pixel units, original reference pictures may not accurately providea suitable reference for motion compensation. In this paper, we propose a deepreference picture generator which can create a picture that is more relevant tothe current encoding frame, thereby further reducing temporal redundancy andimproving video compression efficiency. Inspired by the recent progress ofConvolutional Neural Network(CNN), this paper proposes to use a dilated CNN tobuild the generator. Moreover, we insert the generated deep picture intoVersatile Video Coding(VVC) as a reference picture and perform a comprehensiveset of experiments to evaluate the effectiveness of our network on the latestVVC Test Model VTM. The experimental results demonstrate that our proposedmethod achieves on average 9.7% bit saving compared with VVC under low-delay Pconfiguration.

Dilated convolutional neural network-based deep reference picture generation for video compression