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

Using more reference frames can significantly improve the compressionefficiency in neural video compression. However, in low-latency scenarios, mostexisting neural video compression frameworks usually use the previous one frameas reference. Or a few frameworks which use the previous multiple frames asreference only adopt a simple multi-reference frames propagation mechanism. Inthis paper, we present a more reasonable multi-reference frames propagationmechanism for neural video compression, called butterfly multi-reference framepropagation mechanism (Butterfly), which allows a more effective feature fusionof multi-reference frames. By this, we can generate more accurate temporalcontext conditional prior for Contextual Coding Module. Besides, when thenumber of decoded frames does not meet the required number of reference frames,we duplicate the nearest reference frame to achieve the requirement, which isbetter than duplicating the furthest one. Experiment results show that ourmethod can significantly outperform the previous state-of-the-art (SOTA), andour neural codec can achieve -7.6% bitrate save on HEVC Class D dataset whencompares with our base single-reference frame model with the same compressionconfiguration.

Butterfly: Multiple Reference Frames Feature Propagation Mechanism for Neural Video Compression