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

Versatile Video Coding (H.266/VVC) standard achieves better image qualitywhen keeping the same bits than any other conventional image codec, such asBPG, JPEG, and etc. However, it is still attractive and challenging to improvethe image quality with high compression ratio on the basis of traditionalcoding techniques. In this paper, we design the multi-scale grouped densenetwork (MSGDN) to further reduce the compression artifacts by combining themulti-scale and grouped dense block, which are integrated as the post-processnetwork of VVC intra coding. Besides, to improve the subjective quality ofcompressed image, we also present a generative adversarial network (MSGDN-GAN)by utilizing our MSGDN as generator. Across the extensive experiments onvalidation set, our MSGDN trained by MSE losses yields the PSNR of 32.622 onaverage with teams IMC at the bit-rate of 0.15 in Lowrate track. Moreover, ourMSGDN-GAN could achieve the better subjective performance.

Multi-scale Grouped Dense Network for VVC Intra Coding