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

GAN-based image compression schemes have shown remarkable progress lately dueto their high perceptual quality at low bit rates. However, there are two mainissues, including 1) the reconstructed image perceptual degeneration in color,texture, and structure as well as 2) the inaccurate entropy model. In thispaper, we present a novel GAN-based image compression approach with improvedrate-distortion optimization (RDO) process. To achieve this, we utilize theDISTS and MS-SSIM metrics to measure perceptual degeneration in color, texture,and structure. Besides, we absorb the discretized gaussian-laplacian-logisticmixture model (GLLMM) for entropy modeling to improve the accuracy inestimating the probability distributions of the latent representation. Duringthe evaluation process, instead of evaluating the perceptual quality of thereconstructed image via IQA metrics, we directly conduct the Mean Opinion Score(MOS) experiment among different codecs, which fully reflects the actualperceptual results of humans. Experimental results demonstrate that theproposed method outperforms the existing GAN-based methods and thestate-of-the-art hybrid codec (i.e., VVC).

GAN-based Image Compression with Improved RDO Process