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

Recently, learned image compression methods have been actively studied. Amongthem, entropy-minimization based approaches have achieved superior resultscompared to conventional image codecs such as BPG and JPEG2000. However, thequality enhancement and rate-minimization are conflictively coupled in theprocess of image compression. That is, maintaining high image quality entailsless compression and vice versa. However, by jointly training separate qualityenhancement in conjunction with image compression, the coding efficiency can beimproved. In this paper, we propose a novel joint learning scheme of imagecompression and quality enhancement, called JointIQ-Net, as well as entropymodel improvement, thus achieving significantly improved coding efficiencyagainst the previous methods. Our proposed JointIQ-Net combines an imagecompression sub-network and a quality enhancement sub-network in a cascade,both of which are end-to-end trained in a combined manner within theJointIQ-Net. Also the JointIQ-Net benefits from improved entropy-minimizationthat newly adopts a Gussian Mixture Model (GMM) and further exploits globalcontext to estimate the probabilities of latent representations. In order toshow the effectiveness of our proposed JointIQ-Net, extensive experiments havebeen performed, and showed that the JointIQ-Net achieves a remarkableperformance improvement in coding efficiency in terms of both PSNR and MS-SSIM,compared to the previous learned image compression methods and the conventionalcodecs such as VVC Intra (VTM 7.1), BPG, and JPEG2000. To the best of ourknowledge, this is the first end-to-end optimized image compression method thatoutperforms VTM 7.1 (Intra), the latest reference software of the VVC standard,in terms of the PSNR and MS-SSIM.

An End-to-End Joint Learning Scheme of Image Compression and Quality Enhancement with Improved Entropy Minimization