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 deep learning-based image compression methods have achievedsignificant achievements and gradually outperformed traditional approachesincluding the latest standard Versatile Video Coding (VVC) in both PSNR andMS-SSIM metrics. Two key components of learned image compression frameworks arethe entropy model of the latent representations and the encoding/decodingnetwork architectures. Various models have been proposed, such asautoregressive, softmax, logistic mixture, Gaussian mixture, and Laplacian.Existing schemes only use one of these models. However, due to the vastdiversity of images, it is not optimal to use one model for all images, evendifferent regions of one image. In this paper, we propose a more flexiblediscretized Gaussian-Laplacian-Logistic mixture model (GLLMM) for the latentrepresentations, which can adapt to different contents in different images anddifferent regions of one image more accurately. Besides, in theencoding/decoding network design part, we propose a concatenated residualblocks (CRB), where multiple residual blocks are serially connected withadditional shortcut connections. The CRB can improve the learning ability ofthe network, which can further improve the compression performance.Experimental results using the Kodak and Tecnick datasets show that theproposed scheme outperforms all the state-of-the-art learning-based methods andexisting compression standards including VVC intra coding (4:4:4 and 4:2:0) interms of the PSNR and MS-SSIM. The project page is at\url{https://github.com/fengyurenpingsheng/Learned-image-compression-with-GLLMM}

Learned Image Compression with Discretized Gaussian-Laplacian-Logistic Mixture Model and Concatenated Residual Modules