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

In this paper, a unified transformation method in learned imagecompression(LIC) is proposed from the perspective of modulation. Firstly, thequantization in LIC is considered as a generalized channel with additiveuniform noise. Moreover, the LIC is interpreted as a particular communicationsystem according to the consistency in structures and optimization objectives.Thus, the technology of communication systems can be applied to guide thedesign of modules in LIC. Furthermore, a unified transform method based onsignal modulation (TSM) is defined. In the view of TSM, the existingtransformation methods are mathematically reduced to a linear modulation. Aseries of transformation methods, e.g. TPM and TJM, are obtained by extendingto nonlinear modulation. The experimental results on various datasets andbackbone architectures verify that the effectiveness and robustness of theproposed method. More importantly, it further confirms the feasibility ofguiding LIC design from a communication perspective. For example, when backbonearchitecture is hyperprior combining context model, our method achieves3.52$\%$ BD-rate reduction over GDN on Kodak dataset without increasingcomplexity.

Transformations in Learned Image Compression from a Modulation Perspective