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

Volumetric image compression has become an urgent task to effectivelytransmit and store images produced in biological research and clinicalpractice. At present, the most commonly used volumetric image compressionmethods are based on wavelet transform, such as JP3D. However, JP3D employs anideal, separable, global, and fixed wavelet basis to convert input images frompixel domain to frequency domain, which seriously limits its performance. Inthis paper, we first design a 3-D trained wavelet-like transform to enablesignal-dependent and non-separable transform. Then, an affine wavelet basis isintroduced to capture the various local correlations in different regions ofvolumetric images. Furthermore, we embed the proposed wavelet-like transform toan end-to-end compression framework called aiWave to enable an adaptivecompression scheme for various datasets. Last but not least, we introduce theweight sharing strategies of the affine wavelet-like transform according to thevolumetric data characteristics in the axial direction to reduce the amount ofparameters. The experimental results show that: 1) when cooperating our trained3-D affine wavelet-like transform with a simple factorized entropy module,aiWave performs better than JP3D and is comparable in terms of encoding anddecoding complexities; 2) when adding a context module to further remove signalredundancy, aiWave can achieve a much better performance than HEVC.

aiWave: Volumetric Image Compression with 3-D Trained Affine Wavelet-like Transform