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, we propose a new deep image compression framework calledComplexity and Bitrate Adaptive Network (CBANet), which aims to learn onesingle network to support variable bitrate coding under different computationalcomplexity constraints. In contrast to the existing state-of-the-art learningbased image compression frameworks that only consider the rate-distortiontrade-off without introducing any constraint related to the computationalcomplexity, our CBANet considers the trade-off between the rate and distortionunder dynamic computational complexity constraints. Specifically, to decode theimages with one single decoder under various computational complexityconstraints, we propose a new multi-branch complexity adaptive module, in whicheach branch only takes a small portion of the computational budget of thedecoder. The reconstructed images with different visual qualities can bereadily generated by using different numbers of branches. Furthermore, toachieve variable bitrate decoding with one single decoder, we propose a bitrateadaptive module to project the representation from a base bitrate to theexpected representation at a target bitrate for transmission. Then it willproject the transmitted representation at the target bitrate back to that atthe base bitrate for the decoding process. The proposed bit adaptive module cansignificantly reduce the storage requirement for deployment platforms. As aresult, our CBANet enables one single codec to support multiple bitratedecoding under various computational complexity constraints. Comprehensiveexperiments on two benchmark datasets demonstrate the effectiveness of ourCBANet for deep image compression.

CBANet: Towards Complexity and Bitrate Adaptive Deep Image Compression using a Single Network