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

Image compression has been investigated for many decades. Recently, deeplearning approaches have achieved a great success in many computer visiontasks, and are gradually used in image compression. In this paper, we developthree overall compression architectures based on convolutional autoencoders(CAEs), generative adversarial networks (GANs) as well as super-resolution(SR), and present a comprehensive performance comparison. According toexperimental results, CAEs achieve better coding efficiency than JPEG byextracting compact features. GANs show potential advantages on largecompression ratio and high subjective quality reconstruction. Super-resolutionachieves the best rate-distortion (RD) performance among them, which iscomparable to BPG.

Performance Comparison of Convolutional AutoEncoders, Generative Adversarial Networks and Super-Resolution for Image Compression