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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Lossy image compression aims to represent images in as few bits as possiblewhile maintaining fidelity to the original. Theoretical results indicate thatoptimizing distortion metrics such as PSNR or MS-SSIM necessarily leads to adiscrepancy in the statistics of original images from those of reconstructions,in particular at low bitrates, often manifested by the blurring of thecompressed images. Previous work has leveraged adversarial discriminators toimprove statistical fidelity. Yet these binary discriminators adopted fromgenerative modeling tasks may not be ideal for image compression. In thispaper, we introduce a non-binary discriminator that is conditioned on quantizedlocal image representations obtained via VQ-VAE autoencoders. Our evaluationson the CLIC2020, DIV2K and Kodak datasets show that our discriminator is moreeffective for jointly optimizing distortion (e.g., PSNR) and statisticalfidelity (e.g., FID) than the PatchGAN of the state-of-the-art HiFiC model. OnCLIC2020, we obtain the same FID as HiFiC with 30-40\% fewer bits.

Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Models