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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Existing deep learning-based full-reference IQA (FR-IQA) models usuallypredict the image quality in a deterministic way by explicitly comparing thefeatures, gauging how severely distorted an image is by how far thecorresponding feature lies from the space of the reference images. Herein, welook at this problem from a different viewpoint and propose to model thequality degradation in perceptual space from a statistical distributionperspective. As such, the quality is measured based upon the Wassersteindistance in the deep feature domain. More specifically, the 1DWassersteindistance at each stage of the pre-trained VGG network is measured, based onwhich the final quality score is performed. The deep Wasserstein distance(DeepWSD) performed on features from neural networks enjoys betterinterpretability of the quality contamination caused by various types ofdistortions and presents an advanced quality prediction capability. Extensiveexperiments and theoretical analysis show the superiority of the proposedDeepWSD in terms of both quality prediction and optimization.

DeepWSD: Projecting Degradations in Perceptual Space to Wasserstein Distance in Deep Feature Space