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-to-Image (I2I) multi-domain translation models are usually evaluatedalso using the quality of their semantic interpolation results. However,state-of-the-art models frequently show abrupt changes in the image appearanceduring interpolation, and usually perform poorly in interpolations acrossdomains. In this paper, we propose a new training protocol based on threespecific losses which help a translation network to learn a smooth anddisentangled latent style space in which: 1) Both intra- and inter-domaininterpolations correspond to gradual changes in the generated images and 2) Thecontent of the source image is better preserved during the translation.Moreover, we propose a novel evaluation metric to properly measure thesmoothness of latent style space of I2I translation models. The proposed methodcan be plugged into existing translation approaches, and our extensiveexperiments on different datasets show that it can significantly boost thequality of the generated images and the graduality of the interpolations.

Smoothing the Disentangled Latent Style Space for Unsupervised Image-to-Image Translation