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

Semantically guided conditional Generative Adversarial Networks (cGANs) havebecome a popular approach for face editing in recent years. However, mostexisting methods introduce semantic masks as direct conditional inputs to thegenerator and often require the target masks to perform the correspondingtranslation in the RGB space. We propose SeCGAN, a novel label-guided cGAN forediting face images utilising semantic information without the need to specifytarget semantic masks. During training, SeCGAN has two branches of generatorsand discriminators operating in parallel, with one trained to translate RGBimages and the other for semantic masks. To bridge the two branches in amutually beneficial manner, we introduce a semantic consistency loss whichconstrains both branches to have consistent semantic outputs. Whilst bothbranches are required during training, the RGB branch is our primary networkand the semantic branch is not needed for inference. Our results on CelebA andCelebA-HQ demonstrate that our approach is able to generate facial images withmore accurate attributes, outperforming competitive baselines in terms ofTarget Attribute Recognition Rate whilst maintaining quality metrics such asself-supervised Fr\'{e}chet Inception Distance and Inception Score.

SeCGAN: Parallel Conditional Generative Adversarial Networks for Face Editing via Semantic Consistency