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/

Zendy Plus

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

Zendy Tools

Zendy Open

We present Mask-guided Generative Adversarial Network (MagGAN) forhigh-resolution face attribute editing, in which semantic facial masks from apre-trained face parser are used to guide the fine-grained image editingprocess. With the introduction of a mask-guided reconstruction loss, MagGANlearns to only edit the facial parts that are relevant to the desired attributechanges, while preserving the attribute-irrelevant regions (e.g., hat, scarffor modification `To Bald'). Further, a novel mask-guided conditioning strategyis introduced to incorporate the influence region of each attribute change intothe generator. In addition, a multi-level patch-wise discriminator structure isproposed to scale our model for high-resolution ($1024 \times 1024$) faceediting. Experiments on the CelebA benchmark show that the proposed methodsignificantly outperforms prior state-of-the-art approaches in terms of bothimage quality and editing performance.

MagGAN: High-Resolution Face Attribute Editing with Mask-Guided Generative Adversarial Network