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

The discovery of interpretable directions in the latent spaces of pre-trainedGAN models has recently become a popular topic. In particular, StyleGAN2 hasenabled various image generation and manipulation tasks due to its rich anddisentangled latent spaces. The discovery of such directions is typically doneeither in a supervised manner, which requires annotated data for each desiredmanipulation or in an unsupervised manner, which requires a manual effort toidentify the directions. As a result, existing work typically finds only ahandful of directions in which controllable edits can be made. In this study,we design a novel submodular framework that finds the most representative anddiverse subset of directions in the latent space of StyleGAN2. Our approachtakes advantage of the latent space of channel-wise style parameters, so-calledstyle space, in which we cluster channels that perform similar manipulationsinto groups. Our framework promotes diversity by using the notion of clustersand can be efficiently solved with a greedy optimization scheme. We evaluateour framework with qualitative and quantitative experiments and show that ourmethod finds more diverse and disentangled directions. Our project page can befound at http://catlab-team.github.io/fantasticstyles.

Fantastic Style Channels and Where to Find Them: A Submodular Framework for Discovering Diverse Directions in GANs