Fantastic Style Channels and Where to Find Them: A Submodular Framework for Discovering Diverse Directions in GANs release_svome3s37vh3rluiv5yroxthrm

by Enis Simsar and Umut Kocasari and Ezgi Gülperi Er and Pinar Yanardag

Released as a article .

2022  

Abstract

The discovery of interpretable directions in the latent spaces of pre-trained GAN models has recently become a popular topic. In particular, StyleGAN2 has enabled various image generation and manipulation tasks due to its rich and disentangled latent spaces. The discovery of such directions is typically done either in a supervised manner, which requires annotated data for each desired manipulation or in an unsupervised manner, which requires a manual effort to identify the directions. As a result, existing work typically finds only a handful of directions in which controllable edits can be made. In this study, we design a novel submodular framework that finds the most representative and diverse subset of directions in the latent space of StyleGAN2. Our approach takes advantage of the latent space of channel-wise style parameters, so-called style space, in which we cluster channels that perform similar manipulations into groups. Our framework promotes diversity by using the notion of clusters and can be efficiently solved with a greedy optimization scheme. We evaluate our framework with qualitative and quantitative experiments and show that our method finds more diverse and disentangled directions. Our project page can be found at http://catlab-team.github.io/fantasticstyles.
In text/plain format

Archived Files and Locations

application/pdf  29.9 MB
file_tmerajdr3va6zfvbvv25rrfo4q
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2022-03-31
Version   v2
Language   en ?
arXiv  2203.08516v2
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 220f86af-01bf-4681-b2ad-be66fefcc52a
API URL: JSON