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

TL;DR

This paper introduces a submodular optimization framework to discover a diverse set of interpretable directions in the StyleGAN2 latent space, enhancing controllability and disentanglement in image manipulation tasks.

Contribution

We propose a novel submodular approach that efficiently finds diverse, representative directions in StyleGAN2's style space, improving over existing methods that find limited directions.

Findings

Finds more diverse manipulation directions

Produces more disentangled latent directions

Outperforms prior methods in qualitative and quantitative evaluations

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.