GANzilla: User-Driven Direction Discovery in Generative Adversarial Networks

TL;DR

GANzilla is a user-driven tool that enables non-expert users to discover meaningful editing directions in GANs through an iterative scatter/gather approach, facilitating targeted image modifications.

Contribution

It introduces a novel interactive method allowing users to control GAN outputs without requiring algorithmic expertise, complementing existing algorithm-driven approaches.

Findings

Users successfully discovered editing directions for specific image modifications.

Participants achieved high-level goals like making faces appear happier.

The tool demonstrated diversity in user-generated editing directions.

Abstract

Generative Adversarial Network (GAN) is widely adopted in numerous application areas, such as data preprocessing, image editing, and creativity support. However, GAN's 'black box' nature prevents non-expert users from controlling what data a model generates, spawning a plethora of prior work that focused on algorithm-driven approaches to extract editing directions to control GAN. Complementarily, we propose a GANzilla: a user-driven tool that empowers a user with the classic scatter/gather technique to iteratively discover directions to meet their editing goals. In a study with 12 participants, GANzilla users were able to discover directions that (i) edited images to match provided examples (closed-ended tasks) and that (ii) met a high-level goal, e.g., making the face happier, while showing diversity across individuals (open-ended tasks).