GANzilla: User-Driven Direction Discovery in Generative Adversarial Networks

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).

References in corpus (8)

• Learning Transferable Visual Models From Natural Language Supervision
• Generating Videos with Scene Dynamics
• GANSpace: Discovering Interpretable GAN Controls
• Unsupervised Discovery of Interpretable Directions in the GAN Latent Space
• Controlling generative models with continuous factors of variations
• Closed-Form Factorization of Latent Semantics in GANs
• Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesis
• GANSlider: How Users Control Generative Models for Images using Multiple Sliders with and without Feedforward Information

Cited by in corpus (8)

• PromptCharm: Text-to-Image Generation through Multi-modal Prompting and Refinement
• A Taxonomy for Human-LLM Interaction Modes: An Initial Exploration
• Concept Induction: Analyzing Unstructured Text with High-Level Concepts Using LLooM
• Augmenting Pathologists with NaviPath: Design and Evaluation of a Human-AI Collaborative Navigation System
• GANravel: User-Driven Direction Disentanglement in Generative Adversarial Networks
• MemoVis: A GenAI-Powered Tool for Creating Companion Reference Images for 3D Design Feedback
• GenTune: Toward Traceable Prompts to Improve Controllability of Image Refinement in Environment Design
• Concept Lens: Visually Analyzing the Consistency of Semantic Manipulation in GANs