GANSpiration: Balancing Targeted and Serendipitous Inspiration in User Interface Design with Style-Based Generative Adversarial Network

TL;DR

GANSpiration introduces a style-based GAN to provide UI designers with both targeted and serendipitous design inspiration, improving relevance and diversity of suggested examples to enhance creative workflows.

Contribution

This work presents a novel GAN-based approach for UI design inspiration that balances relevance and diversity, addressing limitations of existing retrieval-based tools.

Findings

Outputs are relevant to input designs.

Suggested examples are diverse and creative.

Practitioners find the suggestions useful for inspiration.

Abstract

Inspiration from design examples plays a crucial role in the creative process of user interface design. However, current tools and techniques that support inspiration usually only focus on example browsing with limited user control or similarity-based example retrieval, leading to undesirable design outcomes such as focus drift and design fixation. To address these issues, we propose the GANSpiration approach that suggests design examples for both targeted and serendipitous inspiration, leveraging a style-based Generative Adversarial Network. A quantitative evaluation revealed that the outputs of GANSpiration-based example suggestion approaches are relevant to the input design, and at the same time include diverse instances. A user study with professional UI/UX practitioners showed that the examples suggested by our approach serve as viable sources of inspiration for overall design concepts and specific design elements. Overall, our work paves the road of using advanced generative machine learning techniques in supporting the creative design practice.