Leveraging Multimodal LLM for Inspirational User Interface Search

TL;DR

This paper introduces a multimodal large language model-based system for more effective and semantically rich mobile UI design search, surpassing existing methods in relevance and context understanding.

Contribution

It presents a novel semantic-based UI search system leveraging MLLMs to interpret UI images without relying on metadata, improving search relevance for designers.

Findings

Outperforms existing UI retrieval methods in computational and human evaluations.

Enriches UI search with semantic understanding of user, mood, and design context.

Provides a new dataset of UI semantics for future research.

Abstract

Inspirational search, the process of exploring designs to inform and inspire new creative work, is pivotal in mobile user interface (UI) design. However, exploring the vast space of UI references remains a challenge. Existing AI-based UI search methods often miss crucial semantics like target users or the mood of apps. Additionally, these models typically require metadata like view hierarchies, limiting their practical use. We used a multimodal large language model (MLLM) to extract and interpret semantics from mobile UI images. We identified key UI semantics through a formative study and developed a semantic-based UI search system. Through computational and human evaluations, we demonstrate that our approach significantly outperforms existing UI retrieval methods, offering UI designers a more enriched and contextually relevant search experience. We enhance the understanding of mobile UI design semantics and highlight MLLMs' potential in inspirational search, providing a rich dataset of UI semantics for future studies.