ProductMeta:

An Interactive System for Metaphorical Product Design Ideation with Multimodal Large Language Models

Qinyi Zhou1,2, Jie Deng1,2, Yu Liu2, Yun Wang2, Yan Xia2, Yang Ou2, Zhicong Lu3, Sai Ma1, Scarlett Li2, Yingqing Xu1

1Tsinghua University, 2Microsoft Research Asia, 3George Mason University

Paper Code Live Demo
Image 1

Abstract

Product metaphors, which involve creating products that convey meaning through metaphorical associations, are a powerful tool in product design. However, according to our formative study, novice designers often struggle to establish coherent links between target and source, to manage the complexity of diverse mapping possibilities, and to balance product usability with metaphorical expression. To address these challenges, we introduce Metaphor, a creativity support tool designed to support novice designers in exploring and developing metaphorical product designs. Metaphor incorporates domain knowledge and decomposes the design process into iterative modules and framework-based interfaces, fostering both divergent and convergent thinking. Through user studies, we demonstrate that Metaphor enables novice designers to generate diverse and contextually relevant design ideas by facilitating structured exploration. We conclude with design implications for human-AI co-creation.

Workflow of Metaphor

Image 2

Module1: Exploring Sources

Image 3

Module2: Exploring Mappings

Image 4

Module 3: Constructing Design Proposals

Image 5

Design Case: Toothpick Holder

Input

Target name: Toothpick holder Using environment: Living room Target Users: Family members in China

Supporting Diverse Source Exploration

Image 6

Supporting Diverse Mapping Exploration

Image 7

Design Cases

Image 8

Bibtex

@unpublished{zhou2024Metaphor, title = {Metaphor: Supporting Ideation in Metaphorical Product Design through Multimodal Large Models}, author = {Zhou, Qinyi and Deng, Jie and Liu, Yu and Wang, Yun and Xia, Yan and Ou, Yang and Lu, Zhicong and Li, Scarlett and Xu, Yingqing}, year = {2025}, note = {Conditionally accepted to CHI 2025}, selected = {true}, preview = {Metaphor.png}, pdf = {Metaphor_1210clear.pdf}, html = {/papers/paper1/} }