Human-Centric GenAI Garment Designer: 3D Fashion Design Recommendations

Wei Che Chien, Sherali Zeadally, Hsin Hung Cho

Research output: Contribution to specialist publicationArticle

Abstract

This study proposes a 3D Fashion Design Recommendation system that integrates Generative AI (GenAI) and consumer electronics technology to enhance the online shopping experience. Users can upload full-body images to the platform, where generative AI analyzes their body shape and suggests suitable outfit options. This system addresses a significant issue in the consumer electronics industry: the frequent occurrence of mismatched clothing purchases in online shopping, which often leads to high return rates and customer dissatisfaction. By providing personalized and accurate fashion recommendations, our system aims to bridge the gap between online and physical shopping experiences. The method utilizes GenAI to recognize and interpret body shapes, ensuring that the recommended outfits match the user’s physique. Experimental results demonstrate the effectiveness of the proposed system in accurately identifying body shapes and offering tailored fashion advice. This innovation not only improves user satisfaction by reducing the likelihood of returns but also contributes to resource conservation by minimizing the amount of unused clothing.

Original languageEnglish
Specialist publicationIEEE Consumer Electronics Magazine
DOIs
StateAccepted/In press - 2024

Bibliographical note

Publisher Copyright:
© 2012 IEEE.

Funding

We thank the anonymous reviewers for their valuable comments which helped us improve the content and presentation of this paper. This work was supported by the National Science Council of the R.O.C. under grants NSTC 112-2221-E-259 -003 - MY2, NSTC 12-2221-E-259 -004 -MY2, NSTC 113-2622-E-259 -002 - and NSTC 112-2221-E-197 -016 -MY3. Sherali was partially supported by a Distinguished Visiting Professorship from the University of Johannesburg, South Africa.

FundersFunder number
University of Johannesburg
National Science CouncilNSTC 112-2221-E-259 -003 - MY2, NSTC 112-2221-E-197 -016 -MY3, NSTC 12-2221-E-259 -004 -MY2, NSTC 113-2622-E-259 -002 -

    ASJC Scopus subject areas

    • Human-Computer Interaction
    • Hardware and Architecture
    • Computer Science Applications
    • Electrical and Electronic Engineering

    Fingerprint

    Dive into the research topics of 'Human-Centric GenAI Garment Designer: 3D Fashion Design Recommendations'. Together they form a unique fingerprint.

    Cite this