2025/04/17 by Mingzhe Yu, Yunshan Ma, Yu, Mingzhe +9 · 1 citation
Arts and Humanities · Computer Science · Engineering · #3D Shape Modeling and Analysis #FOS: Computer and information sciences #Fashion and Cultural Textiles #Generative Adversarial Networks and Image Synthesis #Information Retrieval (cs.IR) #Multimedia (cs.MM)
paper · pdf · doi:10.48550/arxiv.2504.12900
openalex publication_date 2025/04/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Personalized outfit generation aims to construct a set of compatible and personalized fashion items as an outfit. Recently, generative AI models have received widespread attention, as they can generate fashion items for users to complete an incomplete outfit or create a complete outfit. However, they have limitations in terms of lacking diversity and relying on the supervised learning paradigm. Recognizing this gap, we propose a novel framework FashionDPO, which fine-tunes the fashion outfit generation model using direct preference optimization. This framework aims to provide a general fine-tuning approach to fashion generative models, refining a pre-trained fashion outfit generation model using automatically generated feedback, without the need to design a task-specific reward function. To make sure that the feedback is comprehensive and objective, we design a multi-expert feedback generation module which covers three evaluation perspectives, \ie quality, compatibility and personalization. Experiments on two established datasets, \ie iFashion and Polyvore-U, demonstrate the effectiveness of our framework in enhancing the model's ability to align with users' personalized preferences while adhering to fashion compatibility principles. Our code and model checkpoints are available at https://github.com/Yzcreator/FashionDPO.