DiFashion: Towards Personalized Outfit Generation and Recommendation
CoRR(2024)
摘要
The evolution of Outfit Recommendation (OR) in the realm of fashion has
progressed through two distinct phases: Pre-defined Outfit Recommendation and
Personalized Outfit Composition. Despite these advancements, both phases face
limitations imposed by existing fashion products, hindering their effectiveness
in meeting users' diverse fashion needs. The emergence of AI-generated content
has paved the way for OR to overcome these constraints, demonstrating the
potential for personalized outfit generation.
In pursuit of this, we introduce an innovative task named Generative Outfit
Recommendation (GOR), with the goal of synthesizing a set of fashion images and
assembling them to form visually harmonious outfits customized to individual
users. The primary objectives of GOR revolve around achieving high fidelity,
compatibility, and personalization of the generated outfits. To accomplish
these, we propose DiFashion, a generative outfit recommender model that
harnesses exceptional diffusion models for the simultaneous generation of
multiple fashion images. To ensure the fulfillment of these objectives, three
types of conditions are designed to guide the parallel generation process and
Classifier-Free-Guidance are employed to enhance the alignment between
generated images and conditions. DiFashion is applied to both personalized
Fill-In-The-Blank and GOR tasks, and extensive experiments are conducted on the
iFashion and Polyvore-U datasets. The results of quantitative and
human-involved qualitative evaluations highlight the superiority of DiFashion
over competitive baselines.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要