FCBoost-Net: A Generative Network for Synthesizing Multiple Collocated Outfits via Fashion Compatibility Boosting
This work addresses the need for versatile outfit generation in fashion technology, offering users multiple choices, though it appears incremental by building on pre-trained generative models and boosting techniques.
The paper tackles the problem of generating multiple diverse and compatible outfits from a given set of fashion items, addressing limitations in prior work that produced only single options. The proposed FCBoost-Net framework improves fashion compatibility through a boosting-inspired method while maintaining diversity, as confirmed by experiments on visual authenticity, diversity, and compatibility metrics.
Outfit generation is a challenging task in the field of fashion technology, in which the aim is to create a collocated set of fashion items that complement a given set of items. Previous studies in this area have been limited to generating a unique set of fashion items based on a given set of items, without providing additional options to users. This lack of a diverse range of choices necessitates the development of a more versatile framework. However, when the task of generating collocated and diversified outfits is approached with multimodal image-to-image translation methods, it poses a challenging problem in terms of non-aligned image translation, which is hard to address with existing methods. In this research, we present FCBoost-Net, a new framework for outfit generation that leverages the power of pre-trained generative models to produce multiple collocated and diversified outfits. Initially, FCBoost-Net randomly synthesizes multiple sets of fashion items, and the compatibility of the synthesized sets is then improved in several rounds using a novel fashion compatibility booster. This approach was inspired by boosting algorithms and allows the performance to be gradually improved in multiple steps. Empirical evidence indicates that the proposed strategy can improve the fashion compatibility of randomly synthesized fashion items as well as maintain their diversity. Extensive experiments confirm the effectiveness of our proposed framework with respect to visual authenticity, diversity, and fashion compatibility.