Towards Intelligent Design: A Self-driven Framework for Collocated Clothing Synthesis Leveraging Fashion Styles and Textures

TL;DR

This paper presents ST-Net, a self-driven generative framework that synthesizes matching clothing items based on style and texture, eliminating the need for paired training data and improving fashion compatibility in clothing synthesis.

Contribution

Introduces a novel self-supervised generative network for collocated clothing synthesis that does not require paired datasets, leveraging fashion style and texture attributes.

Findings

Outperforms state-of-the-art methods in visual authenticity.

Effectively captures fashion compatibility without paired data.

Constructed a large-scale dataset for unsupervised clothing synthesis.

Abstract

Collocated clothing synthesis (CCS) has emerged as a pivotal topic in fashion technology, primarily concerned with the generation of a clothing item that harmoniously matches a given item. However, previous investigations have relied on using paired outfits, such as a pair of matching upper and lower clothing, to train a generative model for achieving this task. This reliance on the expertise of fashion professionals in the construction of such paired outfits has engendered a laborious and time-intensive process. In this paper, we introduce a new self-driven framework, named style- and texture-guided generative network (ST-Net), to synthesize collocated clothing without the necessity for paired outfits, leveraging self-supervised learning. ST-Net is designed to extrapolate fashion compatibility rules from the style and texture attributes of clothing, using a generative adversarial network. To facilitate the training and evaluation of our model, we have constructed a large-scale dataset specifically tailored for unsupervised CCS. Extensive experiments substantiate that our proposed method outperforms the state-of-the-art baselines in terms of both visual authenticity and fashion compatibility.