COutfitGAN: Learning to Synthesize Compatible Outfits Supervised by Silhouette Masks and Fashion Styles

TL;DR

This paper introduces COutfitGAN, a novel framework for generating compatible fashion items based on given outfits, leveraging silhouette masks and styles, and trained on a large-scale dataset, advancing fashion design automation.

Contribution

The paper presents a new task of synthesizing compatible fashion items and proposes COutfitGAN, a framework that integrates style extraction and GAN-based generation for outfit design.

Findings

COutfitGAN outperforms baselines in similarity, authenticity, and compatibility.

The framework effectively synthesizes photo-realistic, compatible fashion items.

Large-scale dataset with over 200K outfits supports robust training and evaluation.

Abstract

How to recommend outfits has gained considerable attention in both academia and industry in recent years. Many studies have been carried out regarding fashion compatibility learning, to determine whether the fashion items in an outfit are compatible or not. These methods mainly focus on evaluating the compatibility of existing outfits and rarely consider applying such knowledge to 'design' new fashion items. We propose the new task of generating complementary and compatible fashion items based on an arbitrary number of given fashion items. In particular, given some fashion items that can make up an outfit, the aim of this paper is to synthesize photo-realistic images of other, complementary, fashion items that are compatible with the given ones. To achieve this, we propose an outfit generation framework, referred to as COutfitGAN, which includes a pyramid style extractor, an outfit generator, a UNet-based real/fake discriminator, and a collocation discriminator. To train and evaluate this framework, we collected a large-scale fashion outfit dataset with over 200K outfits and 800K fashion items from the Internet. Extensive experiments show that COutfitGAN outperforms other baselines in terms of similarity, authenticity, and compatibility measurements.