BC-GAN: A Generative Adversarial Network for Synthesizing a Batch of Collocated Clothing

TL;DR

This paper introduces BC-GAN, a novel generative adversarial network that synthesizes multiple collocated clothing items simultaneously, improving diversity, authenticity, and fashion compatibility for fashion industry applications.

Contribution

The paper presents BC-GAN, a new batch clothing synthesis framework with a contrastive learning-based discriminator to enhance fashion compatibility among generated items.

Findings

BC-GAN outperforms state-of-the-art methods in diversity and authenticity.

The model effectively captures fashion compatibility among multiple clothing items.

Extensive experiments validate the approach on a large-scale dataset.

Abstract

Collocated clothing synthesis using generative networks has become an emerging topic in the field of fashion intelligence, as it has significant potential economic value to increase revenue in the fashion industry. In previous studies, several works have attempted to synthesize visually-collocated clothing based on a given clothing item using generative adversarial networks (GANs) with promising results. These works, however, can only accomplish the synthesis of one collocated clothing item each time. Nevertheless, users may require different clothing items to meet their multiple choices due to their personal tastes and different dressing scenarios. To address this limitation, we introduce a novel batch clothing generation framework, named BC-GAN, which is able to synthesize multiple visually-collocated clothing images simultaneously. In particular, to further improve the fashion compatibility of synthetic results, BC-GAN proposes a new fashion compatibility discriminator in a contrastive learning perspective by fully exploiting the collocation relationship among all clothing items. Our model was examined in a large-scale dataset with compatible outfits constructed by ourselves. Extensive experiment results confirmed the effectiveness of our proposed BC-GAN in comparison to state-of-the-art methods in terms of diversity, visual authenticity, and fashion compatibility.