BC-GAN: A Generative Adversarial Network for Synthesizing a Batch of Collocated Clothing
This addresses a limitation for users in the fashion industry who need multiple clothing options for personal tastes and scenarios, but it is incremental as it builds on existing GAN-based collocation synthesis.
The paper tackles the problem of synthesizing only one collocated clothing item at a time in fashion intelligence by introducing BC-GAN, a framework that generates multiple visually-collocated clothing images simultaneously, with experiments showing effectiveness in diversity, visual authenticity, and fashion compatibility compared to state-of-the-art methods.
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.