Outfit Generation and Style Extraction via Bidirectional LSTM and Autoencoder

TL;DR

This paper introduces a model that combines bidirectional LSTM and autoencoder techniques to extract style features from outfits, enabling flexible and interpretable outfit generation aligned with user preferences.

Contribution

The study presents a novel unsupervised style extraction module integrated into outfit generation models, improving style interpretability and control without extra data.

Findings

Outperformed baseline in missing item prediction

Successfully extracted distinguishable styles

Generated outfits with controllable styles

Abstract

When creating an outfit, style is a criterion in selecting each fashion item. This means that style can be regarded as a feature of the overall outfit. However, in various previous studies on outfit generation, there have been few methods focusing on global information obtained from an outfit. To address this deficiency, we have incorporated an unsupervised style extraction module into a model to learn outfits. Using the style information of an outfit as a whole, the proposed model succeeded in generating outfits more flexibly without requiring additional information. Moreover, the style information extracted by the proposed model is easy to interpret. The proposed model was evaluated on two human-generated outfit datasets. In a fashion item prediction task (missing prediction task), the proposed model outperformed a baseline method. In a style extraction task, the proposed model extracted some easily distinguishable styles. In an outfit generation task, the proposed model generated an outfit while controlling its styles. This capability allows us to generate fashionable outfits according to various preferences.