Recommendation of Compatible Outfits Conditioned on Style

TL;DR

This paper introduces a method for fashion outfit recommendation that conditions on style, using a novel style encoder to generate outfits aligned with high-level themes, improving upon existing compatibility-based approaches.

Contribution

The work proposes a new style-conditioned outfit generation approach that operates with high-level category labels and a style encoder, enhancing flexibility and practicality over prior methods.

Findings

Outperforms existing state-of-the-art baselines in experiments.

Effectively encodes styles in a smooth latent space.

Generates outfits aligned with high-level style categories.

Abstract

Recommendation in the fashion domain has seen a recent surge in research in various areas, for example, shop-the-look, context-aware outfit creation, personalizing outfit creation, etc. The majority of state of the art approaches in the domain of outfit recommendation pursue to improve compatibility among items so as to produce high quality outfits. Some recent works have realized that style is an important factor in fashion and have incorporated it in compatibility learning and outfit generation. These methods often depend on the availability of fine-grained product categories or the presence of rich item attributes (e.g., long-skirt, mini-skirt, etc.). In this work, we aim to generate outfits conditional on styles or themes as one would dress in real life, operating under the practical assumption that each item is mapped to a high level category as driven by the taxonomy of an online portal, like outdoor, formal etc and an image. We use a novel style encoder network that renders outfit styles in a smooth latent space. We present an extensive analysis of different aspects of our method and demonstrate its superiority over existing state of the art baselines through rigorous experiments.