Creating Capsule Wardrobes from Fashion Images

TL;DR

This paper introduces an automated method for creating capsule wardrobes from fashion images by selecting minimal yet versatile sets of garments that maximize outfit compatibility and user preferences, using submodular optimization.

Contribution

It presents a novel unsupervised approach to learn visual compatibility and an iterative subset selection algorithm for efficient capsule wardrobe creation.

Findings

Achieves effective wardrobe assembly comparable to skilled fashionistas

Improves compatibility prediction over existing methods

Demonstrates scalability on large fashion datasets

Abstract

We propose to automatically create capsule wardrobes. Given an inventory of candidate garments and accessories, the algorithm must assemble a minimal set of items that provides maximal mix-and-match outfits. We pose the task as a subset selection problem. To permit efficient subset selection over the space of all outfit combinations, we develop submodular objective functions capturing the key ingredients of visual compatibility, versatility, and user-specific preference. Since adding garments to a capsule only expands its possible outfits, we devise an iterative approach to allow near-optimal submodular function maximization. Finally, we present an unsupervised approach to learn visual compatibility from "in the wild" full body outfit photos; the compatibility metric translates well to cleaner catalog photos and improves over existing methods. Our results on thousands of pieces from popular fashion websites show that automatic capsule creation has potential to mimic skilled fashionistas in assembling flexible wardrobes, while being significantly more scalable.