# Fashion++: Minimal Edits for Outfit Improvement

## TL;DR

Fashion++ is a neural network-based system that suggests minimal, impactful clothing modifications to improve outfit fashionability, using learned garment encodings and automated training from web photos.

## Contribution

It introduces a novel deep learning approach for minimal outfit edits, explicitly factorizing shape and texture for targeted fashion improvements.

## Key findings

- Successful automatic fashionability improvements demonstrated
- Edits include garment swaps, color tweaks, and fit adjustments
- Validated by automated metrics and human judgment

## Abstract

Given an outfit, what small changes would most improve its fashionability? This question presents an intriguing new vision challenge. We introduce Fashion++, an approach that proposes minimal adjustments to a full-body clothing outfit that will have maximal impact on its fashionability. Our model consists of a deep image generation neural network that learns to synthesize clothing conditioned on learned per-garment encodings. The latent encodings are explicitly factorized according to shape and texture, thereby allowing direct edits for both fit/presentation and color/patterns/material, respectively. We show how to bootstrap Web photos to automatically train a fashionability model, and develop an activation maximization-style approach to transform the input image into its more fashionable self. The edits suggested range from swapping in a new garment to tweaking its color, how it is worn (e.g., rolling up sleeves), or its fit (e.g., making pants baggier). Experiments demonstrate that Fashion++ provides successful edits, both according to automated metrics and human opinion. Project page is at http://vision.cs.utexas.edu/projects/FashionPlus.