se-Shweshwe Inspired Fashion Generation

TL;DR

This paper explores the application of sketch-to-design image generation in se-Shweshwe fashion, addressing technical challenges of small datasets and ethical issues related to cultural representation in computer vision.

Contribution

It introduces a se-Shweshwe dataset and discusses novel methods for fashion design generation that respect cultural heritage and address data scarcity.

Findings

Successful collection of a se-Shweshwe dataset

Application of sketch-to-design generation for cultural fashion

Discussion on ethical considerations in fashion datasets

Abstract

Fashion is one of the ways in which we show ourselves to the world. It is a reflection of our personal decisions and one of the ways in which people distinguish and represent themselves. In this paper, we focus on the fashion design process and expand computer vision for fashion beyond its current focus on western fashion. We discuss the history of Southern African se-Shweshwe fabric fashion, the collection of a se-Shweshwe dataset, and the application of sketch-to-design image generation for affordable fashion-design. The application to fashion raises both technical questions of training with small amounts of data, and also important questions for computer vision beyond fairness, in particular ethical considerations on creating and employing fashion datasets, and how computer vision supports cultural representation and might avoid algorithmic cultural appropriation.