se-Shweshwe Inspired Fashion Generation
This work addresses the need for cultural representation in fashion AI for Southern African communities, though it appears incremental in applying existing methods to new cultural data.
The paper tackles the problem of expanding computer vision beyond Western fashion by creating a se-Shweshwe fabric dataset and applying sketch-to-design image generation for affordable fashion design, addressing technical challenges of small data training and ethical considerations like cultural representation.
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.