FIRST: A Million-Entry Dataset for Text-Driven Fashion Synthesis and Design

TL;DR

This paper introduces FIRST, a large-scale dataset of one million high-resolution fashion images with detailed textual descriptions, to facilitate research in text-driven fashion synthesis and design.

Contribution

The paper presents a new extensive dataset, FIRST, with hierarchical textual annotations, enabling advanced research in AI-driven fashion generation and design.

Findings

Experiments demonstrate the dataset's necessity for training effective models.

The dataset covers diverse attire categories and detailed descriptions.

It supports the development of more creative fashion synthesis systems.

Abstract

Text-driven fashion synthesis and design is an extremely valuable part of artificial intelligence generative content(AIGC), which has the potential to propel a tremendous revolution in the traditional fashion industry. To advance the research on text-driven fashion synthesis and design, we introduce a new dataset comprising a million high-resolution fashion images with rich structured textual(FIRST) descriptions. In the FIRST, there is a wide range of attire categories and each image-paired textual description is organized at multiple hierarchical levels. Experiments on prevalent generative models trained over FISRT show the necessity of FIRST. We invite the community to further develop more intelligent fashion synthesis and design systems that make fashion design more creative and imaginative based on our dataset. The dataset will be released soon.