Fashion-Gen: The Generative Fashion Dataset and Challenge
This provides a new benchmark for generative fashion AI, but it is incremental as it focuses on dataset creation and baseline challenges.
The authors introduced Fashion-Gen, a dataset of 293,008 high-resolution fashion images paired with professional descriptions, and provided baseline results for high-resolution and text-conditioned image generation, inviting the community to improve upon them.
We introduce a new dataset of 293,008 high definition (1360 x 1360 pixels) fashion images paired with item descriptions provided by professional stylists. Each item is photographed from a variety of angles. We provide baseline results on 1) high-resolution image generation, and 2) image generation conditioned on the given text descriptions. We invite the community to improve upon these baselines. In this paper, we also outline the details of a challenge that we are launching based upon this dataset.