SizeGAN: Improving Size Representation in Clothing Catalogs

Abstract

Online clothing catalogs lack diversity in body shape and garment size. Brands commonly display their garments on models of one or two sizes, rarely including plus-size models. In this work, we propose a new method, SizeGAN, for generating images of garments on different-sized models. To change the garment and model size while maintaining a photorealistic image, we incorporate image alignment ideas from the medical imaging literature into the StyleGAN2-ADA architecture. Our method learns deformation fields at multiple resolutions and uses a spatial transformer to modify the garment and model size. We evaluate our approach along three dimensions: realism, garment faithfulness, and size. To our knowledge, SizeGAN is the first method to focus on this size under-representation problem for modeling clothing. We provide an analysis comparing SizeGAN to other plausible approaches and additionally provide the first clothing dataset with size labels. In a user study comparing SizeGAN and two recent virtual tryon methods, we show that our method ranks first in each dimension, and was vastly preferred for realism and garment faithfulness. In comparison to most previous work, which has focused on generating photorealistic images of garments, our work shows that it is possible to generate images that are both photorealistic and cover diverse garment sizes.

Experimental Evidence that Activewear Retail Imagery Elicits Physiological, Attentional andSelf-reported Markers of Body Image Threat in Women

“…Consumers could also only be presented with images of models of a similar size and age to themselves to prevent upward appearance comparisons against unrealistic body image standards. Once image-generating artificial intelligence models can render personalised image variations in real time, these solutions may offer a highly engaging ecommerce experience (Lewis & Guttag, 2022).…”