Abstract
Visualizing an outfit is an essential part of shopping for clothes. On fashion e-commerce platforms, only a limited number of outfits are visually represented, as it is impractical to photograph every possible outfit combination, even with a small assortment of garments. In this paper, we broaden the set of articles that can be combined into visualizations by training two Generative Adversarial Network (GAN) architectures on a dataset of outfits, poses, and fashion model images. Our first approach employs vanilla StyleGAN that is trained only on fashion model images. We show that this method can be used to transfer the style and the pose of one randomly generated outfit to another. In order to control the generated outfit, our second approach modifies StyleGAN by adding outfit/pose embedding networks. This enables us to generate realistic, high-resolution images of fashion models wearing a custom outfit under an input body pose.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L (2009) ImageNet: a large-scale hierarchical image database. In: CVPR
Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial nets. In: NIPS
Han X, Wu Z, Wu Z, Yu R, Davis LS (2017) VITON: an image-based virtual try-on network. In: CVPR
Heusel M, Ramsauer H, Unterthiner T, Nessler B, Hochreiter S (2017) Gans trained by a two time-scale update rule converge to a local nash equilibrium. In: NIPS
Hsiao W, Katsman I, Wu C, Parikh D, Grauman K (2019) Fashion++: minimal edits for outfit improvement. In: ICCV
Huang X, Belongie SJ (2017) Arbitrary style transfer in real-time with adaptive instance normalization. In: ICCV
Jetchev N, Bergmann U (2017) The conditional analogy gan: swapping fashion articles on people images. In: ICCV Workshops
Karras T, Aila T, Laine S, Lehtinen J (2017) Progressive growing of gans for improved quality, stability, and variation. In: ICLR
Karras T, Laine S, Aila T (2019) A style-based generator architecture for generative adversarial networks. In: CVPR
Lassner C, Pons-Moll G, Gehler PV (2017) A generative model of people in clothing. In: ICCV
Ma L, Jia X, Sun Q, Schiele B, Tuytelaars T, Gool LV (2017) Pose guided person image generation. In: NIPS
Mescheder L, Geiger A, Nowozin S (2018) Which training methods for gans do actually converge? In: ICML
Neverova N, Guler RA, Kokkinos I (2018) Dense pose transfer. In: ECCV
Sbai O, Elhoseiny M, Bordes A, LeCun Y, Couprie C (2018) Design: design inspiration from generative networks. In: ICCV
Sun K, Xiao B, Liu D, Wang J (2019) Deep high-resolution representation learning for human pose estimation. In: CVPR
Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: CVPR
Yildirim G, Seward C, Bergmann U (2018) Disentangling multiple conditional inputs in gans. In: KDD Workshop on AI for Fashion
Yildirim G, Jetchev N, Vollgraf R, Bergmann U (2019) Generating high-resolution fashion model images wearing custom outfits. In: ICCV Workshop on Computer Vision for Fashion, Art and Design
Zhu S, Fidler S, Urtasun R, Lin D, Loy CC (2017) Be your own prada: fashion synthesis with structural coherence. In: ICCV
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Yildirim, G., Jetchev, N., Vollgraf, R., Bergmann, U. (2020). Generating High-Resolution Fashion Model Images Wearing Custom Outfits. In: Dokoohaki, N. (eds) Fashion Recommender Systems. Lecture Notes in Social Networks. Springer, Cham. https://doi.org/10.1007/978-3-030-55218-3_7
Download citation
DOI: https://doi.org/10.1007/978-3-030-55218-3_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-55217-6
Online ISBN: 978-3-030-55218-3
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)