Fashion Outfit Recommendation and Transformation Using Generative Adversarial Network Methods
DOI:
https://doi.org/10.54097/hset.v41i.6809Keywords:
Fashion recommendation, fashion transformation, generative adversarial networks.Abstract
Over the last few decades, generative adversarial network (GAN) methods have been increasingly applied and improved in fashion-related scenes, especially during the pandemic. This article provides an overview of several mainstream GAN models for fashion recommendation and fashion transformation, including compatibility matrix-regularized GAN, Outfit GAN, transformer-based GAN, conditional analogy GAN, disentangled cycle-consistency try-on network, and flow-navigated warping GAN. Within each GAN method, the improvements made to perform more related and deliciated are presented with detailed loss functions, the specific evaluation matrixes, and the examinations of generators or discriminators. Moreover, possible directions of improvements for future research and problems with existing models are involved. As for the common restrictions of included methods, including the problem of incomprehensive and non-diverse datasets, the standard evaluation of modish aesthetic value, and the number of fashion items involved in one outfit, are analyzed within fashion outfit recommendation and fashion transformation. Therefore, such restrictions provide possible directions for future analysis in fashion-related networks.
Downloads
References
A. Aggarwal, M. Mittal and G. Battineni, “Generative adversarial network: An overview of theory and applications”, Processing of the IJIM Data Insights, vol. 1, no. 1, 2021.
V. Volokha and K. Bochenina, “Content-Aware Generative Model for Multi-Item Outfit Recommendation”, No. 8016. EasyChair, 2022.
S. Kumar, and M.Das Gupta, “GAN: complementary Fasihon Item Recommendation”, Processing of ArXiv, abs: 1906.05596.
Z. Pan, W. Yu, X. Yi, A. Khan, F. Yuan and Y. Zheng, "Recent Progress on Generative Adversarial Networks (GANs): A Survey," in IEEE Access, vol. 7, pp. 36322-36333, 2019.
L. Liu, H. Zhang, and D. Zhou, “Clothing generation by multi-modal embedding: A compatibility matrix-regularized GAN model”, Image and Vision Computing, Vol 107, 2021.
Z. Shen, Z. He, and X. Xue, “MEAL: Multimodel Ensembel Via Adversarial Learnning,” Processing of the AAAI cnference om Artificial Intelligence, Vol. 33, no. 01, 2019.
M. Moosaei, Y. Lin, A. Akhazhanov, H. Chen, F. Wang, and H. Yang, “OutfitGAN: Learning Compatible Items for Generative Fashion Outfits” Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2022, pp. 2273-2277.
A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, “Attention Is All You Need”, Processing of Advanced in Neural Information Processing Systems 30, 2017.
S. Guo, W. Huang, X. Zhang, P. Srikhanta, Y. Cui, Y. Li, H. Adam, M. R. Scott, and S. Belongie, “The iMaterialist Fashion Attribute Dataset” Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 0-0.
Y. Deldjoo, F. Nazary, A. Ramisa, J. Mcauley, G. Oellegrini, A. Bellogin, and T. D. Noia, Processing of ArXiv, abs: 2202.02757.
H. Wu, D. An, X. Zhu, Z. Zhang, G. Fan, and Z. Hua, “Muti-source material image optimized selection based multi-option composition”, Image and Vision Computing, Vol 107, 2021.
N. Jetchev, and U. Bergmann, “The Conditional Analogy GAN: Swapping Fashion Articles on People Images”, Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2017, pp. 2287-2292.
C. Ge, Y. Song, Y. Ge, H. Yang, W. Liu, and P. Luo, “Disentangled Cycle Consistency for Highly-Realistic Virtual Try-On”, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp. 16928-16937.
X. Han, Z. Wu, Z. Wu, R. Yu, and L. S Davis, “Viton: An image-based virtual try-on network”, Proceeding of the IEEE/CVF conference on Computer Vision and Pattern Recognition (CVPR), 2018.
H. Yang, R. Zhang, X. Guo, W. Liu, W. Zuo, and P. Luo, “Towards photo-realistic virtual try-on by adaptively generating-preserving image content”, Processing of the IEEE International Conference on Computer Vision (ICCV), 2020.
H. Dong, X. Liang, X. Shen, B. Wu, B. Chen, and J. Yin, “FW-GAN: Flow-Navigated Warping GAN for Video Virtual Try-On”, Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019, pp. 1161-1170.
B. Wang, H. Zhang, X. Liang, Y. Chen, and L. L, “Toward characteristic-preserving image-based virtual try-on network”, Processing of ArXiv, abs: 1807.07688.
M. Mirza, and S. Osindero, “Conditional Generative Adversarial Nets”, Processing of ArXiv, abs: 1411.1784.
Z. Pan, W. Yu, X. Yi, A. Khan, F. Yuan, and Y. Zheng, "Rencent Progress on Generative Adversarial Networks (GANs): A survey", in IEEE Access, vol. 7, pp. 36322-36333, 2019.
M. F. Hashmi, B. K. K. Ashish, A. G. Keskar, N. D. Bokde, and Z. W. Geem, "FashionFit: Analysis of Mapping 3D Pose and Neural Body Fit for Custom Virtual Try-On," in IEEE Access, vol. 8, pp. 91603-91615, 2020.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
