skip to main content
research-article

Toward Intelligent Fashion Design: A Texture and Shape Disentangled Generative Adversarial Network

Published:25 February 2023Publication History
Skip Abstract Section

Abstract

Texture and shape in fashion, constituting essential elements of garments, characterize the body and surface of the fabric and outline the silhouette of clothing, respectively. The selection of texture and shape plays a critical role in the design process, as they largely determine the success of a new design for fashion items. In this research, we propose a texture and shape disentangled generative adversarial network (TSD-GAN) to perform “intelligent” design with the transformation of texture and shape in fashion items. Our TSD-GAN aims to learn how to disentangle the features of texture and shape of different fashion items in an unsupervised manner. Specifically, a fashion attribute encoder is developed to decompose the input fashion items into independent representations of texture and shape. Then, to learn the coarse or fine styles hidden in the features of texture and shape, a texture mapping network and a shape mapping network are proposed to disentangle the features into different hierarchical representations. The different hierarchical representations of texture and shape are then fed into a multi-factor-based generator to generate mixed-style fashion items. In addition, a multi-discriminator framework is developed to distinguish the authenticity and texture similarity between the generated images and the real images. Experimental results on different fashion categories demonstrate that our proposed TSD-GAN may be useful for assisting designers to accomplish the design process by transforming the texture and shape of fashion items.

REFERENCES

  1. [1] Abdal Rameen, Qin Yipeng, and Wonka Peter. 2019. Image2stylegan: How to embed images into the StyleGan latent space. In Proceedings of the CVPR. 44314440.Google ScholarGoogle ScholarCross RefCross Ref
  2. [2] Alharbi Yazeed and Wonka Peter. 2020. Disentangled image generation through structured noise injection. In Proceedings of the CVPR. 51335141.Google ScholarGoogle ScholarCross RefCross Ref
  3. [3] Chen Guo, Ma Fenfen, Jiang Yan, and Liu Ruipu. 2018. Virtual reality interactive teaching for Chinese traditional Tibetan clothing. Art, Design Commun. Higher Edu. 17, 1 (2018), 5159.Google ScholarGoogle ScholarCross RefCross Ref
  4. [4] Cho Wonwoong, Choi Sungha, Park David Keetae, Shin Inkyu, and Choo Jaegul. 2019. Image-to-image translation via group-wise deep whitening-and-coloring transformation. In Proceedings of the CVPR. 1063910647.Google ScholarGoogle ScholarCross RefCross Ref
  5. [5] Choi Yunjey, Uh Youngjung, Yoo Jaejun, and Ha Jung-Woo. 2020. Stargan v2: Diverse image synthesis for multiple domains. In Proceedings of the CVPR. 81858194.Google ScholarGoogle ScholarCross RefCross Ref
  6. [6] Collins Edo, Bala Raja, Price Bob, and Susstrunk Sabine. 2020. Editing in style: Uncovering the local semantics of GANs. In Proceedings of the CVPR. 57705779.Google ScholarGoogle ScholarCross RefCross Ref
  7. [7] Cui Yi Rui, Liu Qi, Gao Cheng Ying, and Su Zhongbo. 2018. FashionGAN: Display your fashion design using conditional generative adversarial nets. In Computer Graphics Forum, Vol. 37. Wiley Online Library, 109119.Google ScholarGoogle Scholar
  8. [8] Deng Yingying, Tang Fan, Dong Weiming, Sun Wen, Huang Feiyue, and Xu Changsheng. 2020. Arbitrary style transfer via multi-adaptation network. In Proceedings of the ACM MM. 27192727.Google ScholarGoogle ScholarDigital LibraryDigital Library
  9. [9] Dong Haoye, Liang Xiaodan, Zhang Yixuan, Zhang Xujie, Shen Xiaohui, Xie Zhenyu, Wu Bowen, and Yin Jian. 2020. Fashion editing with adversarial parsing learning. In Proceedings of the CVPR. 81178125.Google ScholarGoogle ScholarCross RefCross Ref
  10. [10] Guan Shanyan, Tai Ying, Ni Bingbing, Zhu Feida, Huang Feiyue, and Yang Xiaokang. 2020. Collaborative learning for faster stylegan embedding. Retrieved from https://arXiv:2007.01758.Google ScholarGoogle Scholar
  11. [11] Guan Weili, Jiao Fangkai, Song Xuemeng, Wen Haokun, Yeh Chung-Hsing, and Chang Xiaojun. 2022. Personalized fashion compatibility modeling via metapath-guided heterogeneous graph learning. In Proceedings of the ACM SIGIR. 482491.Google ScholarGoogle ScholarDigital LibraryDigital Library
  12. [12] Guan Weili, Wen Haokun, Song Xuemeng, Yeh Chung-Hsing, Chang Xiaojun, and Nie Liqiang. 2021. Multimodal compatibility modeling via exploring the consistent and complementary correlations. In Proceedings of the ACM MM. 22992307.Google ScholarGoogle ScholarDigital LibraryDigital Library
  13. [13] Härkönen Erik, Hertzmann Aaron, Lehtinen Jaakko, and Paris Sylvain. 2020. Ganspace: Discovering interpretable gan controls. Adv. Neural Info. Process. Syst. 33 (2020), 98419850.Google ScholarGoogle Scholar
  14. [14] He Kaiming, Zhang Xiangyu, Ren Shaoqing, and Sun Jian. 2016. Deep residual learning for image recognition. In Proceedings of the CVPR. 770778.Google ScholarGoogle ScholarCross RefCross Ref
  15. [15] Heusel Martin, Ramsauer Hubert, Unterthiner Thomas, Nessler Bernhard, and Hochreiter Sepp. 2017. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Adv. Neural Info. Process. Syst. 30 (2017), 66266637.Google ScholarGoogle Scholar
  16. [16] Ho Trang-Thi, Virtusio John Jethro, Chen Yung-Yao, Hsu Chih-Ming, and Hua Kai-Lung. 2020. Sketch-guided deep portrait generation. ACM Trans. Multim. Comput. Commun. Appl. 16, 3 (2020), 88:1–88:18.Google ScholarGoogle ScholarDigital LibraryDigital Library
  17. [17] Huang Xun, Liu Ming-Yu, Belongie Serge, and Kautz Jan. 2018. Multimodal unsupervised image-to-image translation. In Proceedings of the ECCV. 179196.Google ScholarGoogle ScholarDigital LibraryDigital Library
  18. [18] Ji Yuzhu, Zhang Haijun, and Wu Q. M. Jonathan. 2018. Salient object detection via multi-scale attention CNN. Neurocomputing 322 (2018), 130140.Google ScholarGoogle ScholarCross RefCross Ref
  19. [19] Jiang Shuhui, Li Jun, and Fu Yun. 2021. Deep learning for fashion style generation. IEEE TNNLS (2021).Google ScholarGoogle Scholar
  20. [20] Johnson Justin, Alahi Alexandre, and Fei-Fei Li. 2016. Perceptual losses for real-time style transfer and super-resolution. In Proceedings of the ECCV. Springer, 694711.Google ScholarGoogle ScholarCross RefCross Ref
  21. [21] Karras Tero, Laine Samuli, Aittala Miika, Hellsten Janne, Lehtinen Jaakko, and Aila Timo. 2020. Analyzing and improving the image quality of stylegan. In Proceedings of the CVPR. 81078116.Google ScholarGoogle ScholarCross RefCross Ref
  22. [22] Kim Bo-Kyeong, Kim Geonmin, and Lee Soo-Young. 2020. Style-controlled synthesis of clothing segments for fashion image manipulation. IEEE TMM 22, 2 (2020), 298310.Google ScholarGoogle ScholarDigital LibraryDigital Library
  23. [23] Kotovenko Dmytro, Sanakoyeu Artsiom, Lang Sabine, and Ommer Bjorn. 2019. Content and style disentanglement for artistic style transfer. In Proceedings of the ICCV. 44214430.Google ScholarGoogle ScholarCross RefCross Ref
  24. [24] Kukiev Boburmirzo, O‘g‘li A. N. N., and Shaydulloyevich Bekqulov Qudrat. 2019. Technology for creating images in AutoCAD. Eur. J. Res. Reflect. Edu. Sci. 7 (2019).Google ScholarGoogle Scholar
  25. [25] Lee Hsin-Ying, Tseng Hung-Yu, Huang Jia-Bin, Singh Maneesh, and Yang Ming-Hsuan. 2018. Diverse image-to-image translation via disentangled representations. In Proceedings of the ECCV. 3652.Google ScholarGoogle ScholarDigital LibraryDigital Library
  26. [26] Liu Guang-Hai and Yang Jing-Yu. 2013. Content-based image retrieval using color difference histogram. Pattern Recogn. 46, 1 (2013), 188198.Google ScholarGoogle ScholarDigital LibraryDigital Library
  27. [27] Sharma Gaurav, Wu Wencheng, and Dalal Edul N.. 2005. The CIEDE2000 color-difference formula: Implementation notes, supplementary test data, and mathematical observations. Color Res. Appl.: Endors. Inter-Soc. Color Council 30, 1 (2005), 2130.Google ScholarGoogle ScholarCross RefCross Ref
  28. [28] Shelly Gary B. and Starks Joy L.. 2009. Adobe Photoshop CS4: Comprehensive Concepts and Techniques. Cengage Learning.Google ScholarGoogle Scholar
  29. [29] Team Adobe Creative. 2012. Adobe Illustrator CS6 Classroom in a Book. Adobe Press.Google ScholarGoogle ScholarDigital LibraryDigital Library
  30. [30] Xian Wenqi, Sangkloy Patsorn, Agrawal Varun, Raj Amit, Lu Jingwan, Fang Chen, Yu Fisher, and Hays James. 2018. Texturegan: Controlling deep image synthesis with texture patches. In Proceedings of the CVPR. 84568465.Google ScholarGoogle ScholarCross RefCross Ref
  31. [31] Yan Han, Zhang Haijun, Liu Linlin, Zhou Dongliang, Xu Xiaofei, Zhang Zhao, and Yan Shuicheng. 2022. Toward intelligent design: An AI-based fashion designer using generative adversarial networks aided by sketch and rendering generators. IEEE TMM (2022).Google ScholarGoogle Scholar
  32. [32] Yoo Jaejun, Uh Youngjung, Chun Sanghyuk, Kang Byeongkyu, and Ha Jung-Woo. 2019. Photorealistic style transfer via wavelet transforms. In Proceedings of the ICCV. 90359044.Google ScholarGoogle ScholarCross RefCross Ref
  33. [33] Zhang Feifei, Xu Mingliang, and Xu Changsheng. 2022. Tell, imagine, and search: End-to-end learning for composing text and image to image retrieval. ACM Trans. Multim. Comput. Commun. Appl. 18, 2 (2022), 59:1–59:23.Google ScholarGoogle ScholarDigital LibraryDigital Library
  34. [34] Zhang Richard, Isola Phillip, Efros Alexei A., Shechtman Eli, and Wang Oliver. 2018. The unreasonable effectiveness of deep features as a perceptual metric. In Proceedings of the CVPR. 586595.Google ScholarGoogle ScholarCross RefCross Ref
  35. [35] Zhang Yuxin, Tang Fan, Dong Weiming, Huang Haibin, Ma Chongyang, Lee Tong-Yee, and Xu Changsheng. 2022. Domain enhanced arbitrary image style transfer via contrastive learning. In Proceedings of the ACM SIGGRAPH.Google ScholarGoogle ScholarDigital LibraryDigital Library
  36. [36] Zhang Zhu, Ma Jianxin, Zhou Chang, Men Rui, Li Zhikang, Ding Ming, Tang Jie, Zhou Jingren, and Yang Hongxia. 2021. M6-ufc: Unifying multi-modal controls for conditional image synthesis. Retrieved from https://arXiv:2105.14211.Google ScholarGoogle Scholar
  37. [37] Zhu Peihao, Abdal Rameen, Qin Yipeng, and Wonka Peter. 2020. Sean: Image synthesis with semantic region-adaptive normalization. In Proceedings of the CVPR. 51035112.Google ScholarGoogle ScholarCross RefCross Ref
  38. [38] Zhu Shizhan, Urtasun Raquel, Fidler Sanja, Lin Dahua, and Loy Chen Change. 2017. Be your own Prada: Fashion synthesis with structural coherence. In Proceedings of the ICCV. 16891697.Google ScholarGoogle ScholarCross RefCross Ref

Index Terms

  1. Toward Intelligent Fashion Design: A Texture and Shape Disentangled Generative Adversarial Network

    Recommendations

    Comments

    Login options

    Check if you have access through your login credentials or your institution to get full access on this article.

    Sign in

    Full Access

    • Published in

      cover image ACM Transactions on Multimedia Computing, Communications, and Applications
      ACM Transactions on Multimedia Computing, Communications, and Applications  Volume 19, Issue 3
      May 2023
      514 pages
      ISSN:1551-6857
      EISSN:1551-6865
      DOI:10.1145/3582886
      • Editor:
      • Abdulmotaleb El Saddik
      Issue’s Table of Contents

      Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

      Publisher

      Association for Computing Machinery

      New York, NY, United States

      Publication History

      • Published: 25 February 2023
      • Online AM: 13 October 2022
      • Accepted: 2 October 2022
      • Revised: 2 August 2022
      • Received: 17 May 2022
      Published in tomm Volume 19, Issue 3

      Permissions

      Request permissions about this article.

      Request Permissions

      Check for updates

      Qualifiers

      • research-article
    • Article Metrics

      • Downloads (Last 12 months)411
      • Downloads (Last 6 weeks)72

      Other Metrics

    PDF Format

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    Full Text

    View this article in Full Text.

    View Full Text

    HTML Format

    View this article in HTML Format .

    View HTML Format
    About Cookies On This Site

    We use cookies to ensure that we give you the best experience on our website.

    Learn more

    Got it!