现代纺织技术 ›› 2023, Vol. 31 ›› Issue (2): 36-.

• • 上一篇    下一篇

基于生成对抗网络的服装图像生成研究进展

  

  1. 浙江理工大学,a.服装学院;b.服装数字化技术浙江省工程实验室,杭州310018
  • 收稿日期:2022-03-24 出版日期:2023-03-10 网络出版日期:2023-03-20
  • 作者简介:施倩(1997—),女,河南信阳人,硕士研究生,主要从事数字服装、计算机视觉方面的研究。
  • 基金资助:
    浙江省一般软科学研究计划(2022C35099);浙江省丝绸与文化艺术研究中心培育项目(ZSFCRC20204PY)

Research progress of clothing image generation based on Generative Adversarial Networks

  1. a.School of Fashion Design & Engineering; b.Zhejiang Provincial Engineering Laboratory of Fashion Digital Technology, Zhejiang Sci-Tech University, Hangzhou 310018, China
  • Received:2022-03-24 Published:2023-03-10 Online:2023-03-20

摘要: 生成式人工智能正逐步运用在服装零售、电子商务、趋势预测、虚拟现实以及增强现实等服装产业技术中,并广泛覆盖相关品类的服务与产品。深度学习领域,图像生成模型主要包括深度信念网络(DBN)、变分自编码器(VAE)、生成对抗网络(GAN)。文章围绕GAN研究前沿对其变体发展进行分类梳理,将应用于服装领域最为广泛的条件生成对抗网络(CGAN)在Text to Image、Image to Image、Image to Video中的相关研究成果加以介绍,并分析其优化历程、优缺点以及适用类型;列举GAN在服装图像生成中的具体应用,包括服装横幅广告自动生成、个性化服装推荐与生成、服装与图案设计、虚拟试衣;最后针对服装图像生成研究挑战作出总结。研究认为,未来可在多模态生成模型研发、大规模时尚服装数据集构建、服装生成客观评估指标的3个方向展开研究。

关键词: 深度学习, 生成对抗网络, 服装生成, 智能广告设计, 虚拟试衣

Abstract:

The depth generation model mainly includes Deep Belief Network (DBN), Variational SelfEncoder (VAE) and Generative Adversarial Network (GAN). GAN, as a popular indepth learning framework in recent years, constructs two networks G and D which are mutually antagonistic and game, so that they can achieve Nash equilibrium through continuous iterative training and then realize the automatic generation of images. GAN can be applied in many fields, including semisupervised learning, sequence data generation, image processing, domain adaptation, etc. The image processing field can be subdivided into multiple scenes, such as image generation, image superresolution, image style transformation, object transformation and object detection. The most widely used and successful part of GAN in image processing is image generation. Clothing image generation based on 5G, big data, depth learning and other technologies can effectively promote the digital development process of apparel ecommerce.
Conditional Generative Adversarial Network (CGAN) implements constraints on sample generation by adding constraint condition Y to GAN. CGAN can direct the generator to synthesize data in a directional way against expected samples. Therefore, CGAN is an effective model to realize automatic generation of clothing images that meet specific needs. During the training, the generator learns to generate realistic samples matching the labels of the training data set, and the discriminator learns to match the correct labels for the identified real samples. At present, the public clothing data sets that can be applied to clothing image generation mainly include FashionMNIST, Deep Fashion, Fashion AI, etc. According to the data morphology classification of the input model and the output model, the main forms of CGAN implementation in the clothing field are TexttoImage, ImagetoImage and ImagetoVideo. The three data synthesis forms respectively contain various derived GAN models, which correspond to different clothing generation application scenarios. TexttoImage aims to generate the required clothing image based on the given description text, which can be specifically applied to a given model change, clothing texture rendering, character pose and clothing attribute generation, clothing category and background classification; ImagetoImage is mostly applied in clothing design, such as clothing pattern design, clothing image conversion (from sketch to cartoon clothing, model to dress), style transfer, virtual fitting, fashion trend forecast, etc.; ImagetoVideo is usually applied to facial expression video frame prediction, anonymous model video generation, virtual fitting and other scenes.
In recent years, research on GANapplied clothing image generation industry is mostly distributed in the field of ecommerce, including automatic generation of clothing banner advertisements, personalized clothing recommendation system, clothing and pattern design, virtual fitting towards video presentation, etc., which greatly enables the upgrading of related digital clothing industry. However, the industry is still facing the problems of single utility of generation model, narrow application of clothing data set and lack of objective and unified criteria for generation evaluation. The research in the future will focus on the research and development of integrated multimodal generation model, the collection of largescale clothing data sets, and the development of objective criteria for clothing image generation and evaluation.

Key words: deep learning, GAN, clothing generation, intelligent ad design, virtual fitting.

中图分类号: