计算机工程与应用 ›› 2022, Vol. 58 ›› Issue (2): 15-26.DOI: 10.3778/j.issn.1002-8331.2108-0347

• 热点与综述 • 上一篇    下一篇

人脸妆容迁移研究综述

米爱中,张伟,乔应旭,许成敬,霍占强   

  1. 1.河南理工大学 计算机科学与技术学院,河南 焦作 454003
    2.河南能源化工集团有限公司 九里山矿,河南 焦作 454150
  • 出版日期:2022-01-15 发布日期:2022-01-18

Review of Research on Facial Makeup Transfer

MI Aizhong, ZHANG Wei, QIAO Yingxu, XU Chengjing, HUO Zhanqiang   

  1. 1.School of Computer Science and Technology, Henan Polytechnic University, Jiaozuo, Henan 454003, China
    2.Jiulishan Mine, Henan Energy and Chemical Industry Group, Jiaozuo, Henan 454150, China
  • Online:2022-01-15 Published:2022-01-18

摘要: 人脸妆容迁移的目标是在保持源图像面部特征的同时,将人脸妆容从参考图像迁移到源图像,具有重要的理论研究价值和巨大的市场应用价值。目前,生成对抗网络已成为解决人脸妆容迁移问题的主流技术。阐述了人脸妆容迁移面临的主要挑战,按照重点解决问题的不同系统地梳理了已有的人脸妆容迁移方法并分析了其优点和局限性,总结了人脸妆容迁移网络常用的损失函数,介绍了常用的人脸妆容迁移数据集以及模型评价方法,讨论了人脸妆容迁移领域未来的发展趋势。

关键词: 人脸妆容迁移, 生成对抗网络, 颜色匹配, 图案迁移, 局部迁移

Abstract: The goal of facial makeup transfer is to transfer makeup from reference image to source image while maintaining the facial features of source image, which has important theoretical research value and great market application value. At present, the generative adversarial network has become the mainstream technology to solve the facial makeup transfer problems. This paper expounds the main challenges faced by facial makeup transfer, systematically combs the existing facial makeup transfer methods according to different critical problems to be solved, analyzes their advantages and limitations, summarizes the common loss functions of facial makeup transfer network, introduces the common facial makeup transfer datasets and model evaluation methods, and discusses the future development trend in the field of facial makeup transfer.

Key words: facial makeup transfer, generative adversarial networks(GAN), color matching, pattern transfer, partial transfer