计算机科学与探索 ›› 2021, Vol. 15 ›› Issue (11): 2025-2047.DOI: 10.3778/j.issn.1673-9418.2105059

• 综述·探索 • 上一篇    下一篇

人脸合成技术综述

费建伟,夏志华,余佩鹏,戴昀书   

  1. 1. 南京信息工程大学 计算机与软件学院,南京 210044
    2. 暨南大学 网络空间安全学院,广州 510632
  • 出版日期:2021-11-01 发布日期:2021-11-09

Survey of Face Synthesis

FEI Jianwei, XIA Zhihua, YU Peipeng, DAI Yunshu   

  1. 1. School of Computer & Software, Nanjing University of Information Science & Technology, Nanjing 210044, China
    2. College of Cyber Security, Jinan University, Guangzhou 510632, China
  • Online:2021-11-01 Published:2021-11-09

摘要:

人脸合成由于其应用与技术价值,是机器视觉领域的热点之一,而近年来深度学习的突破性进展使该领域吸引了更多关注。将该领域的研究分为四个子类:人脸身份合成、人脸动作合成、人脸属性合成与人脸生成,并系统地总结了这些子类的发展历程、现状,以及现有技术存在的问题。首先针对人脸身份合成,从图形学、数字图像处理与深度学习三个角度总结了各自的合成流程,对关键技术原理进行了详细的解释与分析。其次将人脸动作合成进一步分为利用标签驱动的表情编辑与利用真实人脸驱动的人脸重演,并指出了各自领域中存在的缺陷与难题。然后介绍了基于生成模型,尤其是生成对抗网络在人脸属性合成方面的发展,最终对人脸生成的各类工作进行了简单的阐述。此外,介绍了人脸合成技术的实际应用与当前面临的相关问题,并展望了该领域未来可能的研究方向。

关键词: 人脸合成, 生成对抗网络(GAN), 深度学习

Abstract:

Face synthesis is one of the hot topics in the field of computer vision because of its application and technical value. In recent years, the breakthrough of deep learning has attracted much attention in this field. This paper divides the research in this field into four subcategories: face identity synthesis, face movements synthesis, face attributes synthesis and face generation, and systematically summarizes the development process, status quo, and existing problems of these subcategories. First of all, for face identity synthesis, three approaches are summarized, including computer graphics, digital image processing and deep learning. This paper summarizes their respective routine processes, and analyzes the technical principles of milestone work in detail. Secondly, face movements synthesis is further divided into label driven expression editing and real face driven face reenactment, where the shortcomings and problems in each field are pointed out. Then, the development of face attribute synthesis based on generative model is introduced, especially generative adversarial network. Finally, this paper briefly describes all kinds of researches on face generation. In addition, this paper also introduces the practical application and related problems of face synthesis field and provides the possible research direction in this field.

Key words: face synthesis, generative adversarial network (GAN), deep learning