基于生成对抗网络和扩散模型的人脸年龄编辑综述  

A Survey of Face Age Editing Based on Generative Adversarial Networks and Diffusion Models

作　　者：金家立 高思远 高满达 王文彬 柳绍祯 孙哲南 JIN Jiali;GAO Siyuan;GAO Manda;WANG Wenbin;LIU Shaozhen;SUN Zhenan(School of Artificial Intelligence,University of Chinese Academy of Sciences,Beijing 100049,China;NLPR&MAIS,Institute of Automation,Chinese Academy of Sciences,Beijing 100190,China;China Electric Science and Technology Research Institution Ltd.,Beijing 102200,China;School of Computer Science,Beijing Institute of Technology,Beijing 100081,China)

机构地区：[1]中国科学院大学,人工智能学院,北京100049 [2]中国科学院自动化研究所,模式识别实验室,北京100190 [3]国家能源集团新能源技术研究院有限公司,北京102200 [4]北京理工大学,计算机学院,北京100081

出　　处：《数据与计算发展前沿(中英文)》2025年第1期38-55,共18页Frontiers of Data & Computing

基　　金：国家能源集团科技项目(GJNY-23-99);国家自然科学基金(U23B2054)。

摘　　要：【目的】近年来,深度生成模型在人脸年龄编辑任务中取得了显著进展,本文对基于生成对抗网络和扩散模型等深度生成模型的人脸年龄编辑方法进行汇总。【方法】本文首先介绍人脸年龄编辑的基本概念、相关数据集、评价指标,然后分析常用的生成对抗网络、扩散模型以及其变体在年龄编辑任务中的应用,归纳现有模型在年龄准确性、身份一致性、生成图像质量等方面的性能表现,并讨论不同评价指标的适用性。【结果】基于生成对抗网络和扩散模型的年龄编辑技术已经在生成图像的质量和年龄预测的准确性上取得了显著进展,但在处理较大年龄跨度时,面部细节的生成仍存在不足。【结论】未来的人脸年龄编辑研究可以通过开发更大规模、更高质量的数据集,结合3D人脸重建技术和扩散模型高效的采样算法,进一步提升模型的生成能力和应用效果。[Purpose]In recent years,deep generative models have made significant progress in the task of facial age editing.This paper summarizes facial age editing methods based on deep generative models such as Generative Adversarial Networks(GANs)and diffusion models.[Methods]This survey first introduces the basic concepts of face age editing,relevant datasets,and evaluation metrics.It then analyzes the applications of commonly used GANs,Diffusion Models,and their variants in age editing tasks.The performance of existing models in terms of age accuracy,identity consistency,and image quality is summarized,and the suitability of different evaluation metrics is discussed.[Results]Age editing technology based on GANs and Diffusion Models have achieved significant improvements in image quality and age prediction accuracy.However,challenges remain in generating fine details,particularly when dealing with large age gaps.[Conclusions]Future research in face age editing can further enhance model generation capability and application effects by developing larger,higher-quality datasets and integrating 3D face reconstruction technology with efficient sampling algorithms from Diffusion Models.

关 键 词：深度学习 生成对抗网络 扩散模型 属性编辑 人脸年龄编辑 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]