基于生成对抗网络的人脸年龄编辑方法综述

doi:10.11871/jfdc.issn.2096-742X.2023.02.001

数据与计算发展前沿 ›› 2023, Vol. 5 ›› Issue (2): 2-23.

CSTR: 32002.14.jfdc.CN10-1649/TP.2023.02.001

doi: 10.11871/jfdc.issn.2096-742X.2023.02.001

• 专刊：“人工智能&大数据”科研范式变革专刊（上） • 上一篇下一篇

基于生成对抗网络的人脸年龄编辑方法综述

刘云帆^1,²(),李琦²,孙哲南^1,^2,^*(),谭铁牛^1,²

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，智能感知与计算研究中心，北京 100190

收稿日期:2023-01-28 出版日期:2023-04-20 发布日期:2023-04-24
通讯作者: 孙哲南
作者简介:刘云帆，中国科学院大学人工智能学院，博士研究生，主要研究方向为生物特征识别、计算机视觉、人脸图像编辑。
本文中负责文献整理和论文主体撰写。
LIU Yunfan is currently a graduate student in School of Artificial Intelligence, Chinese Academy of Sciences, and he is now pursuing his Ph.D. degree. His research interests include biometrics, computer vision, and face image editing.
His contributions to this paper are literature survey and man-uscript writing.
E-mail：yunfan.liu@cripac.ia.ac.cn|孙哲南，中国科学院自动化研究所，研究员，博士生导师，中国科学院大学人工智能学院岗位教授，天津中科智能识别产业技术研究院院长，国际模式识别学会会士IAPR Fellow和生物特征识别技术委员会主席，担任国际期刊IEEE Transactions on Biometrics, Behaviour, and Identity Science编委。主要研究方向为生物特征识别、模式识别、计算机视觉。
本文中负责写作指导以及论文最终审定。
SUN Zhenan is currently a professor with the Institute of Automation, Chinese Academy of Sciences. He serves as an Associate Editor of the IEEE Transactions on Biometrics, Behaviour, and Identity Science. He is a fellow of the IAPR. His research interests include biometrics, pattern recognition, and computer vision.
His contributions to this paper are writing instruction and manuscript reviewing.
E-mail: znsun@nlpr.ia.ac.cn
基金资助:
国家自然科学基金面上项目(62076240);北京市自然科学基金会(4222054)

Face Age Editing Methods Based on Generative Adversarial Network: A Survey

LIU Yunfan^1,²(),LI Qi²,SUN Zhenan^1,^2,^*(),TAN Tieniu^1,²

1. School of Artificial Intellignence, University of Chinese Academy of Sciences, Beijing 100049, China
2. Center for Research on Intelligent Perception and Computing, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China

Received:2023-01-28 Online:2023-04-20 Published:2023-04-24
Contact: SUN Zhenan

摘要/Abstract

摘要：

【目的】对基于生成对抗网络的人脸年龄编辑方法进行系统梳理和全面总结。【文献范围】本文从该领域发表在国内外一流会议期刊上的文章出发，按照引用关系对具有代表性的方法进行了检索，并对最终得到的众多研究工作进行了综述。【方法】本文从生成对抗网络内在机制的角度出发，按照隐向量求取和操控方式的不同，对现有方法进行了分类，并对各个模型之间的共性和差异进行了分析和比较。【结果】随着生成对抗网络的快速发展，人脸年龄编辑方法的各方面性能稳步提升，但是仍然面临着诸多问题和挑战。【局限】由于尚不存在一套通用的评价标准，因此本文暂时无法将所有涉及到的方法用一组统一的定量指标进行衡量和比较。【结论】虽然已经取得了显著的成果，但是现有方法在编辑过程的灵活性、极端情况的适应性以及输出结果的多样性方面还有亟待解决的问题。

关键词: 深度学习, 生成对抗网络, 图像转换, 人脸属性, 人脸年龄编辑

Abstract:

[Objective] This paper provides a comprehensive and systematic review of the face age editing methods based on generative adversarial network. [Coverage] This survey contains numerous studies including publications in top-tier international journals and conferences, as well as other representative works in this field. [Methods] From the perspective of the internal mechanism of generative adversarial networks, these studies are categorized according to how the latent vector is obtained and manipulated, and a brief analysis and comparison of the similarity and difference of specific models is provided. [Results] With the rapid development of generative adversarial networks, the performance of the face age editing method in all aspects has been continuously and steadily improved, while there are still challenges and problems in various aspects. [Limitations] Due to the lack of a developed and mature evaluation standard, it is temporarily impossible for this paper to objectively measure and compare the discussed methods with a set of unified quantitative metrics. [Conclusions] Although significant outcome has been achieved, existing methods still face unsolved problems, including the flexibility of the editing process, the adaptability to extreme editing cases, and the diversity of generation results.

Key words: deep learning, generative adversarial network, image translation, facial attribute, face age editing

刘云帆,李琦,孙哲南,谭铁牛. 基于生成对抗网络的人脸年龄编辑方法综述[J]. 数据与计算发展前沿, 2023, 5(2): 2-23.

LIU Yunfan,LI Qi,SUN Zhenan,TAN Tieniu. Face Age Editing Methods Based on Generative Adversarial Network: A Survey[J]. Frontiers of Data and Computing, 2023, 5(2): 2-23, https://cstr.cn/32002.14.jfdc.CN10-1649/TP.2023.02.001.

图/表 14

图1

表1

图2

图3

图4

表2

图5

图6

图7

表3

图8

表4

基于隐空间插值的人脸年龄编辑方法总结"

模型名称	插值隐空间	插值向量建模方法	人脸年龄编辑数据集	定量测量指标
StyleGAN2Distillation^[34]	$W, ? W +$	聚类中心的差向量	FFHQ	FID, US
StyleSpaceAnalysis^[35]	$S$	聚类中心的差向量	FFHQ	ACA, DCI
ACU^[90]	$S$	聚类中心的差向量	FFHQ	ACA, FID
InterFaceGAN^[33]	$Z, ? W$	支持向量机分类平面法向量	CelebA-HQ	-
EnjoyEditingGAN^[37]	$Z, ? W$	多层感知机预测	FFHQ, CelebA, CelebA-HQ	FVA, US
Latent-Transformer^[36]	$W +$	Transformer预测	CelebA-HQ	FVA, APR
Style-Transformer^[91]	$W +$	Transformer预测	FFHQ, CelebA-HQ	FID
SAM^[92]	$W +$	编码器预测	CelebA-HQ	DMEA, US

表4

图9

图10

参考文献 96

[1]	HU G, HUA Y, YUAN Y et al. Attribute-Enhanced Face Recognition with Neural Tensor Fusion Networks[C]. Proceedings of the IEEE International Conference on Computer Vision, 2017: 3764-3773.
[2]	LIU D, WANG N, PENG C et al. Deep Attribute Guided Representation for Heterogeneous Face Recognition[C]. Proceedings of the International Joint Conference on Artificial Intelligence, 2018: 835-841.
[3]	HUANG C, LI Y, LOY C C et al. Deep Imbalanced Lear-ning for Face Recognition and Attribute Prediction[J]. IEEE Transactions on Pattern Analysis and Machine Inte-lligence, 2020, 42(11): 2781-2794.
[4]	LOSS U A aware, JIANG L, ZHANG J et al. Robust RGB-D Face Recognition Using Attribute-Aware Loss[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(10): 2552-2566. doi: 10.1109/TPAMI.2019.2919284 pmid: 31144624
[5]	HAN H, JAIN A K, WANG F et al. Heterogeneous Face Attribute Estimation: A Deep Multi-Task Learning App-roach[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(11): 2597-2609. doi: 10.1109/TPAMI.34
[6]	ZAEEMZADEH A, GHADAR S, FAIETA B et al. Face Image Retrieval with Attribute Manipulation[C]. Pro-ceedings of the IEEE International Conference on Com-puter Vision, 2021: 12096-12105.
[7]	FANG Y, XIAO Z, ZHANG W et al. Attribute Prototype Learning for Interactive Face Retrieval[J]. IEEE Trans-actions on Information Forensics and Security, 2021, 16 (3): 2593-2607.
[8]	CHOI Y, CHOI M, KIM M et al. StarGAN: Unified Gen-erative Adversarial Networks for Multi-domain Image-to-Image Translation[C]. Proceedings of the IEEE Con-ference on Computer Vision and Pattern Recognition, 2018: 8789-8797.
[9]	HE Z, ZUO W, KAN M et al. AttGAN: Facial Attribute Editing by only Changing What You Want[J]. IEEE Transactions on Image Processing, 2019, 28(11): 5464-5478. doi: 10.1109/TIP.2019.2916751 pmid: 31107649
[10]	LIU M, DING Y, XIA M et al. STGAN: A Unified Selec-tive Transfer Network for Arbitrary Image Attribute Editing[C]. Proceedings of the IEEE Conference on Computer Vi-sion and Pattern Recognition, 2019: 3668-3677.
[11]	LIN Y J, WU P W, CHANG C H et al. RelGAN: Multi-domain Image-to-image Translation via Relative Attr-ibutes[C]. Proceedings of the IEEE International Con-ference on Computer Vision, 2019: 5913-5921.
[12]	ZHAO J, CHENG Y, CHENG Y et al. Look Across Elapse: Disentangled Representation Learning and Photo-realistic Cross-age Face Synthesis for Age-invariant Face Recognition[C]. Proceedings of the AAAI Conference on Artificial Intelligence, 2019: 9251-9258.
[13]	HUANG Z, ZHANG J, SHAN H. When Age-Invariant Face Recognition Meets Face Age Synthesis: A Multi-Task Learning Framework[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021: 7278-7287.
[14]	HUANG Z, ZHANG J, SHAN H. When Age-Invariant Face Recognition Meets Face Age Synthesis: A Multi-Task Learning Framework and A New Benchmark[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 1(1): 1-16.
[15]	RAMANATHAN N, CHELLAPPA R. Modeling Age Progression in Young Faces[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2006: 387-394.
[16]	MARK L S, TODD J T. The Perception of Growth in Three Dimensions[J]. Perception & Psychophysics, 1983, 33(2): 193-196. doi: 10.3758/BF03202839
[17]	SUO J, CHEN X, SHAN S et al. A Concatenational Gr-aph Evolution Aging Model[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(11): 2083-2096. doi: 10.1109/TPAMI.2012.22
[18]	SUO J, ZHU S C, SHAN S et al. A Compositional and Dynamic Model for Face Aging[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(3): 385-401. doi: 10.1109/TPAMI.2009.39 pmid: 20075467
[19]	RAMANATHAN N, CHELLAPPA R. Modeling Shape and Textural Variations in Aging Faces[C]. Proceedings of the IEEE International Conference on Automatic Face and Gesture Recognition, 2008: 1-8.
[20]	WANG W, CUI Z, YAN Y et al. Recurrent Face Aging[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 2378-2386.
[21]	DUONG C N, QUACH K G, LUU K et al. Temporal Non-volume Preserving Approach to Facial Age-Progression and Age-Invariant Face Recognition[C]. Proceedings of the IEEE International Conference on Computer Vision, 2017: 3755-3763.
[22]	SHU X, TANG J, LAI H et al. Personalized Age Progr-ession with Aging Dictionary[C]. Proceedings of the IEEE International Conference on Computer Vision, 2015: 3970-3978.
[23]	SHU X, TANG J, LI Z et al. Personalized Age Progre-ssion with Bi-Level Aging Dictionary Learning[J]. IEEE Transactions on Pattern Analysis and Machine Intelli-gence, 2018, 40(4): 905-917.
[24]	GOODFELLOW I, POUGET-ABADIE J, MIRZA M et al. Generative Adversarial Networks[J]. Communications of the ACM, 2020, 63(11): 139-144. doi: 10.1145/3422622
[25]	RADFORD A, METZ L, CHINTALA S. Unsupervised Representation Learning with Deep Convolutional Gen-erative Adversarial Networks[C]. Proceedings of the Inte-rnational Conference on Learning Representations, 2016: 1-16.
[26]	MAO X, LI Q, XIE H et al. Least Squares Generative Adversarial Networks[C]. Proceedings of the IEEE Inte-rnational Conference on Computer Vision, 2017: 2813-2821.
[27]	ARJOVSKY M, CHINTALA S, BOTTOU L. Wasserstein Generative Adversarial Networks[C]. Proceedings of the International Conference on Machine Learning, 2017: 214-223.
[28]	GULRAJANI I, AHMED F, ARJOVSKY M et al. Imp-roved Training of Wasserstein GANs[C]. Proceedings of the Annual Conference on Neural Information Processing Systems, 2017: 5768-5778.
[29]	KARRAS T, TIMO A, SAMULI L et al. Progressive Gro-wing of GANs for Improved Quality, Stability, and Var-iation [C]. Proceedings of the International Conference on Learning Representations, 2018: 1-26.
[30]	KARRAS T, LAINE S, AILA T. A Style-Based Generator Architecture for Generative Adversarial Networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(12): 4217-4228. doi: 10.1109/TPAMI.2020.2970919
[31]	KARRAS T, LAINE S, AITTALA M et al. Analyzing and Improving the Image Quality of StyleGAN[C]. Procee-dings of the IEEE Conference on Computer Vision and Pattern Recognition, 2020: 8107-8116.
[32]	KARRAS T, AITTALA M, LAINE S et al. Alias-Free Generative Adversarial Networks[C]. Proceedings of the Annual Conference on Neural Information Processing Systems, 2021: 852-863.
[33]	SHEN Y, GU J, TANG X et al. Interpreting the Latent Space of GANs for Semantic Face Editing[C]. Proceed-ings of the IEEE Conference on Computer Vision and Pattern Recognition, 2020: 9240-9249.
[34]	VIAZOVETSKYI Y, IVASHKIN V, KASHIN E. Style-GAN2 Distillation for Feed-Forward Image Manipulation[C]. Proceedings of the European Conference on Computer Vision, 2020: 170-186.
[35]	WU Z, LISCHINSKI D, SHECHTMAN E. StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021: 12858-12867.
[36]	YAO X, NEWSON A, GOUSSEAU Y et al. A Latent Transformer for Disentangled Face Editing in Images and Videos[C]. Proceedings of the IEEE International Conference on Computer Vision, 2021: 13769-13778.
[37]	ZHUANG P, KOYEJO O, SCHWING A G. Enjoy Your Editing: Controllable GANs for Image Editing via Latent Space Navigation[C]. Proceedings of the International Conference on Learning Representations, 2021: 1-16.
[38]	PANG Y, LIN J, QIN T et al. Image-to-Image Translation: Methods and Applications[J]. IEEE Transactions on Multimedia, 2022, 24(3): 3859-3881. doi: 10.1109/TMM.2021.3109419
[39]	GRIMMER M, RAMACHANDRA R, BUSCH C. Deep Face Age Progression: A Survey[J]. IEEE Access, 2021, 9(1): 83376-83393. doi: 10.1109/ACCESS.2021.3085835
[40]	PANIS G, LANITIS A, TSAPATSOULIS N et al. Ove-rview of Research on Facial Aging using the FG-NET Aging Database[J]. IET Biometrics, 2016, 5(2): 37-46. doi: 10.1049/iet-bmt.2014.0053
[41]	RICANEK K, TESAFAYE T. MORPH: A Longitudinal Image Database of Normal Adult Age-progression[C]. Proceedings of the IEEE International Conference on Automatic Face and Gesture Recognition, 2006: 341-345.
[42]	CHEN B C, CHEN C S, HSU W H. Cross-age Reference Coding for Age-invariant Face Recognition and Retrieval[C]. Proceedings of the European Conference on Comp-uter Vision, 2014: 768-783.
[43]	ROTHE R, TIMOFTE R,VAN GOOL L. DEX: Deep EXpectation of Apparent Age from a Single Image[C]. Proceedings of the IEEE International Conference on Computer Vision Workshops, 2015: 252-257.
[44]	ZHANG Z, SONG Y, QI H. Age Progression / Regression by Conditional Adversarial Autoencoder[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: 5810-5818.
[45]	OR-EL R, SENGUPTA S, FRIED O et al. Lifespan Age Transformation Synthesis[C]. Proceedings of the European Conference on Computer Vision. Springer International Pu-blishing, 2020: 739-755.
[46]	LIU Z, LUO P, WANG X et al. Deep Learning Face At-tributes in the Wild[C]. Proceedings of the IEEE Interna-tional Conference on Computer Vision, 2015: 3730-3738.
[47]	MOSCHOGLOU S, PAPAIOANNOU A, SAGONAS C et al. AgeDB: The First Manually Collected, In-the-Wild Age Database[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2017: 1997-2005.
[48]	SRINIVAS N, RICANEK K, MICHALSKI D et al. Face Recognition Algorithm Bias: Performance Differences on Images of children and adults[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2019: 2269-2277.
[49]	HUANG X, BELONGIE S. Arbitrary Style transfer in real-time with adaptive instance normalization[C]. Proc-eedings of the IEEE International Conference on Compu-ter Vision, 2017: 1501-1510.
[50]	XIA W, ZHANG Y, YANG Y et al. GAN Inversion: A Survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 1(1): 1-17.
[51]	SALIMANS T, GOODFELLOW I, ZAREMBA W et al. Improved Techniques for Training GANs[C]. Proceed-ings of the Annual Conference on Neural Information Processing Systems, 2016: 2234-2242.
[52]	SZEGEDY C, VANHOUCKE V, IOFFE S et al. Rethin-king the Inception Architecture for Computer Vision[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE, 2016: 2818-2826.
[53]	HEUSEL M, RAMSAUER H, UNTERTHINER T et al. GANs Trained by a Two Time-scale Update Rule Con-verge to a Local Nash Equilibrium[C]. Proceedings of the Annual Conference on Neural Information Processing Sys-tems, 2017: 6627-6638.
[54]	HUANG Z, CHEN S, ZHANG J et al. PFA-GAN: Pro-gressive Face Aging with Generative Adversarial Net-work[J]. IEEE Transactions on Information Forensics and Security, 2021, 16(4): 2031-2045. doi: 10.1109/TIFS.10206
[55]	EASTWOOD C, WILLIAMS C K I. A Framework for the Quantitative Evaluation of Disentangled Represen-tations[C]. Proceedings of the International Conference on Learning Representations, 2018: 1-15.
[56]	YANG H, HUANG D, WANG Y et al. Learning Face Age Progression: A Pyramid Architecture of GANs[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 31-39.
[57]	LIU Y, LI Q, SUN Z. Attribute-aware Face Aging with Wavelet-based Generative Adversarial Networks[C]. Proc-eedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019: 11869-11878.
[58]	LIU Y, LI Q, SUN Z et al. A3GAN: An Attribute-Aware Attentive Generative Adversarial Network for Face Ag-ing[J]. IEEE Transactions on Information Forensics and Security, 2021, 16(2): 2776-2790. doi: 10.1109/TIFS.2021.3065499
[59]	HE Z, KAN M, SHAN S et al. S2GAN: Share Aging Factors Across Ages and Share Aging Trends Among Individuals[C]. Proceedings of the IEEE International Conference on Computer Vision, 2019: 9439-9448.
[60]	WANG Z, XU T, WEIXIN L et al. Face Aging with Identity-Preserved Conditional Generative Adversarial Networks[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: 7939-7947.
[61]	YANG H, HUANG D, WANG Y et al. Learning Con-tinuous Face Age Progression: A Pyramid of GANs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(2): 499-515. doi: 10.1109/TPAMI.34
[62]	SUN Y, TANG J, SHU X et al. Facial Age Synthesis with Label Distribution-Guided Generative Adversarial Network[J]. IEEE Transactions on Information Forensics and Security, 2020, 15(3): 2679-2691. doi: 10.1109/TIFS.10206
[63]	SHI C, ZHANG J, YAO Y et al. CAN-GAN: Conditi-oned-attention normalized GAN for face age synthesis[J]. Pattern Recognition Letters, 2020, 138(2): 520-526. doi: 10.1016/j.patrec.2020.08.021
[64]	LI P, HU Y, LI Q et al. Global and Local Consistent Age Generative Adversarial Networks[C]. Proceedings of the International Conference on Pattern Recognition, 2018: 1073-1078.
[65]	LI P, HU Y, HE R et al. Global and Local Consistent Wavelet-Domain Age Synthesis[J]. IEEE Transactions on Information Forensics and Security, 2019, 14(11): 2943-2957. doi: 10.1109/TIFS.10206
[66]	DESPOIS J, FLAMENT F,MATTHIEU PERROT. Agin-gMapGAN (AMGAN): High-Resolution Contr-ollable Face Aging with Spatially-Aware Conditional GANs[C]. Proceedings of the European Conference on Computer Vision Workshop, 2022: 613-628.
[67]	ZHU H, HUANG Z, SHAN H et al. Look Globally, Age Locally: Face Aging with an Attention Mechanism[C]. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, IEEE, 2020: 1963-1967.
[68]	WANG H, SANCHEZ V, LI C T. Age-Oriented Face Synthesis with Conditional Discriminator Pool and Adv-ersarial Triplet Loss[J]. IEEE Transactions on Image Processing, 2021, 30(4): 5413-5425. doi: 10.1109/TIP.2021.3084106
[69]	DUAN M, LI K, LIAO Q et al. DEF-Net: A Face Aging Model by Using Different Emotional Learnings[J]. IEEE Transactions on Circuits and Systems for Video Tech-nology, 2022, 32(5): 3012-3022.
[70]	SUN Y, TANG J, SUN Z et al. Facial Age and Exp-ression Synthesis Using Ordinal Ranking Adversarial Networks[J]. IEEE Transactions on Information Fore-nsics and Security, 2020, 15(2): 2960-2972.
[71]	FANG H, DENG W, ZHONG Y et al. Triple-GAN: Prog-ressive Face Aging with Triple Translation Loss[C]. Proc-eedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2020: 3500-3509.
[72]	LIU S, SUN Y, ZHU D et al. Face Aging with Contextual Generative Adversarial Nets[C]. Proceedings of the ACM International Conference on Multimedia, 2017: 82-90.
[73]	ZHU J Y, PARK T, ISOLA P et al. Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks[C]. Proceedings of the IEEE International Conference on Computer Vision, 2017: 2242-2251.
[74]	ZHANG G, KAN M, SHAN S et al. Generative Adve-rsarial Network with Spatial Attention for Face Attribute Editing[C]. Proceedings of the European Conference on Computer Vision, 2018: 422-437.
[75]	SONG J, ZHANG J, GAO L et al. Dual Conditional GA-Ns for Face Aging and Rejuvenation[C]. Proceedings of the International Joint Conference on Artificial Intellig-ence, 2018: 899-905.
[76]	PALSSON S, AGUSTSSON E, TIMOFTE R et al. Gen-erative Adversarial Style Transfer Networks for Face Aging[C]. Proceedings of the IEEE Conference on Com-puter Vision and Pattern Recognition Workshops, 2018: 2197-2205.
[77]	LI Q, LIU Y, SUN Z. Age Progression and Regression with Spatial Attention Modules[C]. Proceedings of the AAAI Conference on Artificial Intelligence, 2020: 11378-11385.
[78]	SUN M, WANG J, LIU J et al. A Unified Framework for Biphasic Facial Age Translation with Noisy-Semantic Guided Generative Adversarial Networks[J]. IEEE Tran-sactions on Information Forensics and Security, 2022, 17(2): 1513-1527.
[79]	KINGMA D P, WELLING M. Auto-encoding Variational Bayes[C]. Proceedings of the International Conference on Learning Representations, 2014: 1-14.
[80]	SONG J, ZHANG J, GAO L et al. AgeGAN++: Face Aging and Rejuvenation With Dual Conditional GANs[J]. IEEE Transactions on Multimedia, 2022, 24(2): 791-804. doi: 10.1109/TMM.2021.3059336
[81]	ANTIPOV G, BACCOUCHE M, DUGELAY J L. Face Aging with Conditional Generative Adversarial Net-works[C]. Proceedings of the IEEE International Confer-ence on Image Processing, 2017: 2089-2093.
[82]	JEON S, LEE P, HONG K et al. Continuous Face Aging Generative Adversarial Networks[C]. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, 2021: 1995-1999.
[83]	DEB D, AGGARWAL D, JAIN A K. Identifying Missing Children: Face Age-progression via Deep Feature Aging[C]. Proceedings of the International Conference on Pattern Recognition, 2020: 10540-10547.
[84]	LI Z, JIANG R, AARABI P. Continuous Face Aging via Self-estimated Residual Age Embedding[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021: 15003-15012.
[85]	YAO X, PUY G, NEWSON A et al. High Resolution Face Age Editing[C]. Proceedings of the International Conference on Pattern Recognition, 2020: 8624-8631.
[86]	MAKHMUDKHUJAEV F, HONG S, PARK I K. Re-Aging GAN: Toward Personalized Face Age Transfor-mation[C]. Proceedings of the IEEE International Con-ference on Computer Vision, 2021: 3888-3897.
[87]	LI P, HUANG H, HU Y et al. Hierarchical Face Aging Through Disentangled Latent Characteristics[C]. Pro-ceedings of the European Conference on Computer Visi-on. Springer International Publishing, 2020: 86-101.
[88]	HUANG Z, CHEN S, ZHANG J et al. AgeFlow: Cond-itional Age Progression and Regression with Normalizing Flows[C]. Proceedings of the International Joint Confer-ence on Artificial Intelligence, 2021: 743-750.
[89]	HE S, LIAO W, YANG M Y et al. Disentangled Lifespan Face Synthesis[C]. Proceedings of the IEEE International Conference on Computer Vision, 2021: 3857-3866.
[90]	WANG R, CHEN J, YU G et al. Attribute-specific Con-trol Units in StyleGAN for Fine-grained Image Mani-pulation[C]. Proceedings of the ACM International Conf-erence on Multimedia, 2021: 926-934.
[91]	HU X, HUANG Q, SHI Z et al. Style Transformer for Image Inversion and Editing[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2022: 11337-11346.
[92]	ALALUF Y, PATASHNIK O, COHEN-OR D. Only a Matter of Style: Age Transformation using a Style-based Regression Model[J]. ACM Transactions on Graphics, 2021, 40(4): 1-12.
[93]	ROMERO A, ARBEL´AEZ P, GOOL L Van et al. SMIT: Stochastic Multi-Label Image-to-Image Translation[C]. Proceedings of the IEEE International Conference on Computer Vision Workshops, 2019: 1-10.
[94]	WANG Y, GONZALEZ-GARCIA A, VAN DE WEIJER J et al. SDIT: Scalable and Diverse Cross-domain Image Translation[C]. Proceedings of the ACM International Conference on Multimedia, 2019: 1267-1276.
[95]	XIAO T, HONG J, MA J. ELEGANT: Exchanging Latent Encodings with GAN for Transferring Multiple Face Attributes[C]. Proceedings of the European Conference on Computer Vision, 2018: 172-187.
[96]	ZHU P, ABDAL R, QIN Y et al. SEAN: Image Synthesis with Semantic Region-adaptive Normalization[C]. Proc-eedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2020: 5103-5112.

数据集名称	图像数量	人物数量	年龄范围	标签类型	图像属性	采集环境	图像来源
FG-Net^[40]	1002	82	0-69	年龄值	灰度、彩色	非受控	私人数码/扫描照片
MORPH Alb.1^[41]	1690	515	15-68	年龄值	灰度	受控	受控环境下采集
MORPH Alb.2^[41]	55134	13618	16-77	年龄值	彩色	受控	受控环境下采集
CACD^[42]	163446	2000	16-62	年龄值	彩色	非受控	谷歌图像搜索引擎
IMDB-WIKI^[43]	523051	20284	0-100	年龄值	灰度、彩色	非受控	IMDB、Wikipedia网站
UTKFace^[44]	20000	-	0-116	年龄值	灰度、彩色	非受控	谷歌、必应图像搜索引擎
FFHQ-Aging^[45]	70000	-	0-70+	年龄组	彩色	非受控	原始FFHQ数据集

模型名称	映射类型	网络类型	年龄组跨度	年龄组个数	人脸年龄编辑数据集	定量测量指标
PA-GAN^[56]	双域	单向	10	4	FG-Net, MORPH, CACD	MEA, FVC, FVA
AW-GAN^[57]	双域	单向	10	4	MORPH, CACD	MEA, DMEA, FVC, FVA, APR
A³GAN^[58]	双域	单向	10	4	FG-Net, MORPH, CACD, CelebA	MEA, DMEA, FVC, FVA, APR
PFA-GAN^[54]	多域	单向	10	4	FG-Net, MORPH, CACD	IS, MEA, DMEA, FVC, FVA, PCC
S²GAN^[59]	多域	单向	10	5	MORPH, CACD	ACA, FID, MEA, DMEA, FVA
IPC-GAN^[60]	多域	单向	10	5	CACD	IS, US
PA-GAN++^[61]	多域	单向	10	4	FG-Net, MORPH, CACD	MEA, FVC, FVA, US
ldGAN^[62]	多域	单向	3	12	MORPH	MEA, FVC
CAN-GAN^[63]	多域	单向	10	4	FG-Net, MORPH, CACD	MEA, DMEA, FVC, FVA
GLCA-GAN^[64]	多域	单向	10	4	FG-Net, MORPH, CACD	FVA
WaveletGLCA-GAN^[65]	多域	单向	10	4	FG-Net, MORPH, CACD	MEA, FVA
AM-GAN^[66]	多域	单向	连续年龄编辑		FFHQ-Aging	FID, DMAE
AA-GAN^[67]	多域	单向	10	5	MORPH	MEA, FVC, FVA
MTFE-GAN^[68]	多域	单向	10	4	MORPH, CACD	FID, MEA, FVA, KL散度
DEF-Net^[69]	多域	单向	10	4	MORPH, CACD	US
ranking-GAN^[70]	多域	单向	5	7	MORPH	MEA, FVC
Triple-GAN^[71]	多域	单向	10	5	MORPH, CACD	ACA, MEA, FVC, FVA
C-GAN^[72]	多域	单向	10	7	FG-Net, MORPH, CACD	FVA, US
Dual-cGAN^[75]	多域	循环	10	9	FG-Net, UTKFace	FVC, US
F-GAN^[76]	多域	循环	10	6	FG-Net, CelebA	DMEA, US
SA-GAN^[77]	多域	循环	4~30	9	FG-Net, MORPH, CACD, UTKFace, IMDB-WIKI, CelebA	DMEA, FVC, FVA
NSG-GAN^[78]	多域	循环	10	4	FG-Net, MORPH, CACD	DMEA, FVC, FVA

模型名称	子空间数量	解耦方法	年龄组跨度	年龄组数量	人脸年龄编辑数据集	定量测量指标
CAAE^[44]	2	对抗训练	5~10	10	FG-Net, MORPH, CACD	US
AgeGAN++^[80]	2	对抗训练	4~30	9	FG-Net, MORPH, CACD	FID, EMA, FVC, US
AIM^[12]	2	域适应	老化/年轻化		FG-Net, MORPH, CACD	FVA
MLTFace^[13,14]	2	域适应	10	7	FG-Net, MORPH, CACD, AgeDB, LCAF	ACA, EVC, FVA, US
Age-cGAN^[81]	2	优化重建	10	6	IMDB-WIKI	FVA
CFA-GAN^[82]	2	正交分解	连续年龄编辑		MORPH	MEA, DMEA, FVC, FVA
CA-GAN^[83]	2	伪成对数据	4	8	FG-Net, CACD, ITWCC	FVA
PAT-GAN^[84]	2	特征调制	连续年龄编辑		CACD, FFHQ-Aging	FID, MEA, FVA
HRFAE^[85]	2	特征调制	连续年龄编辑		CACD, FFHQ-Aging, CelebA-HQ	MEA, APR, Blurriness
LATS^[45]	2	AdaIN	3~20	10	CACD, FFHQ-Aging, CelebA-HQ	US
ReAgingGAN^[86]	2	AdaIN	连续年龄编辑		FG-Net, MORPH, CACD	FID, ACA
DAAE^[87]	3	VAE优化目标	连续年龄编辑		FG-Net, MORPH, CACD, UTKFace, AgeDB	DMEA, MEA, FVA
AgeFlow^[88]	3	基于flow的模型	10	4	FG-Net, MORPH, CACD, CelebA	ACA, FVC, APR
DLATS^[89]	3	人脸形状正则化	10	6	FFHQ-Aging	FVA, US

基于生成对抗网络的人脸年龄编辑方法综述

Face Age Editing Methods Based on Generative Adversarial Network: A Survey

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 14

参考文献 96

相关文章 15

编辑推荐

Metrics

本文评价

[1]	李妍,何洪波,王闰强. 微博热度预测研究综述[J]. 数据与计算发展前沿, 2023, 5(2): 119-135.
[2]	涂又友,郑奇靖,赵瑾. 基于深度学习方法研究分子/固体界面量子化质子耦合的电荷转移过程[J]. 数据与计算发展前沿, 2023, 5(2): 37-49.
[3]	许淞源,刘峰. ESDRec：一种面向地球大数据平台的数据推荐模型[J]. 数据与计算发展前沿, 2023, 5(1): 55-64.
[4]	石雪梅,朱克亮,张祥民,张树涛,陈良锋. 基于生成对抗网络的有遮挡人脸修复方法[J]. 数据与计算发展前沿, 2022, 4(4): 123-131.
[5]	陈琼,杨咏,黄天林,冯媛. 小样本图像语义分割综述[J]. 数据与计算发展前沿, 2021, 3(6): 17-34.
[6]	蒲晓蓉,黄佳欣,刘军池,孙家瑜,罗纪翔,赵越,陈柯成,任亚洲. 面向临床需求的CT图像降噪综述[J]. 数据与计算发展前沿, 2021, 3(6): 35-49.
[7]	何涛,王桂芳,马廷灿. 基于词嵌入语义异常的跨学科研究内容发现方法[J]. 数据与计算发展前沿, 2021, 3(6): 50-59.
[8]	张怡宁,何洪波,王闰强. 热门数字音频预测技术综述[J]. 数据与计算发展前沿, 2021, 3(4): 81-92.
[9]	陈子健,李俊,岳兆娟,赵泽方. 基于自编码器与属性信息的混合推荐模型[J]. 数据与计算发展前沿, 2021, 3(3): 148-155.
[10]	肖建平,龙春,赵静,魏金侠,胡安磊,杜冠瑶. 基于深度学习的网络入侵检测研究综述[J]. 数据与计算发展前沿, 2021, 3(3): 59-74.
[11]	李序,连一峰,张海霞,黄克振. 网络安全知识图谱关键技术[J]. 数据与计算发展前沿, 2021, 3(3): 9-18.
[12]	赵伟昱,张宏海,仲波. 基于深度学习的遥感影像地块分割方法[J]. 数据与计算发展前沿, 2021, 3(2): 133-141.
[13]	沈飙,陈扬,杨琛,刘博文. 海洋科学中尺度涡的计算机视觉检测和分析方法[J]. 数据与计算发展前沿, 2020, 2(6): 30-41.
[14]	任荟颖,王婧,王彦棡. 基于AutoML的湍流建模[J]. 数据与计算发展前沿, 2020, 2(4): 121-131.
[15]	张圣林,林潇霏,孙永谦,张玉志,裴丹. 基于深度学习的无监督KPI异常检测[J]. 数据与计算发展前沿, 2020, 2(3): 87-100.