Abstract
Age transformation aims to preserve personalized facial information while altering a given face to appear at a target age. This technique finds extensive applications in fields such as face recognition, movie special effects, and social entertainment, among others. With the advancement of deep learning, particularly Generative Adversarial Networks (GANs), research on age transformation has made significant progress, leading to the emergence of a diverse range of deep learning-based methods. However, a comprehensive and systematic literature review of these methods is currently lacking. In this survey, we provide an all-encompassing review of deep learning methods for facial aging. Firstly, we summarize the key aspects of feature preservation during the age transformation process. Subsequently, we present a comprehensive overview of facial age transformation techniques, categorized according to various deep learning network architectures. Additionally, we conduct an analysis and comparison of commonly used face image datasets, offering recommendations for dataset selection. Furthermore, we consolidate the qualitative and quantitative evaluation metrics commonly employed in age transformation methodologies through experimental assessment. Finally, we address potential areas of future research in age transformation methods, based on the current challenges and limitations.
Similar content being viewed by others
Data availability
The datasets generated during and/or analyzed during the current study are available from the corresponding author upon reasonable request.
Notes
Face aging and rejuvenation are applied to predict a person appearance at different ages. Face age progression (prediction of future appearance) and Face age regression (estimation of previous appearance) are also known as face aging and rejuvenation.
References
Alaluf Y, Patashnik O, Cohen-Or D (2021) Only a matter of style: age transformation using a style-based regression model. ACM Trans Graph (TOG) 40(4):1–12
Albert AM, Ricanek K Jr, Patterson E (2007) A review of the literature on the aging adult skull and face: implications for forensic science research and applications. Forensic Sci Int 172(1):1–9
Alley TR (2013) Social and applied aspects of perceiving faces. Psychology Press, London
Antipov G, Baccouche M, Dugelay JL (2017) Face aging with conditional generative adversarial networks. In: 2017 IEEE international conference on image processing (ICIP), IEEE, pp 2089–2093
Bando Y, Kuratate T, Nishita T (2002) A simple method for modeling wrinkles on human skin. In: Proceedings of the 10th pacific conference on computer graphics and applications, 2002. IEEE, pp 166–175
Banerjee S, Mittal G, Joshi A, et al (2023) Identity-preserving aging of face images via latent diffusion models. arXiv:2307.08585
Baykal G, Ozcelik F, Unal G (2022) Exploring deshufflegans in self-supervised generative adversarial networks. Pattern Recognit 122(108):244
Berg AC, Justo SC (2003) Aging of orbicularis muscle in virtual human faces. In: Proceedings on 7th international conference on information visualization, 2003. IV 2003. IEEE, pp 164–168
Bińkowski M, Sutherland D, Arbel M, et al (2018) Demystifying mmd gans. ICLR
Boussaad L, Boucetta A (2022) Deep-learning based descriptors in application to aging problem in face recognition. J King Saud Univ Comput Inf Sci 34(6):2975–2981
Chandaliya PK, Nain N (2022) Childgan: face aging and rejuvenation to find missing children. Pattern Recognit 129(108):761
Chandaliya PK, Nain N (2023) AW-GAN: face aging and rejuvenation using attention with wavelet GAN. Neural Comput Appl 35(3):2811–2825
Chandaliya PK, Sinha A, Nain N (2020) Childface: Gender aware child face aging. In: 2020 International conference of the biometrics special interest group (BIOSIG). IEEE, pp 1–5
Chen BC, Chen CS, Hsu WH (2014) Cross-age reference coding for age-invariant face recognition and retrieval. In: Computer vision–ECCV 2014: 13th European conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part VI 13, Springer, pp 768–783
Chen K, Yao L, Zhang D et al (2019) A semisupervised recurrent convolutional attention model for human activity recognition. IEEE Trans Neural Netw Learn Syst 31(5):1747–1756
Chen X, Lathuilière S (2023) Face aging via diffusion-based editing. arXiv:2309.11321
Dahlan HA (2021) A survey on deep learning face age estimation model: method and ethnicity. Int J Adv Comput Sci Appl. https://doi.org/10.14569/ijacsa.2021.0121111
Deb D, Aggarwal D, Jain AK (2021) Identifying missing children: face age-progression via deep feature aging. In: 2020 25th international conference on pattern recognition (ICPR). IEEE, pp 10,540–10,547
Deshmukh T, Kokate D (2022) Human face aging based on deep learning: a survey. Available at SSRN 4043509
Despois J, Flament F, Perrot M (2020) AgingMapGAN (AMGAN): high-resolution controllable face aging with spatially-aware conditional GANs. In: Computer vision–ECCV 2020 workshops: glasgow, UK, August 23–28, 2020, Proceedings, Part III 16. Springer, pp 613–628
Eidinger E, Enbar R, Hassner T (2014) Age and gender estimation of unfiltered faces. IEEE Trans Inf Forensics Secur 9(12):2170–2179
Fang H, Deng W, Zhong Y, et al (2020) Triple-GAN: progressive face aging with triple translation loss. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops, pp 804–805
Fu Y (2014) Fg-net aging database. https://yanweifu.github.io/FG_NET_data
Fu Y, Xu Y, Huang TS (2007) Estimating human age by manifold analysis of face pictures and regression on aging features. In: 2007 IEEE international conference on multimedia and expo. IEEE, pp 1383–1386
Fu Y, Guo G, Huang TS (2010) Age synthesis and estimation via faces: a survey. IEEE Trans Pattern Anal Mach Intell 32(11):1955–1976
Gandhi MR (2004) A method for automatic synthesis of aged human facial images. PhD thesis, McGill University, Montreal, Canada
Gomez-Trenado G, Lathuilière S, Mesejo P et al (2022) Custom structure preservation in face aging. In: Computer vision—ECCV 2022: 17th European conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XVI. Springer, pp 565–580
Goodfellow I, Pouget-Abadie J, Mirza M, et al (2014) Generative adversarial nets. In: Ghahramani Z, Welling M, Cortes C, et al (eds), Advances in neural information processing systems, vol 27. Curran Associates, Inc., https://proceedings.neurips.cc/paper_files/paper/2014/file/5ca3e9b122f61f8f06494c97b1afccf3-Paper.pdf
Grimmer M, Ramachandra R, Busch C (2021) Deep face age progression: a survey. IEEE Access 9:83,376-83,393
Gulrajani I, Ahmed F, Arjovsky M, et al (2017) Improved training of wasserstein gans. In: Advances in neural information processing systems, vol 30
Guo G, Fu Y, Huang TS, et al (2008) Locally adjusted robust regression for human age estimation. In: 2008 IEEE workshop on applications of computer vision, IEEE, pp 1–6
He K, Zhang X, Ren S, et al (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778
He S, Liao W, Yang MY, et al (2021) Disentangled lifespan face synthesis. In: Proceedings of the IEEE/CVF international conference on computer vision, pp 3877–3886
Heusel M, Ramsauer H, Unterthiner T, et al (2017) Gans trained by a two time-scale update rule converge to a local nash equilibrium. In: Advances in neural information processing systems, vol 30
Ho J, Jain A, Abbeel P (2020) Denoising diffusion probabilistic models. Adv Neural Inf Process Syst 33:6840–6851
Hore A, Ziou D (2010) Image quality metrics: PSNR vs. SSIM. In: 2010 20th international conference on pattern recognition, IEEE, pp 2366–2369
Horng WB, Lee CP, Chen CW et al (2001) Classification of age groups based on facial features. J Appl Sci Eng 4(3):183–192
Hsu GS, Xie RC, Chen ZT, et al (2022) Agetransgan for facial age transformation with rectified performance metrics. In: European conference on computer vision. Springer, pp 580–595
Huang X, Belongie S (2017) Arbitrary style transfer in real-time with adaptive instance normalization. In: Proceedings of the IEEE international conference on computer vision, pp 1501–1510
Huang X, Gong M (2022) Landmark-guided conditional gans for face aging. In: Image analysis and processing–ICIAP 2022: 21st international conference, Lecce, Italy, May 23–27, 2022, Proceedings, Part I. Springer, pp 270–283
Huang Z, Chen S, Zhang J et al (2020) PFA-GAN: progressive face aging with generative adversarial network. IEEE Trans Inf Forensics Secur 16:2031–2045
Huang Z, Zhang J, Shan H (2021) When age-invariant face recognition meets face age synthesis: a multi-task learning framework. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 7282–7291
Jeon S, Lee P, Hong K et al (2021) Continuous face aging generative adversarial networks. In: ICASSP 2021-2021 IEEE international conference on acoustics. Speech and signal processing (ICASSP). IEEE, pp 1995–1999
Karras T, Laine S, Aila T (2019) A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 4401–4410
Karras T, Laine S, Aittala M, et al (2020) Analyzing and improving the image quality of stylegan. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 8110–8119
Kemelmacher-Shlizerman I, Suwajanakorn S, Seitz SM (2014) Illumination-aware age progression. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3334–3341
Kemmer B, Simões R, Lima C (2022) Face aging using generative adversarial networks. In: Generative adversarial learning: architectures and applications. Springer, pp 145–168
Khajavi M, Ahmadyfard A (2023) Human face aging based on active appearance model using proper feature set. Signal Image Video Process 17(4):1465–1473
Kim YH, Nam SH, Hong SB et al (2022) GRA-GAN: generative adversarial network for image style transfer of gender, race, and age. Expert Syst Appl 198(116):792
Kingma D, Welling M (2013) Auto-encoding variational bayes. ICLR
Klare B, Jain AK (2010) On a taxonomy of facial features. In: 2010 4th IEEE international conference on biometrics: theory, applications and systems (BTAS). IEEE, pp 1–8
Korgialas C, Pantraki E, Bolari A et al (2023) Face aging by explainable conditional adversarial autoencoders. J Imaging 9(5):96
Krizhevsky A, Sutskever I, Hinton GE (2017) Imagenet classification with deep convolutional neural networks. Commun ACM 60(6):84–90
Kuo TH, Jia Z, Kuo TW, et al (2023) Bitrackgan: Cascaded cyclegans to constraint face aging. arXiv:2304.11313
Kwak Jg, Han DK, Ko H (2020) CAFE-GAN: arbitrary face attribute editing with complementary attention feature. In: Computer Vision—ECCV 2020: 16th European conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part XIV 16. Springer, pp 524–540
Lanitis A, Taylor CJ, Cootes TF (2002) Toward automatic simulation of aging effects on face images. IEEE Trans Pattern Anal Mach Intell 24(4):442–455
Ledig C, Theis L, Huszár F, et al (2017) Photo-realistic single image super-resolution using a generative adversarial network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4681–4690
Lee J, Yun J, Park S, et al (2021) Improving face recognition with large age gaps by learning to distinguish children. arXiv:2110.11630
Li Z, Jiang R, Aarabi P (2021) Continuous face aging via self-estimated residual age embedding. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 15,008–15,017
Liu L, Yu H, Wang S et al (2021) Learning shape and texture progression for young child face aging. Signal Process Image Commun 93(116):127
Liu S, Sun Y, Zhu D, et al (2017) Face aging with contextual generative adversarial nets. In: Proceedings of the 25th ACM international conference on Multimedia, pp 82–90
Ma W, Zhou Y, He J (2021) Semi-supervised face aging and rejuvenating. J Electron Imaging 30(2):023,003-023,003
Maeng J, Oh K, Suk HI (2023) Age-aware guidance via masking-based attention in face aging. In: 15th ACM international conference on Information and knowledge management
Makhmudkhujaev F, Hong S, Park IK (2021) Re-aging gan: toward personalized face age transformation. In: Proceedings of the IEEE/CVF international conference on computer vision, pp 3908–3917
Mao X, Li Q, Xie H, et al (2017) Least squares generative adversarial networks. In: Proceedings of the IEEE international conference on computer vision, pp 2794–2802
Martin V, Seguier R, Porcheron A et al (2019) Face aging simulation with a new wrinkle oriented active appearance model. Multimedia Tools Appl 78:6309–6327
Megvii Incorporated (2012) Face++ research toolkit. http://www.faceplusplus.com
Mendelson B, Wong CH (2013) Anatomy of the aging face. Plastic Surg 2:78–92
Mirza M, Osindero S (2014) Conditional generative adversarial nets. arXiv:1411.1784
Mishra A, Krishna Reddy S, Mittal A, et al (2018) A generative model for zero shot learning using conditional variational autoencoders. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 2188–2196
Moschoglou S, Papaioannou A, Sagonas C, et al (2017) Agedb: the first manually collected, in-the-wild age database. In: proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 51–59
Nagisetty V, Graves L, Scott J, et al (2020) xai-gan: Enhancing generative adversarial networks via explainable ai systems. arXiv:2002.10438
Nickabadi A, Fard MS, Farid NM, et al (2022) A comprehensive survey on semantic facial attribute editing using generative adversarial networks. arXiv:2205.10587
Or-El R, Sengupta S, Fried O, et al (2020) Lifespan age transformation synthesis. In: Computer Vision–ECCV 2020: 16th European conference, Glasgow, UK, August 23–28, 2020, Proceedings, Part VI 16. Springer, pp 739–755
Othmani A, Taleb AR, Abdelkawy H et al (2020) Age estimation from faces using deep learning: a comparative analysis. Comput Vis Image Understand 196(102):961
Park U, Tong Y, Jain AK (2010) Age-invariant face recognition. IEEE Trans Pattern Anal Mach Intell 32(5):947–954
Pranoto H, Heryadi Y, Warnars HLHS et al (2022) Recent generative adversarial approach in face aging and dataset review. IEEE Access 10:28,693-28,716
Ramanathan N, Chellappa R (2006) Modeling age progression in young faces. In: 2006 IEEE computer society conference on computer vision and pattern recognition (CVPR’06). IEEE, pp 387–394
Rexbye H, Petersen I, Johansens M et al (2006) Influence of environmental factors on facial ageing. Age Ageing 35(2):110–115
Ricanek K, Tesafaye T (2006) Morph: a longitudinal image database of normal adult age-progression. In: 7th international conference on automatic face and gesture recognition (FGR06). IEEE, pp 341–345
Riccio D, Tortora G, De Marsico M, et al (2012) Ega-ethnicity, gender and age, a pre-annotated face database. In: 2012 IEEE workshop on biometric measurements and systems for security and medical applications (BIOMS) proceedings. IEEE, pp 1–8
Rombach R, Blattmann A, Lorenz D, et al (2022) High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 10,684–10,695
Roomi SMM, Virasundarii S, Selvamegala S, et al (2011) Race classification based on facial features. In: 2011 3rd national conference on computer vision, pattern recognition, image processing and graphics. IEEE, pp 54–57
Rostami M, Farajollahi A, Parvin H (2022) Deep learning-based face detection and recognition on drones. J Ambient Intell Humaniz Comput. https://doi.org/10.1007/s12652-022-03897-8
Salimans T, Goodfellow I, Zaremba W, et al (2016) Improved techniques for training gans. In: Advances in neural information processing systems, vol 29
Shu X, Xie GS, Li Z et al (2016) Age progression: current technologies and applications. Neurocomputing 208:249–261
Simonite T (2006) Virtual face-ageing may help find missing persons. NewScientist com. http://technologynewscientist-com/channel/tech/forensic-science
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556
Sohl-Dickstein J, Weiss E, Maheswaranathan N, et al (2015) Deep unsupervised learning using nonequilibrium thermodynamics. In: International conference on machine learning, PMLR, pp 2256–2265
Song J, Zhang J, Gao L, et al (2018) Dual conditional gans for face aging and rejuvenation. In: IJCAI, pp 899–905
Song J, Zhang J, Gao L et al (2021) AgeGAN++: Face aging and rejuvenation with dual conditional GANs. IEEE Trans Multimedia 24:791–804
Song Y, Sohl-Dickstein J, Kingma DP, et al (2020) Score-based generative modeling through stochastic differential equations. arXiv:2011.13456
Sun Y, Wang X, Tang X (2013) Deep convolutional network cascade for facial point detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3476–3483
Suo J, Zhu SC, Shan S et al (2009) A compositional and dynamic model for face aging. IEEE Trans Pattern Anal Mach Intell 32(3):385–401
Sveikata K, Balciuniene I, Tutkuviene J et al (2011) Factors influencing face aging: literature review. Stomatologija 13(4):113–116
Wang W, Cui Z, Yan Y, et al (2016) Recurrent face aging. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2378–2386
Wang Z, Tang X, Luo W, et al (2018) Face aging with identity-preserved conditional generative adversarial networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 7939–7947
Xiao T, Xu Y, Yang K, et al (2015) The application of two-level attention models in deep convolutional neural network for fine-grained image classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 842–850
Xu K, Ba J, Kiros R, et al (2015) Show, attend and tell: neural image caption generation with visual attention. In: International conference on machine learning, PMLR, pp 2048–2057
Yang C, Lv Z (2020) Gender based face aging with cycle-consistent adversarial networks. Image Vis Comput 100(103):945
Yang H, Huang D, Wang Y, et al (2018a) Learning face age progression: a pyramid architecture of gans. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 31–39
Yang TY, Huang YH, Lin YY, et al (2018b) Ssr-net: A compact soft stagewise regression network for age estimation. In: IJCAI, p 7
Yao X, Puy G, Newson A, et al (2021) High resolution face age editing. In: 2020 25th international conference on pattern recognition (ICPR). IEEE, pp 8624–8631
Yin J, Boyce MC (2015) Unique wrinkles as identity tags. Nature 520(7546):164–165
Zhang H, Goodfellow I, Metaxas D, et al (2019) Self-attention generative adversarial networks. In: International conference on machine learning, PMLR, pp 7354–7363
Zhang R, Isola P, Efros AA, et al (2018) The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 586–595
Zhang Y, Liu L, Li C, et al (2017a) Quantifying facial age by posterior of age comparisons. arXiv:1708.09687
Zhang Z, Song Y, Qi H (2017b) Age progression/regression by conditional adversarial autoencoder. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5810–5818
Zhao J, Cheng Y, Cheng Y, et al (2019) Look across elapse: Disentangled representation learning and photorealistic cross-age face synthesis for age-invariant face recognition. In: Proceedings of the AAAI conference on artificial intelligence, pp 9251–9258
Zhu H, Huang Z, Shan H et al (2020) Look globally, age locally: Face aging with an attention mechanism. In: ICASSP 2020-2020 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, pp 1963–1967
Zhu JY, Park T, Isola P, et al (2017) Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE international conference on computer vision, pp 2223–2232
Zoran D, Chrzanowski M, Huang PS, et al (2020) Towards robust image classification using sequential attention models. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 9483–9492
Acknowledgements
This work was supported in part by National Natural Science Foundation of China (61806071, 62102129) and Natural Science Foundation of Hebei Province (F2019202381, F2019202464).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Guo, Y., Su, X., Yan, G. et al. Age transformation based on deep learning: a survey. Neural Comput & Applic 36, 4537–4561 (2024). https://doi.org/10.1007/s00521-023-09376-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-023-09376-1