Face aging with conditional generative adversarial networks

By Grigory Antipov, Moez Baccouche, Jean-Luc Dugelay. 2017

533 citations recorded by the source corpus.

It has been recently shown that Generative Adversarial Networks (GANs) can produce synthetic images of exceptional visual fidelity. In this work, we propose the first GAN-based method for automatic face aging. Contrary to previous works employing GANs for altering of facial attributes, we make a particular emphasize on preserving the original person's identity in the aged version of his/her face. To this end, we introduce a novel approach for “Identity-Preserving” optimization of GAN's latent vectors. The objective evaluation of the resulting aged and rejuvenated face images by the state-of-the-art face recognition and age estimation solutions demonstrate the high potential of the proposed method.

Subfields: Computer Vision and Pattern Recognition, Generative Models, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Generative Models

In Signal Processing

Citations in the corpus

FairFace: Face Attribute Dataset for Balanced Race, Gender, and Age (2019, background): “…image datasets [22, 31, 13, 69, 37, 24, 41, 68, 15, 27, 46, 8, 39] have been proposed and fostered research and development for automated face detection [35, 21], alignment [66, 44], recognition [57, 49], generation [67, 5, 26, 58], modiﬁcation [3, 32, 19], and attribute classiﬁcation [31, 37].”
Black-Box vs. White-Box: Understanding Their Advantages and Weaknesses From a Practical Point of View (2019, background): “face frontal view generation [50], generating new human poses [51], photos to emojis [52], photograph editing [53]–[55], face aging [56], [57], photo blending [58], super resolution [59]–[61], photo inpainting [62]–[64], video prediction [65], and 3D object generation [66], [67]; among”
An overview of deep learning in medical imaging focusing on MRI (2018, methodology): “These can also be used for biological image synthesis [207,208] and text-to-image synthesis [209–211].”
Fader Networks: Manipulating Images by Sliding Attributes (2017, methodology): “[1] use a pre-trained face recognition system instead of a conditional GAN to learn the latent space, and only focuses on the age attribute.”
Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs (2017, methodology): “This approach has been mainly used for image generation tasks [21, 18, 2].”
CausalGAN: Learning Causal Implicit Generative Models with Adversarial Training (2017, methodology): “Various neural network architectures have been proposed for solving this problem [27, 30, 1].”
Algorithmic Fairness (2020, methodology): “In computer vision (CV), for instance, adversarial learning is used for tasks such as image generation (such as in [9]) or modification (such as in [7]), along with other CV tasks.”
FaceForensics++: Learning to Detect Manipulated Facial Images (2019, methodology): “Generative adversarial networks (GANs) are used to apply Face Aging [6], to generate new viewpoints [33], or to alter face attributes like skin color [44].”
Memorization Precedes Generation: Learning Unsupervised GANs with Memory Networks (2018, methodology): “…transfer GANs extract the content information from input data using auxiliary encoder networks (Yan et al., 2016; Perarnau et al., 2016; Antipov et al., 2017; Denton et al., 2016; Lu et al., 2017; Zhang et al., 2017; Isola et al., 2017; Taigman et al., 2017; Kim et al., 2017; Zhu et…”
Generative Adversarial Networks for Face Generation: A Survey (2022, background): “Age-cGAN (an age conditional GAN) [5] synthesizes aging faces while preserving the original person’s identity.”
Attributing Fake Images to GANs: Learning and Analyzing GAN Fingerprints (2018, background): “GANs [31, 52, 10, 32, 38, 19] have shown improved photorealism in image synthesis [40, 15, 69], translation [36, 70, 71], or manipulation [9, 60, 61].”
Manipulating Attributes of Natural Scenes via Hallucination (2018, background): “[2016] were the first to propose a architecture that can be trained on large scale datasets, which sparked a wave of studies aimed at improving this line of work [Arjovsky et al. 2017; Mao et al. 2016; Salimans et al. 2016]. Larsen et al. [2016] integrates adversarial discriminator to VAE framework ”
A Survey on Generative Adversarial Networks: Variants, Applications, and Training (2020, methodology): “The Age-CGAN [49] model was proposed for face aging of human faces to anticipate future looks and looks.”
A survey on face data augmentation for the training of deep neural networks (2019, background): “In addition, the works [42, 60, 73, 140] limited the identity feature distance (Manhattan distance or Euclidean distance) to decrease the identity loss in the process of face image generation.”
Deep Structural Causal Models for Tractable Counterfactual Inference (2020, background): “Here, y could be the style of a picture for style transfer [43], the image domain (e.g. drawing to photo) for image-to-image translation [44], the age of a person in natural images [45] or medical scans [46], or a predicted output for explainability [11].”
Generative Adversarial Networks (GANs) (2020, background): “Generation of realistic images has wide range of practical applications, such as anime character generation [159]–[164], image synthesis [165]–[168], super resolution [10], [124], [169]–[177], image editing and blending [178], [179], inpainting [125], [180]–[182], interactive image generation [183],”
How Generative Adversarial Networks and Its Variants Work : An Overview of GAN (2017, methodology): “In addition, we can transform an image to other specific domains [140],[122],[133] and perform various tasks such as an object transfiguration [139], super resolution [62], 3D image generation [128], [32], and control attributes of data [72],[4],[88],[36].”
FaceForensics: A Large-scale Video Dataset for Forgery Detection in Human Faces (2018, methodology): “Generative adversarial networks (GANs) are used to apply Face Aging [18], to generate new viewpoints [19], or to alter face attributes like skin color [20].”