Continuous Face Aging Generative Adversarial Networks
- URL: http://arxiv.org/abs/2102.13318v1
- Date: Fri, 26 Feb 2021 06:22:25 GMT
- Title: Continuous Face Aging Generative Adversarial Networks
- Authors: Seogkyu Jeon, Pilhyeon Lee, Kibeom Hong, Hyeran Byun
- Abstract summary: Face aging is the task aiming to translate the faces in input images to designated ages.
Previous methods have limited themselves only able to produce discrete age groups, each of which consists of ten years.
We propose the continuous face aging generative adversarial networks (CFA-GAN)
- Score: 11.75204350455584
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Face aging is the task aiming to translate the faces in input images to
designated ages. To simplify the problem, previous methods have limited
themselves only able to produce discrete age groups, each of which consists of
ten years. Consequently, the exact ages of the translated results are unknown
and it is unable to obtain the faces of different ages within groups. To this
end, we propose the continuous face aging generative adversarial networks
(CFA-GAN). Specifically, to make the continuous aging feasible, we propose to
decompose image features into two orthogonal features: the identity and the age
basis features. Moreover, we introduce the novel loss function for identity
preservation which maximizes the cosine similarity between the original and the
generated identity basis features. With the qualitative and quantitative
evaluations on MORPH, we demonstrate the realistic and continuous aging ability
of our model, validating its superiority against existing models. To the best
of our knowledge, this work is the first attempt to handle continuous target
ages.
Related papers
- ID$^3$: Identity-Preserving-yet-Diversified Diffusion Models for Synthetic Face Recognition [60.15830516741776]
Synthetic face recognition (SFR) aims to generate datasets that mimic the distribution of real face data.
We introduce a diffusion-fueled SFR model termed $textID3$.
$textID3$ employs an ID-preserving loss to generate diverse yet identity-consistent facial appearances.
arXiv Detail & Related papers (2024-09-26T06:46:40Z) - DiffAge3D: Diffusion-based 3D-aware Face Aging [61.3027596093854]
We propose DiffAge3D, the first 3D-aware aging framework that performs faithful aging and identity preservation in a 3D setting.
Our framework includes a robust 3D-aware aging dataset generation pipeline by utilizing a pre-trained 3D GAN.
We demonstrate that DiffAge3D outperforms existing methods, particularly in multiview-consistent aging and fine details preservation.
arXiv Detail & Related papers (2024-08-28T16:36:09Z) - Diverse and Lifespan Facial Age Transformation Synthesis with Identity Variation Rationality Metric [12.438204529412706]
We introduce $rmDLATboldsymbol+$ to realize Diverse and Lifespan Age Transformation on human faces.
Apart from the diversity mechanism embedded in the model, multiple consistency restrictions are leveraged to keep it away from counterfactual aging syntheses.
arXiv Detail & Related papers (2024-01-25T09:26:08Z) - Pluralistic Aging Diffusion Autoencoder [63.50599304294062]
Face aging is an ill-posed problem because multiple plausible aging patterns may correspond to a given input.
This paper proposes a novel CLIP-driven Pluralistic Aging Diffusion Autoencoder to enhance the diversity of aging patterns.
arXiv Detail & Related papers (2023-03-20T13:20:14Z) - A Unified Framework for Biphasic Facial Age Translation with
Noisy-Semantic Guided Generative Adversarial Networks [54.57520952117123]
Biphasic facial age translation aims at predicting the appearance of the input face at any age.
We propose a unified framework for biphasic facial age translation with noisy-semantic guided generative adversarial networks.
arXiv Detail & Related papers (2021-09-15T15:30:35Z) - Disentangled Lifespan Face Synthesis [100.29058545878341]
A lifespan face synthesis (LFS) model aims to generate a set of photo-realistic face images of a person's whole life, given only one snapshot as reference.
The generated face image given a target age code is expected to be age-sensitive reflected by bio-plausible transformations of shape and texture.
This is achieved by extracting shape, texture and identity features separately from an encoder.
arXiv Detail & Related papers (2021-08-05T22:33:14Z) - Continuous Face Aging via Self-estimated Residual Age Embedding [8.443742714362521]
We propose a unified network structure that embeds a linear age estimator into a GAN-based model.
The embedded age estimator is trained jointly with the encoder and decoder to estimate the age of a face image.
The personalized target age embedding is synthesized by incorporating both personalized residual age embedding of the current age and exemplar-face aging basis of the target age.
arXiv Detail & Related papers (2021-04-30T18:06:17Z) - When Age-Invariant Face Recognition Meets Face Age Synthesis: A
Multi-Task Learning Framework [20.579282497730944]
MTLFace can learn age-invariant identity-related representation while achieving pleasing face synthesis.
In contrast to the conventional one-hot encoding that achieves group-level FAS, we propose a novel identity conditional module to achieve identity-level FAS.
Extensive experiments on five benchmark cross-age datasets demonstrate the superior performance of our proposed MTLFace.
arXiv Detail & Related papers (2021-03-02T07:03:27Z) - PFA-GAN: Progressive Face Aging with Generative Adversarial Network [19.45760984401544]
This paper proposes a novel progressive face aging framework based on generative adversarial network (PFA-GAN)
The framework can be trained in an end-to-end manner to eliminate accumulative artifacts and blurriness.
Extensively experimental results demonstrate superior performance over existing (c)GANs-based methods.
arXiv Detail & Related papers (2020-12-07T05:45:13Z) - Age Gap Reducer-GAN for Recognizing Age-Separated Faces [72.26969872180841]
We propose a novel algorithm for matching faces with temporal variations caused due to age progression.
The proposed generative adversarial network algorithm is a unified framework that combines facial age estimation and age-separated face verification.
arXiv Detail & Related papers (2020-11-11T16:43:32Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.