Facial aging simulator considering geometry and patch-tiled texture

Tazoe, Yusuke; Gohara, Hiroaki; Maejima, Akinobu; Morishima, Shigeo

doi:10.1145/2342896.2343002

Cited by 52 publications

(21 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, researchers have made great progress on age progression. For example, the physical model-based methods [27,26,14,22] parametrically model biological facial change with age, e.g., muscle, wrinkle, skin, etc. However, they suffer from complex modeling, the requirement of sufficient dataset to cover long time span, and are computationally expensive; the prototype-based methods [28,11,24,29] tend to divide training data into different age groups and learn a transformation between groups.…”

Section: Progression/ Regressionmentioning

confidence: 99%

Age Progression/Regression by Conditional Adversarial Autoencoder

Zhang

Song

2017

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

900

683

View full text Add to dashboard Cite

If I provide you a face image of mine (without telling you the actual age when I took the picture) and a large amount of face images that I crawled (containing labeled faces of different ages but not necessarily paired), can you show me what I would look like when I am 80 or what I was like when I was 5?" The answer is probably a "No." Most existing face aging works attempt to learn the transformation between age groups and thus would require the paired samples as well as the labeled query image. In this paper, we look at the problem from a generative modeling perspective such that no paired samples is required. In addition, given an unlabeled image, the generative model can directly produce the image with desired age attribute. We propose a conditional adversarial autoencoder (CAAE) that learns a face manifold, traversing on which smooth age progression and regression can be realized simultaneously. In CAAE, the face is first mapped to a latent vector through a convolutional encoder, and then the vector is projected to the face manifold conditional on age through a deconvolutional generator. The latent vector preserves personalized face features (i.e., personality) and the age condition controls progression vs. regression. Two adversarial networks are imposed on the encoder and generator, respectively, forcing to generate more photo-realistic faces. Experimental results demonstrate the appealing performance and flexibility of the proposed framework by comparing with the state-of-the-art and ground truth.

show abstract

Section: Progression/ Regressionmentioning

confidence: 99%

Age Progression/Regression by Conditional Adversarial Autoencoder

Zhang

Song

2017

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

900

683

View full text Add to dashboard Cite

show abstract

“…Labels of 'Race' and 'Gender' are all obtained via advanced publicly available APIs of Face++ [13] and placed underneath each image. been proposed to address this problem in the last two decades [8,20,19,21,7]. With the rapid development of deep learning, deep generative models are widely adopted to synthesize aged face images [23,3,4].…”

Section: Introductionmentioning

confidence: 99%

Attribute-Aware Face Aging With Wavelet-Based Generative Adversarial Networks

Liu¹,

Sun

2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

140

128

View full text Add to dashboard Cite

Since it is difficult to collect face images of the same subject over a long range of age span, most existing face aging methods resort to unpaired datasets to learn age mappings. However, the matching ambiguity between young and aged face images inherent to unpaired training data may lead to unnatural changes of facial attributes during the aging process, which could not be solved by only enforcing identity consistency like most existing studies do. In this paper, we propose an attribute-aware face aging model with waveletbased Generative Adversarial Networks (GANs) to address the above issues. To be specific, we embed facial attribute vectors into both the generator and discriminator of the model to encourage each synthesized elderly face image to be faithful to the attribute of its corresponding input. In addition, a wavelet packet transform (WPT) module is incorporated to improve the visual fidelity of generated images by capturing age-related texture details at multiple scales in the frequency space. Qualitative results demonstrate the ability of our model in synthesizing visually plausible face images, and extensive quantitative evaluation results show that the proposed method achieves state-of-the-art performance on existing datasets. * Authors contributed equally.

show abstract

“…Besides, the training data are usually very limited and the face images for the same person only cover a narrow range of ages. Traditional face aging approaches can be roughly split into to two classes, i.e., the prototyping ones [15,38], and the modeling ones [36,37]. However, these approaches o en require face aging sequences of the same person with wide range of ages which are very costly to collect.…”

Section: Introductionmentioning

confidence: 99%

Face Aging with Contextual Generative Adversarial Nets

Liu

Sun

Zhu

et al. 2017

Proceedings of the 25th ACM International Conference on Multimedia

114

View full text Add to dashboard Cite

Face aging, which renders aging faces for an input face, has a racted extensive a ention in the multimedia research. Recently, several conditional Generative Adversarial Nets (GANs) based methods have achieved great success. ey can generate images ing the real face distributions conditioned on each individual age group. However, these methods fail to capture the transition pa erns, e.g., the gradual shape and texture changes between adjacent age groups. In this paper, we propose a novel Contextual Generative Adversarial Nets (C-GANs) to speci cally take it into consideration. e C-GANs consists of a conditional transformation network and two discriminative networks. e conditional transformation network imitates the aging procedure with several specially designed residual blocks. e age discriminative network guides the synthesized face to t the real conditional distribution. e transition pa ern discriminative network is novel, aiming to distinguish the real transition pa erns with the fake ones. It serves as an extra regularization term for the conditional transformation network, ensuring the generated image pairs to t the corresponding real transition pa ern distribution. Experimental results demonstrate the proposed framework produces appealing results by comparing with the state-of-the-art and ground truth. We also observe performance gain for cross-age face veri cation.

show abstract

Facial aging simulator considering geometry and patch-tiled texture

Abstract: a) Aging Face Model (male) (b) Aging Face Model (female) Figure 1: Synthesized Aging Face Models (a), (b).

Cited by 52 publications

References 2 publications

Age Progression/Regression by Conditional Adversarial Autoencoder

Age Progression/Regression by Conditional Adversarial Autoencoder

Attribute-Aware Face Aging With Wavelet-Based Generative Adversarial Networks

Face Aging with Contextual Generative Adversarial Nets

Contact Info

Product

Resources

About