Global and Local Consistent Wavelet-Domain Age Synthesis

• Published in: IEEE transactions on information forensics and security Vol. 14; no. 11; pp. 2943 - 2957
• Main Authors: Li, Peipei, Hu, Yibo, He, Ran, Sun, Zhenan
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.11.2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Age; Age synthesis; Aging; generative adversarial network; Generative adversarial networks; global and local features; Linear transformations; Prototypes; Regularization; Synthesis; Task analysis; Topology; Wavelet domain; wavelet transform; Wavelet transforms
• DOI: 10.1109/TIFS.2019.2907973
• ISSN: 1556-6013

Age synthesis is a challenging task due to the complicated and non-linear transformation in the human aging process. Aging information is usually reflected in local facial parts, such as wrinkles at the eye corners. However, these local facial parts contribute less in previous GAN-based methods for age synthesis. To address this issue, we propose a wavelet-domain global and local consistent age generative adversarial network (WaveletGLCA-GAN), in which one global specific network and three local specific networks are integrated together to capture both global topology information and local texture details of human faces. Different from the most existing methods that modeling age synthesis in image domain, we adopt wavelet transform to depict the textual information in frequency domain. Moreover, five types of losses are adopted: 1) adversarial loss aims to generate realistic wavelets; 2) identity preserving loss aims to better preserve identity information; 3) age preserving loss aims to enhance the accuracy of age synthesis; 4) pixel-wise loss aims to preserve the background information of the input face; and 5) the total variation regularization aims to remove ghosting artifacts. Our method is evaluated on three face aging datasets, including CACD2000, Morph, and FG-NET. Qualitative and quantitative experiments show the superiority of the proposed method over other state-of-the-arts.