How Old Are You? Face Age Translation with Identity Preservation Using GANs

Abstract

We present a novel framework to generate images of different age while preserving identity information, which is known as face aging. Different from most recent popular face aging networks utilizing Generative Adversarial Networks(GANs) application, our approach do not simply transfer a young face to an old one. Instead, we employ the edge map as intermediate representations, firstly edge maps of young faces are extracted, a CycleGAN-based network is adopted to transfer them into edge maps of old faces, then another pix2pixHD-based network is adopted to transfer the synthesized edge maps, concatenated with identity information, into old faces. In this way, our method can generate more realistic transfered images, simultaneously ensuring that face identity information be preserved well, and the apparent age of the generated image be accurately appropriate. Experimental results demonstrate that our method is feasible for face age translation.

arXiv comment9 pages, 10 figures

References in corpus (11)

• Conditional Generative Adversarial Nets
• Self-Attention Generative Adversarial Networks
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs
• Unsupervised Attention-guided Image to Image Translation
• Towards the Automatic Anime Characters Creation with Generative Adversarial Networks
• Learning Face Age Progression: A Pyramid Architecture of GANs
• Look Across Elapse: Disentangled Representation Learning and Photorealistic Cross-Age Face Synthesis for Age-Invariant Face Recognition
• Video synthesis of human upper body with realistic face
• A Realistic Face-to-Face Conversation System based on Deep Neural Networks
• A Neural Virtual Anchor Synthesizer based on Seq2Seq and GAN Models