Two Birds with One Stone: Transforming and Generating Facial Images with Iterative GAN

Abstract

Generating high fidelity identity-preserving faces with different facial attributes has a wide range of applications. Although a number of generative models have been developed to tackle this problem, there is still much room for further improvement.In paticular, the current solutions usually ignore the perceptual information of images, which we argue that it benefits the output of a high-quality image while preserving the identity information, especially in facial attributes learning area.To this end, we propose to train GAN iteratively via regularizing the min-max process with an integrated loss, which includes not only the per-pixel loss but also the perceptual loss. In contrast to the existing methods only deal with either image generation or transformation, our proposed iterative architecture can achieve both of them. Experiments on the multi-label facial dataset CelebA demonstrate that the proposed model has excellent performance on recognizing multiple attributes, generating a high-quality image, and transforming image with controllable attributes.

References in corpus (9)

• Conditional Generative Adversarial Nets
• Conditional Image Synthesis With Auxiliary Classifier GANs
• Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Loss
• Autoencoding beyond pixels using a learned similarity metric
• Perceptual Adversarial Networks for Image-to-Image Transformation
• Face Expression Recognition and Analysis: The State of the Art
• Age Progression/Regression by Conditional Adversarial Autoencoder
• Neural Face Editing with Intrinsic Image Disentangling
• Generate Identity-Preserving Faces by Generative Adversarial Networks