Two Birds with One Stone: Transforming and Generating Facial Images with Iterative GAN
This work addresses the need for high-fidelity, identity-preserving facial image manipulation, which is incremental as it builds on existing GAN methods by adding iterative training and perceptual regularization.
The paper tackles the problem of generating and transforming facial images while preserving identity by proposing an iterative GAN architecture that integrates perceptual loss, achieving excellent performance on multi-label facial datasets like CelebA.
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.