Only a Matter of Style: Age Transformation Using a Style-Based Regression Model
This work provides a method for more controlled and disentangled age transformation for image manipulation researchers and practitioners, though the specific problem it solves is an incremental improvement on existing techniques.
This paper addresses the challenge of age transformation in facial images by developing an image-to-image translation method that encodes real faces into the latent space of a pre-trained StyleGAN. The method uses an age regression network to guide the generation of desired age transformations, treating the aging process as a regression task. The authors claim qualitative and quantitative advantages over state-of-the-art approaches.
The task of age transformation illustrates the change of an individual's appearance over time. Accurately modeling this complex transformation over an input facial image is extremely challenging as it requires making convincing, possibly large changes to facial features and head shape, while still preserving the input identity. In this work, we present an image-to-image translation method that learns to directly encode real facial images into the latent space of a pre-trained unconditional GAN (e.g., StyleGAN) subject to a given aging shift. We employ a pre-trained age regression network to explicitly guide the encoder in generating the latent codes corresponding to the desired age. In this formulation, our method approaches the continuous aging process as a regression task between the input age and desired target age, providing fine-grained control over the generated image. Moreover, unlike approaches that operate solely in the latent space using a prior on the path controlling age, our method learns a more disentangled, non-linear path. Finally, we demonstrate that the end-to-end nature of our approach, coupled with the rich semantic latent space of StyleGAN, allows for further editing of the generated images. Qualitative and quantitative evaluations show the advantages of our method compared to state-of-the-art approaches.