faceaging

Today's topic introduces a state-of-the-art Age Transformation framework, SAM, which is a framework for demonstrating the process of changing the look and appearance of an individual character over time as the character ages. The framework encodes real facial images directly into the latent space of a pre-trained unconditional GAN (e.g., StyleGAN), controlled by a given age offset. A pre-trained age regression network is also used to explicitly guide the encoder in generating a latent encoding corresponding to the desired age.The SAM approach treats successive age processes as the input age and the desired goal ...