Learning a Deep Reinforcement Learning Policy Over the Latent Space of a Pre-trained GAN for Semantic Age Manipulation
This addresses the challenge of generating realistic, identity-preserving age-altered images for computer vision applications, but it is incremental as it builds on existing GAN and reinforcement learning methods.
The paper tackled the problem of semantic age manipulation in images by learning a deep reinforcement learning policy over the latent space of a pre-trained GAN, resulting in high fidelity images with required age alterations while preserving identity.
Learning a disentangled representation of the latent space has become one of the most fundamental problems studied in computer vision. Recently, many Generative Adversarial Networks (GANs) have shown promising results in generating high fidelity images. However, studies to understand the semantic layout of the latent space of pre-trained models are still limited. Several works train conditional GANs to generate faces with required semantic attributes. Unfortunately, in these attempts, the generated output is often not as photo-realistic as the unconditional state-of-the-art models. Besides, they also require large computational resources and specific datasets to generate high fidelity images. In our work, we have formulated a Markov Decision Process (MDP) over the latent space of a pre-trained GAN model to learn a conditional policy for semantic manipulation along specific attributes under defined identity bounds. Further, we have defined a semantic age manipulation scheme using a locally linear approximation over the latent space. Results show that our learned policy samples high fidelity images with required age alterations, while preserving the identity of the person.