Semi-Latent GAN: Learning to generate and modify facial images from attributes
This addresses the need for unified facial image generation and manipulation tools, offering a novel approach for applications in computer vision and graphics.
The paper tackles the problem of generating and modifying facial images using high-level attributes, proposing a model that achieves both tasks coherently by learning relationships in a Semi-Latent Facial Attribute Space, with experiments on CelebA and CASIA-WebFace datasets validating its effectiveness.
Generating and manipulating human facial images using high-level attributal controls are important and interesting problems. The models proposed in previous work can solve one of these two problems (generation or manipulation), but not both coherently. This paper proposes a novel model that learns how to both generate and modify the facial image from high-level semantic attributes. Our key idea is to formulate a Semi-Latent Facial Attribute Space (SL-FAS) to systematically learn relationship between user-defined and latent attributes, as well as between those attributes and RGB imagery. As part of this newly formulated space, we propose a new model --- SL-GAN which is a specific form of Generative Adversarial Network. Finally, we present an iterative training algorithm for SL-GAN. The experiments on recent CelebA and CASIA-WebFace datasets validate the effectiveness of our proposed framework. We will also make data, pre-trained models and code available.