GAGAN: Geometry-Aware Generative Adversarial Networks

TL;DR

GAGAN introduces a novel GAN framework that incorporates geometric shape information into the image generation process, resulting in more realistic and attribute-controlled face images.

Contribution

The paper proposes GAGAN, a new approach that integrates statistical shape models into GANs to improve the realism and control of generated images.

Findings

GAGAN generates higher quality face images with diverse attributes.

Incorporating geometric information enhances the realism of generated objects.

GAGAN can augment existing GAN architectures for better image synthesis.

Abstract

Deep generative models learned through adversarial training have become increasingly popular for their ability to generate naturalistic image textures. However, aside from their texture, the visual appearance of objects is significantly influenced by their shape geometry; information which is not taken into account by existing generative models. This paper introduces the Geometry-Aware Generative Adversarial Networks (GAGAN) for incorporating geometric information into the image generation process. Specifically, in GAGAN the generator samples latent variables from the probability space of a statistical shape model. By mapping the output of the generator to a canonical coordinate frame through a differentiable geometric transformation, we enforce the geometry of the objects and add an implicit connection from the prior to the generated object. Experimental results on face generation indicate that the GAGAN can generate realistic images of faces with arbitrary facial attributes such as facial expression, pose, and morphology, that are of better quality than current GAN-based methods. Our method can be used to augment any existing GAN architecture and improve the quality of the images generated.