Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning

TL;DR

DiscoFaceGAN introduces a novel face generation method that combines 3D priors with contrastive learning to achieve highly disentangled and controllable virtual face images, advancing face synthesis technology.

Contribution

The paper presents a new approach integrating 3D priors with imitative-contrastive learning for precise control and disentanglement in face image generation.

Findings

Effective disentanglement of identity, expression, pose, and illumination.

Precise control over generated face properties.

Ability to embed real images into the learned latent space.

Abstract

We propose DiscoFaceGAN, an approach for face image generation of virtual people with disentangled, precisely-controllable latent representations for identity of non-existing people, expression, pose, and illumination. We embed 3D priors into adversarial learning and train the network to imitate the image formation of an analytic 3D face deformation and rendering process. To deal with the generation freedom induced by the domain gap between real and rendered faces, we further introduce contrastive learning to promote disentanglement by comparing pairs of generated images. Experiments show that through our imitative-contrastive learning, the factor variations are very well disentangled and the properties of a generated face can be precisely controlled. We also analyze the learned latent space and present several meaningful properties supporting factor disentanglement. Our method can also be used to embed real images into the disentangled latent space. We hope our method could provide new understandings of the relationship between physical properties and deep image synthesis.