Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning
arXiv:2004.11660
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.
Accepted by CVPR2020 (Oral)
References in corpus (12)
- Conditional Generative Adversarial Nets
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Progressive Growing of GANs for Improved Quality, Stability, and Variation
- Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
- Deep Convolutional Inverse Graphics Network
- Disentangling by Factorising
- Invertible Conditional GANs for image editing
- Single Image Portrait Relighting
- Diagnosing and Enhancing VAE Models
- Disentangling Factors of Variation via Generative Entangling
- Understanding Visual Concepts with Continuation Learning
- FaceFeat-GAN: a Two-Stage Approach for Identity-Preserving Face Synthesis