论文标题
通过3D模仿对抗性学习解开且可控的面部图像生成
Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning
论文作者
论文摘要
我们提出了Discofacegan，这是一种针对虚拟人的面部图像产生的方法，该虚拟人具有散布的，可控制的潜在表示，用于不存在的人的身份，表达，姿势和照明。我们将3D先验嵌入对抗性学习中，并训练网络以模仿分析性3D面部变形和渲染过程的图像形成。为了应对真实面孔和渲染面之间的域间隙引起的一代自由，我们进一步引入了对比度学习，以通过比较生成的图像对来促进分离。实验表明，通过我们的模仿对抗性学习，因子变化非常明确，并且可以精确控制生成的面部的特性。我们还分析了学习的潜在空间，并介绍了支持因子分解的几个有意义的特性。我们的方法还可以用来将真实图像嵌入分离的潜在空间中。我们希望我们的方法可以对物理特性与深层图像合成之间的关系提供新的理解。
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.
