Lifting 2D StyleGAN for 3D-Aware Face Generation
This work addresses the problem of 3D-aware face generation for researchers and practitioners working with generative models, offering a self-supervised approach that avoids manual annotations or 3DMM models.
This paper introduces LiftedGAN, a self-supervised framework that disentangles a pre-trained StyleGAN2 to generate 3D-aware faces. It successfully disentangles latent space into texture, shape, viewpoint, and lighting, and generates 3D components for rendering synthetic images, outperforming existing methods in content controllability and image quality.
We propose a framework, called LiftedGAN, that disentangles and lifts a pre-trained StyleGAN2 for 3D-aware face generation. Our model is "3D-aware" in the sense that it is able to (1) disentangle the latent space of StyleGAN2 into texture, shape, viewpoint, lighting and (2) generate 3D components for rendering synthetic images. Unlike most previous methods, our method is completely self-supervised, i.e. it neither requires any manual annotation nor 3DMM model for training. Instead, it learns to generate images as well as their 3D components by distilling the prior knowledge in StyleGAN2 with a differentiable renderer. The proposed model is able to output both the 3D shape and texture, allowing explicit pose and lighting control over generated images. Qualitative and quantitative results show the superiority of our approach over existing methods on 3D-controllable GANs in content controllability while generating realistic high quality images.