The network is capable of generating 2D photos of human and cat faces and turning them into 3D objects.
According to the team, their framework is able to leverage state-of-the-art 2D CNN generators, such as StyleGAN2, and inherit their efficiency and expressiveness by decoupling feature generation and neural rendering. The goal of the project was to improve the computational efficiency and image quality of 3D GANs without overly relying on approximations that affect multi-view consistency and shape quality
Click here to learn more about the network and access its code.