Efficient Geometry-aware 3D Generative Adversarial Networks

🤖 Plain-English Summary

Unsupervised generation of high-quality multi-view-consistent images and 3D shapes using only collections of single-view 2D photographs has been a long-standing challenge. By decoupling feature generation and neural rendering, our framework is able to leverage advanced 2D CNN generators, such as StyleGAN2, and inherit their efficiency and expressiveness.

🔑 Key Findings

• Existing 3D GANs are either compute intensive or make approximations that are not 3D-consistent; the former limits quality and resolution of the generated images and the latter adversely affects multi-view consistency and shape quality.
• In this work, we improve the computational efficiency and image quality of 3D GANs without overly relying on these approximations.
• We introduce an expressive hybrid explicit implicit network architecture that, together with other design choices, synthesizes not only high-resolution multi-view-consistent images in real time but also produces high-quality 3D geometry.

🔗 Related Resources