Efficient Geometry-aware 3D Generative Adversarial Networks
This addresses the problem of inefficient and inconsistent 3D generation for computer vision and graphics applications, representing a significant but incremental advance over existing methods.
The paper tackles the challenge of generating high-quality, multi-view-consistent 3D images and shapes from single-view 2D photos by improving computational efficiency and image quality in 3D GANs, achieving state-of-the-art synthesis with datasets like FFHQ and AFHQ Cats.
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. 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. By decoupling feature generation and neural rendering, our framework is able to leverage state-of-the-art 2D CNN generators, such as StyleGAN2, and inherit their efficiency and expressiveness. We demonstrate state-of-the-art 3D-aware synthesis with FFHQ and AFHQ Cats, among other experiments.