1. [Publications](/publications) 2. Efficient Geometry-aware 3D Generative Adversarial Networks # Efficient Geometry-aware 3D Generative Adversarial Networks ![](/sites/default/files/styles/wide/public/publications/teaser_4.jpg?itok=tIqDiFck) 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. ## Authors Eric R. Chan (Stanford University) Connor Z. Lin (Stanford University) Matthew A. Chan (Stanford University) [Koki Nagano](/person/koki-nagano) Boxiao Pan (Stanford University) [Shalini De Mello](/person/shalini-de-mello) Orazio Gallo (NVIDIA) Leonidas Guibas (Stanford University) [Jonathan Tremblay](/person/jonathan-tremblay) Sameh Khamis (NVIDIA) [Tero Karras](/person/tero-karras) Gordon Wetzstein (Stanford University) ## Publication Date Sunday, June 19, 2022 ## Published in [IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2022](https://cvpr2022.thecvf.com/) ## Research Area [Artificial Intelligence and Machine Learning ](/research-area/machine-learning-artificial-intelligence) [Computer Vision](/research-area/computer-vision) [Generative AI](/research-area/generative-ai) ## External Links [Project Page](https://nvlabs.github.io/eg3d/) [arXiv](https://arxiv.org/abs/2112.07945) [Code on GitHub](https://github.com/NVlabs/eg3d) ## Uploaded Files [Paper PDF](https://d1qx31qr3h6wln.cloudfront.net/publications/eg3d.pdf "Open file in new window")46.77 MB ## Award Oral ## Copyright This material is posted here with permission of the IEEE. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to .