Recent works have shown that 3D-aware GANs trained on unstructured single
image collections can generate multiview images of novel instances. The key
underpinnings to achieve this are a 3D radiance field generator and a volume
rendering process. However, existing methods either cannot generate
high-resolution images (e.g., up to 256X256) due to the high computation cost
of neural volume rendering, or rely on 2D CNNs for image-space upsampling which
jeopardizes the 3D consistency across different views. This paper proposes a
novel 3D-aware GAN that can generate high resolution images (up to 1024X1024)
while keeping strict 3D consistency as in volume rendering. Our motivation is
to achieve super-resolution directly in the 3D space to preserve 3D
consistency. We avoid the otherwise prohibitively-expensive computation cost by
applying 2D convolutions on a set of 2D radiance manifolds defined in the
recent generative radiance manifold (GRAM) approach, and apply dedicated loss
functions for effective GAN training at high resolution. Experiments on FFHQ
and AFHQv2 datasets show that our method can produce high-quality 3D-consistent
results that significantly outperform existing methods.

本文提出了一种新的 3D-aware GAN，通过在最近的生成辐射流多面体（GRAM）方法定义的一组 2D 辐射流多面体上应用 2D 卷积并应用专用的损失函数进行高效 GAN 训练，从而避免了 prohibitively-expensive 的计算成本，并能够以体积渲染的严格 3D 一致性生成高分辨率图像（高达 1024X1024）。与现有方法相比，在 FFHQ 和 AFHQv2 数据集上的实验表明，我们的方法能够产生高质量的 3D-consistent 结果，明显优于现有的方法。