What is really needed to make an existing 2D GAN 3D-aware? To answer this question, we modify a classical GAN, i.e., StyleGANv2, as little as possible. We find that only two modifications are absolutely necessary: 1) a multiplane image style generator branch which produces a set of alpha maps conditioned on their depth; 2) a pose-conditioned discriminator. We refer to the generated output as a 'generative multiplane image' (GMPI) and emphasize that its renderings are not only high-quality but also guaranteed to be view-consistent, which makes GMPIs different from many prior works. Importantly, the number of alpha maps can be dynamically adjusted and can differ between training and inference, alleviating memory concerns and enabling fast training of GMPIs in less than half a day at a resolution of $1024^2$. Our findings are consistent across three challenging and common high-resolution datasets, including FFHQ, AFHQv2, and MetFaces.

这篇论文通过对传统的GAN模型StyleGANv2进行尽可能少的改动，引入一个多平面图像生成器和姿态条件鉴别器，实现了一种名为“生成性多平面图像”的输出，它的渲染不仅高质量而且保证视角的一致性，并能够在不到半天的时间内以$1024^2$的分辨率训练。

生成多层平面图像：使2D GAN具备3D感知能力