TL;DR本文提出了利用 GAN 进行 3D 重建,并引入了 GAN 相机流形的概念,通过精准的相机控制,实现了真正自由视点的渲染,在输入少量的照片的同时具有明显的语义控制能力。
Abstract
Current generative adversarial networks (GANs) produce photorealistic
renderings of portrait images. Embedding real images into the latent space of
such models enables high-level image editing. While recent methods provide
considerable semantic control over the (re-)generated images, t