Alexander W. Bergman, Petr Kellnhofer, Wang Yifan, Eric R. Chan, David B. Lindell...
TL;DR提出使用 3D GAN 框架对人体或脸部特征进行辐射场生成,通过显式变形场将其变形为期望的姿势或表情,并展示了编辑生成体或脸部特征时显式变形训练过程在提高其质量方面的显著优势。
Abstract
unsupervised learning of 3D-aware generative adversarial networks (GANs)
using only collections of single-view 2D photographs has very recently made
much progress. These 3d gans, however, have not been demonstrat