Shiyang Cheng, Michael Bronstein, Yuxiang Zhou, Irene Kotsia, Maja Pantic...
TL;DR本文提出了一种名为 MeshGAN 的新型的生成对抗网络架构,该架构可以直接操作 3D 网格,成功应用于 3D 人脸表情生成。
Abstract
generative adversarial networks (gans) are currently the method of choice for
generating visual data. Certain GAN architectures and training methods have
demonstrated exceptional performance in generating realist