Larissa T. Triess, Andre Bühler, David Peter, Fabian B. Flohr, J. Marius Zöllner
TL;DR使用辅助分类器 GAN 和核密度估计的生成对抗网络，能够在生成高质量高多样性 3D 对象的同时实现对其属性的控制。
Abstract
generative models can be used to synthesize 3d objects of high quality and diversity. However, there is typically no control over the properties of the generated object.This paper proposes a novel →