TL;DR该研究提出了一种使用网格训练 GAN 的方法来生成三维形状,这种训练方法允许更多的表现力和空间控制,并提出了一种基于统计分析的鲁棒性评估标准。
Abstract
Previous approaches to generate shapes in a 3D setting train a GAN on the
latent space of an autoencoder (AE). Even though this produces convincing
results, it has two major shortcomings. As the GAN is limited to reproduce the
dataset the AE was trained on, we cannot reuse a trained AE