3D物体生成和重建的改进对抗性系统

Jul, 2017

3D物体生成和重建的改进对抗性系统

Improved Adversarial Systems for 3D Object Generation and Reconstruction

Edward Smith, David Meger

TL;DR本研究提出了一种新方法，用于通过生成式对抗网络（GAN）训练理解物体的详细三维形状以及从二维图像中重建三维形状和形状完成。该方法使用梯度惩罚的Wasserstein距离作为训练目标，从而从联合对象形状分布中获得更好的生成效果，并在与现有基线比较中取得了明显的数量级改进。

Abstract

This paper describes a new approach for training generative adversarial networks (GAN) to understand the detailed 3d shape of objects. While GANs have been used in this domain previously, they are notoriously har