BriefGPT.xyz
Nov, 2017
In2I ：基于生成对抗网络的无监督多图像到图像转换
In2I : Unsupervised Multi-Image-to-Image Translation Using Generative Adversarial Networks
HTML
PDF
Pramuditha Perera, Mahdi Abavisani, Vishal M. Patel
TL;DR
本文介绍了一种利用多个输入域来实现图像翻译的方案，使用基于生成对抗网络的多模式生成器结构和一种新的损失项，潜在一致性损失，实现了比现有无监督图像到图像转换方法更好的转换效果。
Abstract
In
unsupervised image-to-image translation
, the goal is to learn the mapping between an input image and an output image using a set of unpaired training images. In this paper, we propose an extension of the
unsupervised
→