BriefGPT.xyz
Dec, 2017
基于示例生成对抗网络的眼睛修复
Eye In-Painting with Exemplar Generative Adversarial Networks
HTML
PDF
Brian Dolhansky, Cristian Canton Ferrer
TL;DR
本文提出一种基于 Exemplar GANs 的新型修复方法,可以利用样本信息,生成高质量、个性化的修复结果,并且在多个点插入其它信息以增加描述能力,将此方法应用于天然图片中的眼睛修复任务,并开发了新的数据集进行比较。
Abstract
This paper introduces a novel approach to
in-painting
where the identity of the object to remove or change is preserved and accounted for at inference time:
exemplar gans
(ExGANs). ExGANs are a type of conditiona
→