BriefGPT.xyz
Feb, 2017
使用图卷积神经网络统一局部与非局部信号处理
Unifying local and non-local signal processing with graph CNNs
HTML
PDF
Gilles Puy, Srdan Kitic, Patrick Pérez
TL;DR
本文提出一种基于图卷积神经网络的本地和非本地信号处理的统一框架，并通过卷积层采用变量输入，从而使网络能够适应图结构的变化，进而设计了一种新的风格迁移方法。
Abstract
This paper deals with the unification of local and non-local
signal processing
on graphs within a single
convolutional neural network
(CNN) framework. Building upon recent works on
→