使用随机卷积滤波器的浅层卷积神经网络纹理合成

May, 2016

使用随机卷积滤波器的浅层卷积神经网络纹理合成

Texture Synthesis Using Shallow Convolutional Networks with Random Filters

Ivan Ustyuzhaninov, Wieland Brendel, Leon A. Gatys, Matthias Bethge

TL;DR研究表明，随机浅层卷积神经网络的特征空间可以作为自然纹理的模型，可以用于纹理合成算法，并且相较于深层CNNs模型，浅层CNNs模型具有相当的性能。

Abstract

Here we demonstrate that the feature space of random shallow convolutional neural networks (CNNs) can serve as a surprisingly good model of natural textures. Patches from the same texture are consistently classif