Texture and art with deep neural networks

被引：52

作者：

Gatys, Leon A. ^{[1
,2
,3
,4
]}

Ecker, Alexander S. ^{[1
,2
,3
,6
]}

Bethge, Matthias ^{[1
,2
,3
,5
]}

机构：

[1] Univ Tubingen, Werner Reichardt Ctr Integrat Neurosci, Tubingen, Germany

[2] Univ Tubingen, Inst Theoret Phys, Tubingen, Germany

[3] Bernstein Ctr Computat Neurosci, Tubingen, Germany

[4] Grad Sch Neural Informat Proc, Tubingen, Germany

[5] Max Planck Inst Biol Cybernet, Tubingen, Germany

[6] Baylor Coll Med, Dept Neurosci, Houston, TX 77030 USA

来源：

CURRENT OPINION IN NEUROBIOLOGY | 2017年 / 46卷

关键词：

STATISTICS; RECOGNITION; MODEL;

D O I：

10.1016/j.conb.2017.08.019

中图分类号：

Q189 [神经科学];

学科分类号：

071006 ;

摘要：

Although the study of biological vision and computer vision attempt to understand powerful visual information processing from different angles, they have a long history of informing each other. Recent advances in texture synthesis that were motivated by visual neuroscience have led to a substantial advance in image synthesis and manipulation in computer vision using convolutional neural networks (CNNs). Here, we review these recent advances and discuss how they can in turn inspire new research in visual perception and computational neuroscience.

引用

页码：178 / 186

页数：9