.png){kind=icon}
返回
CLAST: Contrastive Learning for Arbitrary Style Transfer
.png){kind=icon}
PRE
AI
DOI：10.1109/TIP.2022.3215899.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Arbitrary style transfer aims at migrating the style of a reference style painting to a target content image. Existing methods find it challenging to achieve good content fidelity and style migration at the same time. Moreover, they all rely on manually defined content and style, which is of limited universality and robustness. In this paper, we propose to introduce contrastive learning into style transfer, instructing the network to automatically learn to model the structural content and artistic style based on natural contrastive relationships in style transfer. Compared with existing methods, our learned modeling of content and style is more robust and universal. In addition, we further propose instance-wise contrastive style losses and a patch-wise contrastive content loss to guide style transfer. Combining the proposed contrastive losses and two self-reconstruction strategies, we develop a new style transfer framework, which is pluggable and can be flexibly applied to various style transfer modules. Experimental results demonstrate that our method has strong flexibility and synthesizes stylized images with higher quality.
Keyword:
Feature extraction
Painting
Training
Neural networks
Loss measurement
Modulation
Generative adversarial networks
Style transfer
image synthesis
contrastive learning
image processing
self-supervised learning
期刊
IF:
13.7
论文数:
1.0W
被引数:
8.4W
机构
引用论文
ARVino - outdoor augmented reality visualisation of viticulture GIS dataARVino-葡萄栽培GIS数据的户外增强现实可视化
OAAI
.png){kind=icon}
OAAI分享收藏分享收藏分享收藏Spectrophotometric Determination of Carbon Disulfide Using Bis(4-(4 -Nitrophenyl)azo-2-Nitrophenyl) Disulfide双 (4-硝基苯基) azo-2-Nitrophenyl) 二硫化物分光光度法测定二硫化碳
PREAI
分享收藏Exploring the causality links between financial markets and foreign direct investment in Africa
PREAI
分享收藏
查看更多内容