arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1705.04058cs.CVcs.NEeess.IVstat.ML
收藏

神经风格迁移研究进展

Neural Style Transfer: A Review

Microsoft Visual Perception Laboratory(微软视觉感知实验室);College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院);School of Computing, Informatics, and Decision Systems Engineering, Arizona State University(亚利桑那州立大学计算、信息学与决策系统工程学院);Department of Computer Science, The University of Hong Kong(香港大学计算机科学系)

Yongcheng Jing, Yezhou Yang, Zunlei Feng, Jingwen Ye, Yizhou Yu, Mingli Song

摘要:

Gatys等人的开创性工作证明了卷积神经网络(CNN)通过分离和重组图像内容和风格来创建艺术图像的能力。这种使用CNN以不同风格渲染内容图像的过程被称为神经风格转移(NST)。从那时起,NST已成为学术文献和工业应用的热门话题。它正受到越来越多的关注,并提出了各种方法来改进或扩展原始NST算法。在本文中,我们的目的是提供一个全面的概述目前的进展NST。首先,我们提出了一个分类的NST领域的当前算法。然后,我们提出了几种评价方法,并比较不同的NST算法定性和定量。评论的结论与讨论的各种应用NST和开放的问题,为今后的研究。本文讨论的论文列表、相应的代码、预训练模型和更多比较结果可在https://github.com/ycjing/Neural-Style-Transfer-Papers上公开获取。

英文摘要:

The seminal work of Gatys et al. demonstrated the power of Convolutional Neural Networks (CNNs) in creating artistic imagery by separating and recombining image content and style. This process of using CNNs to render a content image in different styles is referred to as Neural Style Transfer (NST). Since then, NST has become a trending topic both in academic literature and industrial applications. It is receiving increasing attention and a variety of approaches are proposed to either improve or extend the original NST algorithm. In this paper, we aim to provide a comprehensive overview of the current progress towards NST. We first propose a taxonomy of current algorithms in the field of NST. Then, we present several evaluation methods and compare different NST algorithms both qualitatively and quantitatively. The review concludes with a discussion of various applications of NST and open problems for future research. A list of papers discussed in this review, corresponding codes, pre-trained models and more comparison results are publicly available at https://github.com/ycjing/Neural-Style-Transfer-Papers.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑