TY - JOUR
T1 - Neural Style Transfer
T2 - A Review
AU - Jing, Yongcheng
AU - Yang, Yezhou
AU - Feng, Zunlei
AU - Ye, Jingwen
AU - Yu, Yizhou
AU - Song, Mingli
N1 - Funding Information:
This work is supported by National Key Research and Development Program(2016YFB1200203), NationalNatural Science Foundation of China (61572428,U1509206), Key Research and Development Program of Zhejiang Province (2018C01004), the Program of International Science and Technology Cooperation (2013DFG12840) and the Fundamental Research Funds for the Central Universities.
Funding Information:
This work is supported by National Key Research and Development Program (2016YFB1200203), National Natural Science Foundation of China (61572428,U1509206), Key Research and Development Program of Zhejiang Province (2018C01004), the Program of International Science and Technology Cooperation (2013DFG12840) and the Fundamental Research Funds for the Central Universities.
Publisher Copyright:
© 1995-2012 IEEE.
PY - 2020/11/1
Y1 - 2020/11/1
N2 - 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://osf.io/f8tu4/.
AB - 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://osf.io/f8tu4/.
KW - Neural style transfer (NST)
KW - convolutional neural network (CNN)
UR - http://www.scopus.com/inward/record.url?scp=85092680398&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85092680398&partnerID=8YFLogxK
U2 - 10.1109/TVCG.2019.2921336
DO - 10.1109/TVCG.2019.2921336
M3 - Article
C2 - 31180860
AN - SCOPUS:85092680398
SN - 1077-2626
VL - 26
SP - 3365
EP - 3385
JO - IEEE Transactions on Visualization and Computer Graphics
JF - IEEE Transactions on Visualization and Computer Graphics
IS - 11
M1 - 8732370
ER -