Arbitrary style transfer in real-time with adaptive instance normalization
Research output: Contribution to conference › Paper › Research › peer-review
Standard
Arbitrary style transfer in real-time with adaptive instance normalization. / Huang, Xun; Belongie, Serge.
2019. Paper presented at 5th International Conference on Learning Representations, ICLR 2017, Toulon, France.Research output: Contribution to conference › Paper › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - CONF
T1 - Arbitrary style transfer in real-time with adaptive instance normalization
AU - Huang, Xun
AU - Belongie, Serge
N1 - Publisher Copyright: © 5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings. All Rights Reserved.
PY - 2019
Y1 - 2019
N2 - Gatys et al. (2015) recently introduced a neural algorithm that renders a content image in the style of another image, achieving so-called style transfer. However, their framework requires a slow iterative optimization process, which limits its practical application. Fast approximations with feed-forward neural networks have been proposed to speed up neural style transfer. Unfortunately, the speed improvement comes at a cost: the network is usually tied to a fixed set of styles and cannot adapt to arbitrary new styles. In this paper, we present a simple yet effective approach that for the first time enables arbitrary style transfer in real-time. At the heart of our method is a novel adaptive instance normalization (AdaIN) layer that aligns the mean and variance of the content features with those of the style features. Our method achieves speed comparable to the fastest existing approach, without the restriction to a pre-defined set of styles.
AB - Gatys et al. (2015) recently introduced a neural algorithm that renders a content image in the style of another image, achieving so-called style transfer. However, their framework requires a slow iterative optimization process, which limits its practical application. Fast approximations with feed-forward neural networks have been proposed to speed up neural style transfer. Unfortunately, the speed improvement comes at a cost: the network is usually tied to a fixed set of styles and cannot adapt to arbitrary new styles. In this paper, we present a simple yet effective approach that for the first time enables arbitrary style transfer in real-time. At the heart of our method is a novel adaptive instance normalization (AdaIN) layer that aligns the mean and variance of the content features with those of the style features. Our method achieves speed comparable to the fastest existing approach, without the restriction to a pre-defined set of styles.
UR - http://www.scopus.com/inward/record.url?scp=85083950854&partnerID=8YFLogxK
M3 - Paper
AN - SCOPUS:85083950854
T2 - 5th International Conference on Learning Representations, ICLR 2017
Y2 - 24 April 2017 through 26 April 2017
ER -
ID: 301823730