Exploring the structure of a real-time, arbitrary neural artistic stylization network. Ghiasi, G., Lee, H., Kudlur, M., Dumoulin, V., & Shlens, J. Procedings of the British Machine Vision Conference 2017, 2017. 249 citations (Semantic Scholar/DOI) [2023-12-14] Conference Name: British Machine Vision Conference 2017 ISBN: 9781901725605 Place: London, UK Publisher: British Machine Vision Association
Exploring the structure of a real-time, arbitrary neural artistic stylization network [link]Paper  doi  abstract   bibtex   
In this paper, we present a method which combines the flexibility of the neural algorithm of artistic style with the speed of fast style transfer networks to allow real-time stylization using any content/style image pair. We build upon recent work leveraging conditional instance normalization for multi-style transfer networks by learning to predict the conditional instance normalization parameters directly from a style image. The model is successfully trained on a corpus of roughly 80,000 paintings and is able to generalize to paintings previously unobserved. We demonstrate that the learned embedding space is smooth and contains a rich structure and organizes semantic information associated with paintings in an entirely unsupervised manner.
@article{ghiasi_exploring_2017,
	title = {Exploring the structure of a real-time, arbitrary neural artistic stylization network},
	url = {http://www.bmva.org/bmvc/2017/papers/paper114/index.html},
	doi = {10.5244/C.31.114},
	abstract = {In this paper, we present a method which combines the flexibility of the neural algorithm of artistic style with the speed of fast style transfer networks to allow real-time stylization using any content/style image pair. We build upon recent work leveraging conditional instance normalization for multi-style transfer networks by learning to predict the conditional instance normalization parameters directly from a style image. The model is successfully trained on a corpus of roughly 80,000 paintings and is able to generalize to paintings previously unobserved. We demonstrate that the learned embedding space is smooth and contains a rich structure and organizes semantic information associated with paintings in an entirely unsupervised manner.},
	language = {en},
	urldate = {2023-12-14},
	journal = {Procedings of the British Machine Vision Conference 2017},
	author = {Ghiasi, Golnaz and Lee, Honglak and Kudlur, Manjunath and Dumoulin, Vincent and Shlens, Jonathon},
	year = {2017},
	note = {249 citations (Semantic Scholar/DOI) [2023-12-14]
Conference Name: British Machine Vision Conference 2017
ISBN: 9781901725605
Place: London, UK
Publisher: British Machine Vision Association},
	pages = {114},
}

Downloads: 0