Texture Networks: Feed-forward Synthesis of Textures and Stylized Images
Dmitry Ulyanov, Vadim Lebedev, Andrea, Victor Lempitsky
Abstract
Gatys et al. recently demonstrated that deep networks can generate beautiful textures and stylized images from a single texture example. However, their methods requires a slow and memory-consuming optimization process. We propose here an alternative approach that moves the computational burden to a learning stage. Given a single example of a texture, our approach trains compact feed-forward convolutional networks to generate multiple samples of the same texture of arbitrary size and to transfer artistic style from a given image to any other image. The resulting networks are remarkably light-weight and can generate textures of quality comparable to Gatys et al., but hundreds of times faster. More generally, our approach highlights the power and flexibility of generative feed-forward models trained with complex and expressive loss functions.
BibTeX
@InProceedings{pmlr-v48-ulyanov16,
title = {Texture Networks: Feed-forward Synthesis of Textures and Stylized Images},
author = {Ulyanov, Dmitry and Lebedev, Vadim and Andrea, and Lempitsky, Victor},
booktitle = {Proceedings of The 33rd International Conference on Machine Learning},
pages = {1349--1357},
year = {2016},
editor = {Balcan, Maria Florina and Weinberger, Kilian Q.},
volume = {48},
series = {Proceedings of Machine Learning Research},
address = {New York, New York, USA},
month = {20--22 Jun},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v48/ulyanov16.pdf},
url = {https://proceedings.mlr.press/v48/ulyanov16.html},
abstract = {Gatys et al. recently demonstrated that deep networks can generate beautiful textures and stylized images from a single texture example. However, their methods requires a slow and memory-consuming optimization process. We propose here an alternative approach that moves the computational burden to a learning stage. Given a single example of a texture, our approach trains compact feed-forward convolutional networks to generate multiple samples of the same texture of arbitrary size and to transfer artistic style from a given image to any other image. The resulting networks are remarkably light-weight and can generate textures of quality comparable to Gatys et al., but hundreds of times faster. More generally, our approach highlights the power and flexibility of generative feed-forward models trained with complex and expressive loss functions.}
}