Photorealistic image style transfer algorithms aim at stylizing a content
photo using the style of a reference photo with the constraint that the
stylized photo should remains photorealistic. While several methods exist for
this task, they tend to generate spatially inconsistent stylizations with
noticeable artifacts. In addition, these methods are computationally expensive,
requiring several minutes to stylize a VGA photo. In this paper, we present a
novel algorithm to address the limitations. The proposed algorithm consists of
a stylization step and a smoothing step. While the stylization step transfers
the style of the reference photo to the content photo, the smoothing step
encourages spatially consistent stylizations. Unlike existing algorithms that
require iterative optimization, both steps in our algorithm have closed-form
solutions. Experimental results show that the stylized photos generated by our
algorithm are twice more preferred by human subjects in average. Moreover, our
method runs 60 times faster than the state-of-the-art approach. Code and
additional results are available at <a href="https://github.com/NVIDIA/FastPhotoStyle">this https URL</a> .
%0 Generic
%1 citeulike:14553960
%A xxx,
%D 2018
%K deconv metric semisup style\_transfer
%T A Closed-form Solution to Photorealistic Image Stylization
%U http://arxiv.org/abs/1802.06474
%X Photorealistic image style transfer algorithms aim at stylizing a content
photo using the style of a reference photo with the constraint that the
stylized photo should remains photorealistic. While several methods exist for
this task, they tend to generate spatially inconsistent stylizations with
noticeable artifacts. In addition, these methods are computationally expensive,
requiring several minutes to stylize a VGA photo. In this paper, we present a
novel algorithm to address the limitations. The proposed algorithm consists of
a stylization step and a smoothing step. While the stylization step transfers
the style of the reference photo to the content photo, the smoothing step
encourages spatially consistent stylizations. Unlike existing algorithms that
require iterative optimization, both steps in our algorithm have closed-form
solutions. Experimental results show that the stylized photos generated by our
algorithm are twice more preferred by human subjects in average. Moreover, our
method runs 60 times faster than the state-of-the-art approach. Code and
additional results are available at <a href="https://github.com/NVIDIA/FastPhotoStyle">this https URL</a> .
@misc{citeulike:14553960,
abstract = {{Photorealistic image style transfer algorithms aim at stylizing a content
photo using the style of a reference photo with the constraint that the
stylized photo should remains photorealistic. While several methods exist for
this task, they tend to generate spatially inconsistent stylizations with
noticeable artifacts. In addition, these methods are computationally expensive,
requiring several minutes to stylize a VGA photo. In this paper, we present a
novel algorithm to address the limitations. The proposed algorithm consists of
a stylization step and a smoothing step. While the stylization step transfers
the style of the reference photo to the content photo, the smoothing step
encourages spatially consistent stylizations. Unlike existing algorithms that
require iterative optimization, both steps in our algorithm have closed-form
solutions. Experimental results show that the stylized photos generated by our
algorithm are twice more preferred by human subjects in average. Moreover, our
method runs 60 times faster than the state-of-the-art approach. Code and
additional results are available at <a href="https://github.com/NVIDIA/FastPhotoStyle">this https URL</a> .}},
added-at = {2019-02-27T22:23:29.000+0100},
archiveprefix = {arXiv},
author = {xxx},
biburl = {https://www.bibsonomy.org/bibtex/20aea4e00051ae492e77395551cfe8a1e/nmatsuk},
citeulike-article-id = {14553960},
citeulike-linkout-0 = {http://arxiv.org/abs/1802.06474},
citeulike-linkout-1 = {http://arxiv.org/pdf/1802.06474},
day = 22,
eprint = {1802.06474},
interhash = {a23bee8fb98556b320c107f24547c63b},
intrahash = {0aea4e00051ae492e77395551cfe8a1e},
keywords = {deconv metric semisup style\_transfer},
month = feb,
posted-at = {2018-03-22 07:41:14},
priority = {0},
timestamp = {2019-02-27T22:23:29.000+0100},
title = {{A Closed-form Solution to Photorealistic Image Stylization}},
url = {http://arxiv.org/abs/1802.06474},
year = 2018
}