Arbitrary style transfer using neurally-guided patch-based synthesis

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F20%3A00340340" target="_blank" >RIV/68407700:21230/20:00340340 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1016/j.cag.2020.01.002" target="_blank" >https://doi.org/10.1016/j.cag.2020.01.002</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1016/j.cag.2020.01.002" target="_blank" >10.1016/j.cag.2020.01.002</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Arbitrary style transfer using neurally-guided patch-based synthesis

Popis výsledku v původním jazyce

We present a new approach to example-based style transfer combining neural methods with patch-based synthesis to achieve compelling stylization quality even for high-resolution imagery. We take advantage of neural techniques to provide adequate stylization at the global level and use their output as a prior for subsequent patch-based synthesis at the detail level. Thanks to this combination, our method keeps the high frequencies of the original artistic media better, thereby dramatically increases the fidelity of the resulting stylized imagery. We show how to stylize extremely large images (e.g., 340 Mpix) without the need to run the synthesis at the pixel level, yet retaining the original high-frequency details. We demonstrate the power and generality of this approach on a novel stylization algorithm that delivers comparable visual quality to state-of-art neural style transfer while completely eschewing any purpose-trained stylization blocks and only using the response of a feature extractor as guidance for patch-based synthesis.

Název v anglickém jazyce

Arbitrary style transfer using neurally-guided patch-based synthesis

Popis výsledku anglicky

We present a new approach to example-based style transfer combining neural methods with patch-based synthesis to achieve compelling stylization quality even for high-resolution imagery. We take advantage of neural techniques to provide adequate stylization at the global level and use their output as a prior for subsequent patch-based synthesis at the detail level. Thanks to this combination, our method keeps the high frequencies of the original artistic media better, thereby dramatically increases the fidelity of the resulting stylized imagery. We show how to stylize extremely large images (e.g., 340 Mpix) without the need to run the synthesis at the pixel level, yet retaining the original high-frequency details. We demonstrate the power and generality of this approach on a novel stylization algorithm that delivers comparable visual quality to state-of-art neural style transfer while completely eschewing any purpose-trained stylization blocks and only using the response of a feature extractor as guidance for patch-based synthesis.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2020

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Computers & Graphics

ISSN

0097-8493

e-ISSN

1873-7684

Svazek periodika

87

Číslo periodika v rámci svazku

1

Stát vydavatele periodika

GB - Spojené království Velké Británie a Severního Irska

Počet stran výsledku

10

Strana od-do

62-71

Kód UT WoS článku

000527936700007

EID výsledku v databázi Scopus

2-s2.0-85079391552