Enhancing Neural Style Transfer using Patch-Based Synthesis
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F19%3A00331355" target="_blank" >RIV/68407700:21230/19:00331355 - isvavai.cz</a>
Result on the web
<a href="https://dcgi.fel.cvut.cz/home/sykorad/stylitneural.html" target="_blank" >https://dcgi.fel.cvut.cz/home/sykorad/stylitneural.html</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.2312/exp.20191075" target="_blank" >10.2312/exp.20191075</a>
Alternative languages
Result language
angličtina
Original language name
Enhancing Neural Style Transfer using Patch-Based Synthesis
Original language description
We present a new approach to example-based style transfer which combines 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 also 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.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2019
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the 8th ACM/EG Expressive Symposium
ISBN
978-3-03868-078-9
ISSN
—
e-ISSN
—
Number of pages
8
Pages from-to
43-50
Publisher name
Eurographics Association
Place of publication
Aire-la-Ville
Event location
Janov
Event date
May 5, 2019
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—