STALP: Style Transfer With Auxiliary Limited Pairing

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F21%3A00349941" target="_blank" >RIV/68407700:21230/21:00349941 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1111/cgf.142655" target="_blank" >https://doi.org/10.1111/cgf.142655</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1111/cgf.142655" target="_blank" >10.1111/cgf.142655</a>

Jazyk výsledku

angličtina

Název v původním jazyce

STALP: Style Transfer With Auxiliary Limited Pairing

Popis výsledku v původním jazyce

We present an approach to example-based stylization of images that uses a single pair of a source image and its stylized counterpart. We demonstrate how to train an image translation network that can perform real-time semantically meaningful style transfer to a set of target images with similar content as the source image. A key added value of our approach is that it considers also consistency of target images during training. Although those have no stylized counterparts, we constrain the translation to keep the statistics of neural responses compatible with those extracted from the stylized source. In contrast to concurrent techniques that use a similar input, our approach better preserves important visual characteristics of the source style and can deliver temporally stable results without the need to explicitly handle temporal consistency. We demonstrate its practical utility on various applications including video stylization, style transfer to panoramas, faces, and 3D models.

Název v anglickém jazyce

STALP: Style Transfer With Auxiliary Limited Pairing

Popis výsledku anglicky

We present an approach to example-based stylization of images that uses a single pair of a source image and its stylized counterpart. We demonstrate how to train an image translation network that can perform real-time semantically meaningful style transfer to a set of target images with similar content as the source image. A key added value of our approach is that it considers also consistency of target images during training. Although those have no stylized counterparts, we constrain the translation to keep the statistics of neural responses compatible with those extracted from the stylized source. In contrast to concurrent techniques that use a similar input, our approach better preserves important visual characteristics of the source style and can deliver temporally stable results without the need to explicitly handle temporal consistency. We demonstrate its practical utility on various applications including video stylization, style transfer to panoramas, faces, and 3D models.

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

<a href="/cs/project/EF16_019%2F0000765" target="_blank" >EF16_019/0000765: Výzkumné centrum informatiky</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2021

Kód důvěrnosti údajů

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

Název periodika

Computer Graphics Forum

ISSN

0167-7055

e-ISSN

1467-8659

Svazek periodika

40

Číslo periodika v rámci svazku

2

Stát vydavatele periodika

CH - Švýcarská konfederace

Počet stran výsledku

11

Strana od-do

563-573

Kód UT WoS článku

000657959600046

EID výsledku v databázi Scopus

2-s2.0-85107365098