Interactive style transfer: Towards styling user-specified object
Researches dealing with the task of style transfer have focused and produced results that only transfers the style of a reference image to the entirety of another image. As this domain would be beneficial in digital art, it would be preferable for such algorithms to support a more flexible style tra...
Saved in:
Main Authors: | , , , , |
---|---|
Format: | text |
Published: |
Animo Repository
2018
|
Subjects: | |
Online Access: | https://animorepository.dlsu.edu.ph/faculty_research/4386 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | De La Salle University |
id |
oai:animorepository.dlsu.edu.ph:faculty_research-5203 |
---|---|
record_format |
eprints |
spelling |
oai:animorepository.dlsu.edu.ph:faculty_research-52032022-11-16T02:52:29Z Interactive style transfer: Towards styling user-specified object Virtusio, John Jethro Talavera, Arces Tan, Daniel Stanley Hua, Kai Lung Azcarraga, Arnulfo P. Researches dealing with the task of style transfer have focused and produced results that only transfers the style of a reference image to the entirety of another image. As this domain would be beneficial in digital art, it would be preferable for such algorithms to support a more flexible style transfer, such that the style would be applied only on a specific portion of an image. We propose a framework that can selectively apply a given style onto an object using only 4 user-defined points. Our approach combines a style transfer module and an object segmentation module to synthesize the stylized image. As the ultimate goal is to develop an artistic application tool, we also introduce a method that makes use of specific filters to preserve certain characteristics of an image, such as its high frequency components. Experiments show that our proposed method is able to produce pleasing results with minimal effort while also being able to handle more complicated tasks such as the application of multiple reference style images onto different objects in an image. © 2018 IEEE. 2018-07-02T07:00:00Z text https://animorepository.dlsu.edu.ph/faculty_research/4386 info:doi/10.1109/VCIP.2018.8698689 Faculty Research Work Animo Repository Image segmentation Computer Sciences |
institution |
De La Salle University |
building |
De La Salle University Library |
continent |
Asia |
country |
Philippines Philippines |
content_provider |
De La Salle University Library |
collection |
DLSU Institutional Repository |
topic |
Image segmentation Computer Sciences |
spellingShingle |
Image segmentation Computer Sciences Virtusio, John Jethro Talavera, Arces Tan, Daniel Stanley Hua, Kai Lung Azcarraga, Arnulfo P. Interactive style transfer: Towards styling user-specified object |
description |
Researches dealing with the task of style transfer have focused and produced results that only transfers the style of a reference image to the entirety of another image. As this domain would be beneficial in digital art, it would be preferable for such algorithms to support a more flexible style transfer, such that the style would be applied only on a specific portion of an image. We propose a framework that can selectively apply a given style onto an object using only 4 user-defined points. Our approach combines a style transfer module and an object segmentation module to synthesize the stylized image. As the ultimate goal is to develop an artistic application tool, we also introduce a method that makes use of specific filters to preserve certain characteristics of an image, such as its high frequency components. Experiments show that our proposed method is able to produce pleasing results with minimal effort while also being able to handle more complicated tasks such as the application of multiple reference style images onto different objects in an image. © 2018 IEEE. |
format |
text |
author |
Virtusio, John Jethro Talavera, Arces Tan, Daniel Stanley Hua, Kai Lung Azcarraga, Arnulfo P. |
author_facet |
Virtusio, John Jethro Talavera, Arces Tan, Daniel Stanley Hua, Kai Lung Azcarraga, Arnulfo P. |
author_sort |
Virtusio, John Jethro |
title |
Interactive style transfer: Towards styling user-specified object |
title_short |
Interactive style transfer: Towards styling user-specified object |
title_full |
Interactive style transfer: Towards styling user-specified object |
title_fullStr |
Interactive style transfer: Towards styling user-specified object |
title_full_unstemmed |
Interactive style transfer: Towards styling user-specified object |
title_sort |
interactive style transfer: towards styling user-specified object |
publisher |
Animo Repository |
publishDate |
2018 |
url |
https://animorepository.dlsu.edu.ph/faculty_research/4386 |
_version_ |
1767196084207091712 |