Guided neural style transfer for shape stylization.
Designing logos, typefaces, and other decorated shapes can require professional skills. In this paper, we aim to produce new and unique decorated shapes by stylizing ordinary shapes with machine learning. Specifically, we combined parametric and non-parametric neural style transfer algorithms to tra...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2020-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0233489 |
| _version_ | 1819017346524643328 |
|---|---|
| author | Gantugs Atarsaikhan Brian Kenji Iwana Seiichi Uchida |
| author_facet | Gantugs Atarsaikhan Brian Kenji Iwana Seiichi Uchida |
| author_sort | Gantugs Atarsaikhan |
| collection | DOAJ |
| description | Designing logos, typefaces, and other decorated shapes can require professional skills. In this paper, we aim to produce new and unique decorated shapes by stylizing ordinary shapes with machine learning. Specifically, we combined parametric and non-parametric neural style transfer algorithms to transfer both local and global features. Furthermore, we introduced a distance-based guiding to the neural style transfer process, so that only the foreground shape will be decorated. Lastly, qualitative evaluation and ablation studies are provided to demonstrate the usefulness of the proposed method. |
| first_indexed | 2024-12-21T03:02:04Z |
| format | Article |
| id | doaj.art-041ba0587a7142ba8535fb7e336bc3f8 |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-12-21T03:02:04Z |
| publishDate | 2020-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-041ba0587a7142ba8535fb7e336bc3f82022-12-21T19:18:08ZengPublic Library of Science (PLoS)PLoS ONE1932-62032020-01-01156e023348910.1371/journal.pone.0233489Guided neural style transfer for shape stylization.Gantugs AtarsaikhanBrian Kenji IwanaSeiichi UchidaDesigning logos, typefaces, and other decorated shapes can require professional skills. In this paper, we aim to produce new and unique decorated shapes by stylizing ordinary shapes with machine learning. Specifically, we combined parametric and non-parametric neural style transfer algorithms to transfer both local and global features. Furthermore, we introduced a distance-based guiding to the neural style transfer process, so that only the foreground shape will be decorated. Lastly, qualitative evaluation and ablation studies are provided to demonstrate the usefulness of the proposed method.https://doi.org/10.1371/journal.pone.0233489 |
| spellingShingle | Gantugs Atarsaikhan Brian Kenji Iwana Seiichi Uchida Guided neural style transfer for shape stylization. PLoS ONE |
| title | Guided neural style transfer for shape stylization. |
| title_full | Guided neural style transfer for shape stylization. |
| title_fullStr | Guided neural style transfer for shape stylization. |
| title_full_unstemmed | Guided neural style transfer for shape stylization. |
| title_short | Guided neural style transfer for shape stylization. |
| title_sort | guided neural style transfer for shape stylization |
| url | https://doi.org/10.1371/journal.pone.0233489 |
| work_keys_str_mv | AT gantugsatarsaikhan guidedneuralstyletransferforshapestylization AT briankenjiiwana guidedneuralstyletransferforshapestylization AT seiichiuchida guidedneuralstyletransferforshapestylization |