Text-Guided Style Transfer-Based Image Manipulation Using Multimodal Generative Models

Togo, Ren; Kotera, Megumi; Ogawa, Takahiro et al.

IEEE Access, 2021, 9, 64860-64870

Permalink : https://hdl.handle.net/2115/81720

このアイテムのアクセス数:552件（2026-08-12 02:11 集計）

閲覧可能ファイル 

ファイル フォーマット サイズ 閲覧回数 説明
https://doi.org/10.1109/ACCESS.2021.3069876     14

論文情報

ファイル出力 EndNote Basic出力 Mendeley出力

アクセス権
open access
URI
https://hdl.handle.net/2115/81720
タイトル
Text-Guided Style Transfer-Based Image Manipulation Using Multimodal Generative Models
著者
Togo, Ren ; Kotera, Megumi ; Ogawa, Takahiro ; Haseyama, Miki
著者名
Togo, Ren
著者名
Kotera, Megumi
e-Rad_Researcher
20524028
著者名
Ogawa, Takahiro
e-Rad_Researcher
00218463
著者名
Haseyama, Miki
言語
英語
キーワード
Task analysis
Semantics
Feature extraction
Deep learning
Licenses
Electronic mail
Computational modeling
Style transfer
image manipulation
text-to-image synthesis
aesthetic analysis
generative model
発行日
2021-06-08
出版者
IEEE (Institute of Electrical and Electronics Engineers)
収録物名
IEEE Access
巻(号)
9
ページ
64860-64870
抄録
A new style transfer-based image manipulation framework combining generative networks and style transfer networks is presented in this paper. Unlike conventional style transfer tasks, we tackle a new task, text-guided image manipulation. We realize style transfer-based image manipulation that does not require any reference style images and generate a style image from the user's input sentence. In our method, since an initial reference input sentence for a content image can automatically be given by an image-to-text model, the user only needs to update the reference sentence. This scheme can help users when they do not have any images representing the desired style. Although this text-guided image manipulation is a new challenging task, quantitative and qualitative comparisons showed the superiority of our method.
資源タイプ
学術雑誌論文
出版タイプ
Version of Record
PISSN
2169-3536
関連情報 (isIdenticalTo)
出版社版DOI
https://doi.org/10.1109/ACCESS.2021.3069876