View in EDS HTML Full Text PDF Full Text

Local part attention for image stylization with text prompt.

Saved in:
Bibliographic Details
Title: Local part attention for image stylization with text prompt.
Authors: Truong, Quoc-Truong1,2 (AUTHOR), Nguyen, Vinh-Tiep1,2 (AUTHOR) tiepnv@uit.edu.vn, Nguyen, Lan-Phuong1,2 (AUTHOR), Cao, Hung-Phu1,2 (AUTHOR), Luu, Duc-Tuan1,2 (AUTHOR)
Source: Neural Computing & Applications. Dec2024, Vol. 36 Issue 34, p21859-21871. 13p.
Subjects: Lips, Hair
Abstract: Prompt-based portrait image style transfer aims at translating an input content image to a desired style described by text without a style image. In many practical situations, users may not only attend to the entire portrait image but also the local parts (e.g., eyes, lips, and hair). To address such applications, we propose a new framework that enables style transfer on specific regions described by a text description of the desired style. Specifically, we incorporate semantic segmentation to identify the intended area without requiring edit masks from the user while utilizing a pre-trained CLIP-based model for stylizing. Besides, we propose a text-to-patch matching loss by randomly dividing the stylized image into smaller patches to ensure the consistent quality of the result. To comprehensively evaluate the proposed method, we use several metrics, such as FID, SSIM, and PSNR on a dataset consisting of portraits from the CelebAMask-HQ dataset and style descriptions of other related works. Extensive experimental results demonstrate that our framework outperforms other state-of-the-art methods in terms of both stylization quality and inference time. [ABSTRACT FROM AUTHOR]
Copyright of Neural Computing & Applications is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Full text is not displayed to guests.
FullText Links:
  – Type: pdflink
Text:
  Availability: 1
Header DbId: egs
DbLabel: Engineering Source
An: 181069363
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Local part attention for image stylization with text prompt.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Truong%2C+Quoc-Truong%22">Truong, Quoc-Truong</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Nguyen%2C+Vinh-Tiep%22">Nguyen, Vinh-Tiep</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> tiepnv@uit.edu.vn</i><br /><searchLink fieldCode="AR" term="%22Nguyen%2C+Lan-Phuong%22">Nguyen, Lan-Phuong</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Cao%2C+Hung-Phu%22">Cao, Hung-Phu</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Luu%2C+Duc-Tuan%22">Luu, Duc-Tuan</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Neural+Computing+%26+Applications%22">Neural Computing & Applications</searchLink>. Dec2024, Vol. 36 Issue 34, p21859-21871. 13p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Lips%22">Lips</searchLink><br /><searchLink fieldCode="DE" term="%22Hair%22">Hair</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Prompt-based portrait image style transfer aims at translating an input content image to a desired style described by text without a style image. In many practical situations, users may not only attend to the entire portrait image but also the local parts (e.g., eyes, lips, and hair). To address such applications, we propose a new framework that enables style transfer on specific regions described by a text description of the desired style. Specifically, we incorporate semantic segmentation to identify the intended area without requiring edit masks from the user while utilizing a pre-trained CLIP-based model for stylizing. Besides, we propose a text-to-patch matching loss by randomly dividing the stylized image into smaller patches to ensure the consistent quality of the result. To comprehensively evaluate the proposed method, we use several metrics, such as FID, SSIM, and PSNR on a dataset consisting of portraits from the CelebAMask-HQ dataset and style descriptions of other related works. Extensive experimental results demonstrate that our framework outperforms other state-of-the-art methods in terms of both stylization quality and inference time. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Neural Computing & Applications is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=181069363
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1007/s00521-024-10394-w
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 13
        StartPage: 21859
    Subjects:
      – SubjectFull: Lips
        Type: general
      – SubjectFull: Hair
        Type: general
    Titles:
      – TitleFull: Local part attention for image stylization with text prompt.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Truong, Quoc-Truong
      – PersonEntity:
          Name:
            NameFull: Nguyen, Vinh-Tiep
      – PersonEntity:
          Name:
            NameFull: Nguyen, Lan-Phuong
      – PersonEntity:
          Name:
            NameFull: Cao, Hung-Phu
      – PersonEntity:
          Name:
            NameFull: Luu, Duc-Tuan
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 12
              Text: Dec2024
              Type: published
              Y: 2024
          Identifiers:
            – Type: issn-print
              Value: 09410643
          Numbering:
            – Type: volume
              Value: 36
            – Type: issue
              Value: 34
          Titles:
            – TitleFull: Neural Computing & Applications
              Type: main
ResultId 1