View in EDS

Neural Scene Designer: Self-Styled Semantic Image Manipulation.

Saved in:
Bibliographic Details
Title: Neural Scene Designer: Self-Styled Semantic Image Manipulation.
Authors: Lin, Jianman1 linjianmancjx@gmail.com, Chen, Tianshui2 tianshuichen@gmail.com, Qing, Chunmei1 qchm@scut.edu.cn, Yang, Zhijing2 yzhj@gdut.edu.cn, Huang, Shuangping1 eehsp@scut.edu.cn, Ren, Yuheng3 szcyxy@jmu.edu.cn, Lin, Liang4 linliang@ieee.org
Source: IEEE Transactions on Image Processing. 2025, Vol. 34, p6577-6588. 12p.
Subjects: Image processing, Machine learning, Artificial intelligence, Computer vision, Pattern recognition systems
Abstract: Maintaining stylistic consistency is crucial for the cohesion and aesthetic appeal of images, a fundamental requirement in effective image editing and inpainting. However, existing methods primarily focus on the semantic control of generated content, often neglecting the critical task of preserving this consistency. In this work, we introduce the Neural Scene Designer (NSD), a novel framework that enables photo-realistic manipulation of user-specified scene regions while ensuring both semantic alignment with user intent and stylistic consistency with the surrounding environment. NSD leverages an advanced diffusion model, incorporating two parallel cross-attention mechanisms that separately process text and style information to achieve the dual objectives of semantic control and style consistency. To capture fine-grained style representations, we propose the Progressive Self-style Representational Learning (PSRL) module. This module is predicated on the intuitive premise that different regions within a single image share a consistent style, whereas regions from different images exhibit distinct styles. The PSRL module employs a style contrastive loss that encourages high similarity between representations from the same image while enforcing dissimilarity between those from different images. Furthermore, to address the lack of standardized evaluation protocols for this task, we establish a comprehensive benchmark. This benchmark includes competing algorithms, dedicated style-related metrics, and diverse datasets and settings to facilitate fair comparisons. Extensive experiments conducted on our benchmark demonstrate the effectiveness of the proposed framework. [ABSTRACT FROM AUTHOR]
Copyright of IEEE Transactions on Image Processing is the property of IEEE 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
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 191897278
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Neural Scene Designer: Self-Styled Semantic Image Manipulation.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Lin%2C+Jianman%22">Lin, Jianman</searchLink><relatesTo>1</relatesTo><i> linjianmancjx@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Chen%2C+Tianshui%22">Chen, Tianshui</searchLink><relatesTo>2</relatesTo><i> tianshuichen@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Qing%2C+Chunmei%22">Qing, Chunmei</searchLink><relatesTo>1</relatesTo><i> qchm@scut.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Yang%2C+Zhijing%22">Yang, Zhijing</searchLink><relatesTo>2</relatesTo><i> yzhj@gdut.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Huang%2C+Shuangping%22">Huang, Shuangping</searchLink><relatesTo>1</relatesTo><i> eehsp@scut.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Ren%2C+Yuheng%22">Ren, Yuheng</searchLink><relatesTo>3</relatesTo><i> szcyxy@jmu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Lin%2C+Liang%22">Lin, Liang</searchLink><relatesTo>4</relatesTo><i> linliang@ieee.org</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22IEEE+Transactions+on+Image+Processing%22">IEEE Transactions on Image Processing</searchLink>. 2025, Vol. 34, p6577-6588. 12p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Image+processing%22">Image processing</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+intelligence%22">Artificial intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+vision%22">Computer vision</searchLink><br /><searchLink fieldCode="DE" term="%22Pattern+recognition+systems%22">Pattern recognition systems</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Maintaining stylistic consistency is crucial for the cohesion and aesthetic appeal of images, a fundamental requirement in effective image editing and inpainting. However, existing methods primarily focus on the semantic control of generated content, often neglecting the critical task of preserving this consistency. In this work, we introduce the Neural Scene Designer (NSD), a novel framework that enables photo-realistic manipulation of user-specified scene regions while ensuring both semantic alignment with user intent and stylistic consistency with the surrounding environment. NSD leverages an advanced diffusion model, incorporating two parallel cross-attention mechanisms that separately process text and style information to achieve the dual objectives of semantic control and style consistency. To capture fine-grained style representations, we propose the Progressive Self-style Representational Learning (PSRL) module. This module is predicated on the intuitive premise that different regions within a single image share a consistent style, whereas regions from different images exhibit distinct styles. The PSRL module employs a style contrastive loss that encourages high similarity between representations from the same image while enforcing dissimilarity between those from different images. Furthermore, to address the lack of standardized evaluation protocols for this task, we establish a comprehensive benchmark. This benchmark includes competing algorithms, dedicated style-related metrics, and diverse datasets and settings to facilitate fair comparisons. Extensive experiments conducted on our benchmark demonstrate the effectiveness of the proposed framework. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of IEEE Transactions on Image Processing is the property of IEEE 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=191897278
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1109/TIP.2025.3614000
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 12
        StartPage: 6577
    Subjects:
      – SubjectFull: Image processing
        Type: general
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Artificial intelligence
        Type: general
      – SubjectFull: Computer vision
        Type: general
      – SubjectFull: Pattern recognition systems
        Type: general
    Titles:
      – TitleFull: Neural Scene Designer: Self-Styled Semantic Image Manipulation.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Lin, Jianman
      – PersonEntity:
          Name:
            NameFull: Chen, Tianshui
      – PersonEntity:
          Name:
            NameFull: Qing, Chunmei
      – PersonEntity:
          Name:
            NameFull: Yang, Zhijing
      – PersonEntity:
          Name:
            NameFull: Huang, Shuangping
      – PersonEntity:
          Name:
            NameFull: Ren, Yuheng
      – PersonEntity:
          Name:
            NameFull: Lin, Liang
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Text: 2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 10577149
          Numbering:
            – Type: volume
              Value: 34
          Titles:
            – TitleFull: IEEE Transactions on Image Processing
              Type: main
ResultId 1