View in EDS HTML Full Text PDF Full Text

A deep learning-based neural style transfer optimization approach.

Saved in:
Bibliographic Details
Title: A deep learning-based neural style transfer optimization approach.
Authors: Sethi, Priyanshi1 (AUTHOR), Bhardwaj, Rhythm1 (AUTHOR), Sharma, Nonita1 (AUTHOR), Sharma, Deepak Kumar1 (AUTHOR), Srivastava, Gautam2,3,4 (AUTHOR) srivastavag@brandonu.ca
Source: Intelligent Data Analysis. Mar2025, Vol. 29 Issue 2, p320-331. 12p.
Subjects: Haar function, Artistic style, Wavelet transforms, Mathematical optimization, Image registration
Abstract: Neural style transfer is used as an optimization technique that combines two different images – a content image and a style reference image – to produce an output image that retains the appearance of the content image but has been modified to match the actual style of the style reference image. This is achieved by fine-tuning the output image to match the style reference images and the statistics for both content and style in the content image. These statistics are extracted from the images using a convolutional network. Primitive models such as WCT were improved upon by models such as PhotoWCT, whose spatial and temporal limitations were improved upon by Deep Photo Style Transfer. Eventually, wavelet transforms were introduced to perform photorealistic style transfer. A wavelet-corrected transfer based on whitening and colouring transforms, i.e., WCT2, was proposed that allowed the preservation of core content and eliminated the need for any post-processing steps and constraints. A model called Domain-Aware Universal Style Transfer also came into the picture. It supported both artistic and photorealistic style transfer. This study provides an overview of the neural style transfer technique. The recent advancements and improvements in the field, including the development of multi-scale and adaptive methods and the integration of semantic segmentation, are discussed and elaborated upon. Experiments have been conducted to determine the roles of encoder-decoder architecture and Haar wavelet functions. The optimum levels at which these can be leveraged for effective style transfer are ascertained. The study also highlights the contrast between VGG-16 and VGG-19 structures and analyzes various performance parameters to establish which works more efficiently for particular use cases. On comparing quantitative metrics across Gatys, AdaIN, and WCT, a gradual upgrade was seen across the models, as AdaIN was performing 99.92 percent better than the primitive Gatys model in terms of processing time. Over 1000 iterations, we found that VGG-16 and VGG-19 have comparable style loss metrics, but there is a difference of 73.1 percent in content loss. VGG-19, however, is displaying a better overall performance since it can keep both content and style losses at bay. [ABSTRACT FROM AUTHOR]
Copyright of Intelligent Data Analysis is the property of Sage Publications Inc. 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: 184233779
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: A deep learning-based neural style transfer optimization approach.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Sethi%2C+Priyanshi%22">Sethi, Priyanshi</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Bhardwaj%2C+Rhythm%22">Bhardwaj, Rhythm</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Sharma%2C+Nonita%22">Sharma, Nonita</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Sharma%2C+Deepak+Kumar%22">Sharma, Deepak Kumar</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Srivastava%2C+Gautam%22">Srivastava, Gautam</searchLink><relatesTo>2,3,4</relatesTo> (AUTHOR)<i> srivastavag@brandonu.ca</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Intelligent+Data+Analysis%22">Intelligent Data Analysis</searchLink>. Mar2025, Vol. 29 Issue 2, p320-331. 12p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Haar+function%22">Haar function</searchLink><br /><searchLink fieldCode="DE" term="%22Artistic+style%22">Artistic style</searchLink><br /><searchLink fieldCode="DE" term="%22Wavelet+transforms%22">Wavelet transforms</searchLink><br /><searchLink fieldCode="DE" term="%22Mathematical+optimization%22">Mathematical optimization</searchLink><br /><searchLink fieldCode="DE" term="%22Image+registration%22">Image registration</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Neural style transfer is used as an optimization technique that combines two different images – a content image and a style reference image – to produce an output image that retains the appearance of the content image but has been modified to match the actual style of the style reference image. This is achieved by fine-tuning the output image to match the style reference images and the statistics for both content and style in the content image. These statistics are extracted from the images using a convolutional network. Primitive models such as WCT were improved upon by models such as PhotoWCT, whose spatial and temporal limitations were improved upon by Deep Photo Style Transfer. Eventually, wavelet transforms were introduced to perform photorealistic style transfer. A wavelet-corrected transfer based on whitening and colouring transforms, i.e., WCT2, was proposed that allowed the preservation of core content and eliminated the need for any post-processing steps and constraints. A model called Domain-Aware Universal Style Transfer also came into the picture. It supported both artistic and photorealistic style transfer. This study provides an overview of the neural style transfer technique. The recent advancements and improvements in the field, including the development of multi-scale and adaptive methods and the integration of semantic segmentation, are discussed and elaborated upon. Experiments have been conducted to determine the roles of encoder-decoder architecture and Haar wavelet functions. The optimum levels at which these can be leveraged for effective style transfer are ascertained. The study also highlights the contrast between VGG-16 and VGG-19 structures and analyzes various performance parameters to establish which works more efficiently for particular use cases. On comparing quantitative metrics across Gatys, AdaIN, and WCT, a gradual upgrade was seen across the models, as AdaIN was performing 99.92 percent better than the primitive Gatys model in terms of processing time. Over 1000 iterations, we found that VGG-16 and VGG-19 have comparable style loss metrics, but there is a difference of 73.1 percent in content loss. VGG-19, however, is displaying a better overall performance since it can keep both content and style losses at bay. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Intelligent Data Analysis is the property of Sage Publications Inc. 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=184233779
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3233/IDA-230765
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 12
        StartPage: 320
    Subjects:
      – SubjectFull: Haar function
        Type: general
      – SubjectFull: Artistic style
        Type: general
      – SubjectFull: Wavelet transforms
        Type: general
      – SubjectFull: Mathematical optimization
        Type: general
      – SubjectFull: Image registration
        Type: general
    Titles:
      – TitleFull: A deep learning-based neural style transfer optimization approach.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Sethi, Priyanshi
      – PersonEntity:
          Name:
            NameFull: Bhardwaj, Rhythm
      – PersonEntity:
          Name:
            NameFull: Sharma, Nonita
      – PersonEntity:
          Name:
            NameFull: Sharma, Deepak Kumar
      – PersonEntity:
          Name:
            NameFull: Srivastava, Gautam
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 03
              Text: Mar2025
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-print
              Value: 1088467X
          Numbering:
            – Type: volume
              Value: 29
            – Type: issue
              Value: 2
          Titles:
            – TitleFull: Intelligent Data Analysis
              Type: main
ResultId 1