View in EDS PDF Full Text

HFDDLap: High-Low Frequency Differentiation Dynamic Laplacian Pyramid Network for Image Super-Resolution.

Saved in:
Bibliographic Details
Title: HFDDLap: High-Low Frequency Differentiation Dynamic Laplacian Pyramid Network for Image Super-Resolution.
Authors: LIU, Peituan1 liupeituan@163.com, LI, Tie1 tielitg@163.com, LI, Rui1 lr_1696@126.com, SONG, Bo1 1452254876@qq.com
Source: Technical Gazette / Tehnički Vjesnik. 2026, Vol. 33 Issue 1, p391-404. 14p.
Subjects: Convolutional neural networks, Deconvolution (Mathematics), High resolution imaging, Image processing
Abstract: Existing single image super-resolution (SR) algorithms based on convolution neural networks (CNNs) have achieved usable visual results. However, they often encounter artifacts and blurring, particularly at large scaling factors (e.g., 4×, 8×), due to significant loss of high-frequency information. To address these challenges, we propose a novel high-low frequency differentiation dynamic Laplacian pyramid network (HFDDLap). Our approach introduces a learnable high-low frequency differentiation convolution (HLC) within high-low frequency differentiation residual channel attention blocks (HL-RCAB) to effectively capture and differentiate high- and low-frequency components, enhancing detail preservation. Additionally, we employ a dynamic deconvolution (DDC) that adaptively generates upsampling kernels based on input features, improving reconstruction accuracy by reducing feature distortion. Extensive experiments on 4× and 8× SR demonstrate that our proposed method effectively reconstructs edge details, produces satisfactory SR results and outperforms some state-of-the-art (SOTA) methods in terms of evaluation metrics. [ABSTRACT FROM AUTHOR]
Copyright of Technical Gazette / Tehnički Vjesnik is the property of Tehnicki Vjesnik 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 Links:
  – Type: pdflink
Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 190969719
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: HFDDLap: High-Low Frequency Differentiation Dynamic Laplacian Pyramid Network for Image Super-Resolution.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22LIU%2C+Peituan%22">LIU, Peituan</searchLink><relatesTo>1</relatesTo><i> liupeituan@163.com</i><br /><searchLink fieldCode="AR" term="%22LI%2C+Tie%22">LI, Tie</searchLink><relatesTo>1</relatesTo><i> tielitg@163.com</i><br /><searchLink fieldCode="AR" term="%22LI%2C+Rui%22">LI, Rui</searchLink><relatesTo>1</relatesTo><i> lr_1696@126.com</i><br /><searchLink fieldCode="AR" term="%22SONG%2C+Bo%22">SONG, Bo</searchLink><relatesTo>1</relatesTo><i> 1452254876@qq.com</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Technical+Gazette+%2F+Tehnički+Vjesnik%22">Technical Gazette / Tehnički Vjesnik</searchLink>. 2026, Vol. 33 Issue 1, p391-404. 14p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Convolutional+neural+networks%22">Convolutional neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Deconvolution+%28Mathematics%29%22">Deconvolution (Mathematics)</searchLink><br /><searchLink fieldCode="DE" term="%22High+resolution+imaging%22">High resolution imaging</searchLink><br /><searchLink fieldCode="DE" term="%22Image+processing%22">Image processing</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: Existing single image super-resolution (SR) algorithms based on convolution neural networks (CNNs) have achieved usable visual results. However, they often encounter artifacts and blurring, particularly at large scaling factors (e.g., 4×, 8×), due to significant loss of high-frequency information. To address these challenges, we propose a novel high-low frequency differentiation dynamic Laplacian pyramid network (HFDDLap). Our approach introduces a learnable high-low frequency differentiation convolution (HLC) within high-low frequency differentiation residual channel attention blocks (HL-RCAB) to effectively capture and differentiate high- and low-frequency components, enhancing detail preservation. Additionally, we employ a dynamic deconvolution (DDC) that adaptively generates upsampling kernels based on input features, improving reconstruction accuracy by reducing feature distortion. Extensive experiments on 4× and 8× SR demonstrate that our proposed method effectively reconstructs edge details, produces satisfactory SR results and outperforms some state-of-the-art (SOTA) methods in terms of evaluation metrics. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Technical Gazette / Tehnički Vjesnik is the property of Tehnicki Vjesnik 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=190969719
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.17559/TV-20250204002330
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 14
        StartPage: 391
    Subjects:
      – SubjectFull: Convolutional neural networks
        Type: general
      – SubjectFull: Deconvolution (Mathematics)
        Type: general
      – SubjectFull: High resolution imaging
        Type: general
      – SubjectFull: Image processing
        Type: general
    Titles:
      – TitleFull: HFDDLap: High-Low Frequency Differentiation Dynamic Laplacian Pyramid Network for Image Super-Resolution.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: LIU, Peituan
      – PersonEntity:
          Name:
            NameFull: LI, Tie
      – PersonEntity:
          Name:
            NameFull: LI, Rui
      – PersonEntity:
          Name:
            NameFull: SONG, Bo
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Text: 2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 13303651
          Numbering:
            – Type: volume
              Value: 33
            – Type: issue
              Value: 1
          Titles:
            – TitleFull: Technical Gazette / Tehnički Vjesnik
              Type: main
ResultId 1