FSformer: fusing frequency and spatial domain transformer network for underwater image enhancement: FSformer: fusing frequency and spatial...: D. Liu et al.
Saved in:
| Title: | FSformer: fusing frequency and spatial domain transformer network for underwater image enhancement: FSformer: fusing frequency and spatial...: D. Liu et al. |
|---|---|
| Authors: | Liu, Dalang1 (AUTHOR) 202221090325@std.uestc.edu.cn, Rao, Yunbo1 (AUTHOR) raoyb@uestc.edu.cn, Zhu, Jialong1 (AUTHOR) 202222090634@std.uestc.edu.cn, Ma, Yanjin1 (AUTHOR) 202221090324@std.uestc.edu.cn, Li, Jie2 (AUTHOR) jli@bupt.edu.cn |
| Source: | Multimedia Systems. Jun2025, Vol. 31 Issue 3, p1-11. 11p. |
| Subjects: | Image intensifiers, Artificial intelligence, Image processing, National security, Comparative studies |
| Abstract: | Underwater image enhancement plays a crucial role in safeguarding national security in underwater domains. As the preprocessing step to address challenges such as blurriness and color distortion encountered during underwater imaging, Underwater image enhancement greatly aids in detecting underwater threat targets. However, due to the oversight of utilizing frequency domain information, the existing underwater image enhancement techniques often fail to achieve satisfactory results, leading to subpar reconstruction of degraded images. To tackle these problems, we propose a fusing Frequency and Spatial Domain Transformer network called FSformer for underwater image enhancement. We first devise a novel Frequency-Space Global–Local Transformer block (FSGLT), which not just adaptively integrates information from the frequency and spatial domains, but also enables the model to focus more on severely degraded areas in underwater images. Additionally, a Dual-Branch Feature Enhancement Module (DBFEM) is designed for enhancing extracted deep-level features separately on both the spatial and frequency branches, thereby boosting the ability to restore more details and improve overall image quality in underwater scenarios. On the UIEB dataset, our proposed method achieved PSNR and SSIM values of 24.112 and 0.907 respectively. Through extensive ablation studies and comparative analyses on both synthetic and real-world datasets, we show the effectiveness and superiority of our proposed approach. [ABSTRACT FROM AUTHOR] |
| Copyright of Multimedia Systems 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.
Login for full access.
|
|
| FullText | Links: – Type: pdflink Text: Availability: 1 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 184324949 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: FSformer: fusing frequency and spatial domain transformer network for underwater image enhancement: FSformer: fusing frequency and spatial...: D. Liu et al. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Liu%2C+Dalang%22">Liu, Dalang</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> 202221090325@std.uestc.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Rao%2C+Yunbo%22">Rao, Yunbo</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> raoyb@uestc.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Zhu%2C+Jialong%22">Zhu, Jialong</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> 202222090634@std.uestc.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Ma%2C+Yanjin%22">Ma, Yanjin</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> 202221090324@std.uestc.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Li%2C+Jie%22">Li, Jie</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> jli@bupt.edu.cn</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Multimedia+Systems%22">Multimedia Systems</searchLink>. Jun2025, Vol. 31 Issue 3, p1-11. 11p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Image+intensifiers%22">Image intensifiers</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+intelligence%22">Artificial intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22Image+processing%22">Image processing</searchLink><br /><searchLink fieldCode="DE" term="%22National+security%22">National security</searchLink><br /><searchLink fieldCode="DE" term="%22Comparative+studies%22">Comparative studies</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Underwater image enhancement plays a crucial role in safeguarding national security in underwater domains. As the preprocessing step to address challenges such as blurriness and color distortion encountered during underwater imaging, Underwater image enhancement greatly aids in detecting underwater threat targets. However, due to the oversight of utilizing frequency domain information, the existing underwater image enhancement techniques often fail to achieve satisfactory results, leading to subpar reconstruction of degraded images. To tackle these problems, we propose a fusing Frequency and Spatial Domain Transformer network called FSformer for underwater image enhancement. We first devise a novel Frequency-Space Global–Local Transformer block (FSGLT), which not just adaptively integrates information from the frequency and spatial domains, but also enables the model to focus more on severely degraded areas in underwater images. Additionally, a Dual-Branch Feature Enhancement Module (DBFEM) is designed for enhancing extracted deep-level features separately on both the spatial and frequency branches, thereby boosting the ability to restore more details and improve overall image quality in underwater scenarios. On the UIEB dataset, our proposed method achieved PSNR and SSIM values of 24.112 and 0.907 respectively. Through extensive ablation studies and comparative analyses on both synthetic and real-world datasets, we show the effectiveness and superiority of our proposed approach. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Multimedia Systems 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=184324949 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1007/s00530-025-01753-1 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 11 StartPage: 1 Subjects: – SubjectFull: Image intensifiers Type: general – SubjectFull: Artificial intelligence Type: general – SubjectFull: Image processing Type: general – SubjectFull: National security Type: general – SubjectFull: Comparative studies Type: general Titles: – TitleFull: FSformer: fusing frequency and spatial domain transformer network for underwater image enhancement: FSformer: fusing frequency and spatial...: D. Liu et al. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Liu, Dalang – PersonEntity: Name: NameFull: Rao, Yunbo – PersonEntity: Name: NameFull: Zhu, Jialong – PersonEntity: Name: NameFull: Ma, Yanjin – PersonEntity: Name: NameFull: Li, Jie IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 06 Text: Jun2025 Type: published Y: 2025 Identifiers: – Type: issn-print Value: 09424962 Numbering: – Type: volume Value: 31 – Type: issue Value: 3 Titles: – TitleFull: Multimedia Systems Type: main |
| ResultId | 1 |
