Variational disentanglement for task-agnostic image restoration.
Saved in:
| Title: | Variational disentanglement for task-agnostic image restoration. |
|---|---|
| Authors: | Idrees, Muhammad1 (AUTHOR) idreeskhan045@gmail.com, Huang, Ying1 (AUTHOR) huangying@cqupt.edu.cn, Li, Ailin1 (AUTHOR) lial@cqupt.edu.cn, Jin, Jiahao1 (AUTHOR) s231201014@stu.cqupt.edu.cn |
| Source: | Visual Computer. Apr2026, Vol. 42 Issue 6, p1-21. 21p. |
| Abstract: | Image restoration tasks, such as shadow removal, deraining, and denoising, traditionally necessitate specialized architectures. This paper introduces a task-agnostic image restoration framework based on variational feature disentanglement, utilizing dual variational autoencoder (VAE) encoders to separate degradation-specific features from content-preserving representations. Our approach, integrating a dual-scale attention mechanism, degrade-aware decoder, and a degrade area localizer, demonstrates competitive performance across shadow removal (AISTD, SRD), deraining (Rain100L), and denoising (BSD68) tasks, achieving computational efficiency (58.39 GFLOPs, 79.64 FPS). Here, we show that our architecture, trained independently per task, effectively disentangles features without task-specific architectural components at inference, offering a scalable solution for diverse restoration scenarios. The source code and pre-trained models are available at . [ABSTRACT FROM AUTHOR] |
| Copyright of Visual Computer 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 |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 193019122 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Variational disentanglement for task-agnostic image restoration. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Idrees%2C+Muhammad%22">Idrees, Muhammad</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> idreeskhan045@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Huang%2C+Ying%22">Huang, Ying</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> huangying@cqupt.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Li%2C+Ailin%22">Li, Ailin</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> lial@cqupt.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Jin%2C+Jiahao%22">Jin, Jiahao</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> s231201014@stu.cqupt.edu.cn</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Visual+Computer%22">Visual Computer</searchLink>. Apr2026, Vol. 42 Issue 6, p1-21. 21p. – Name: Abstract Label: Abstract Group: Ab Data: Image restoration tasks, such as shadow removal, deraining, and denoising, traditionally necessitate specialized architectures. This paper introduces a task-agnostic image restoration framework based on variational feature disentanglement, utilizing dual variational autoencoder (VAE) encoders to separate degradation-specific features from content-preserving representations. Our approach, integrating a dual-scale attention mechanism, degrade-aware decoder, and a degrade area localizer, demonstrates competitive performance across shadow removal (AISTD, SRD), deraining (Rain100L), and denoising (BSD68) tasks, achieving computational efficiency (58.39 GFLOPs, 79.64 FPS). Here, we show that our architecture, trained independently per task, effectively disentangles features without task-specific architectural components at inference, offering a scalable solution for diverse restoration scenarios. The source code and pre-trained models are available at . [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Visual Computer 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=193019122 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1007/s00371-026-04454-6 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 21 StartPage: 1 Titles: – TitleFull: Variational disentanglement for task-agnostic image restoration. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Idrees, Muhammad – PersonEntity: Name: NameFull: Huang, Ying – PersonEntity: Name: NameFull: Li, Ailin – PersonEntity: Name: NameFull: Jin, Jiahao IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 04 Text: Apr2026 Type: published Y: 2026 Identifiers: – Type: issn-print Value: 01782789 Numbering: – Type: volume Value: 42 – Type: issue Value: 6 Titles: – TitleFull: Visual Computer Type: main |
| ResultId | 1 |
