Balanced distortion and perception in single-image super-resolution based on optimal transport in wavelet domain.
Saved in:
| Title: | Balanced distortion and perception in single-image super-resolution based on optimal transport in wavelet domain. |
|---|---|
| Authors: | Xiao, Jun1 (AUTHOR), Liu, Tianshan1 (AUTHOR), Zhao, Rui1 (AUTHOR), Lam, Kin-Man1,2 (AUTHOR) enkmlam@polyu.edu.hk |
| Source: | Neurocomputing. Nov2021, Vol. 464, p408-420. 13p. |
| Subjects: | High resolution imaging, Perceptual illusions, Computer vision, Transport theory, Wavelets (Mathematics), Interpolation algorithms, Image fusion, Running speed |
| Abstract: | Single image super-resolution (SISR) is a classic ill-posed problem in computer vision. In recent years, deep-learning-based (DL-based) models have achieved promising results with the SISR problem. However, most existing methods suffer from an intrinsic trade-off between distortion and perceptual quality. To satisfy the requirements in different real-world situations, the balance of distortion and visual quality for image super-resolution is a critical issue. In DL-based models, the uses of hybrid loss (i.e., the combination of the distortion loss and the perceptual loss) and network interpolation are two common approaches to balancing the distortion and perceptual quality of super-resolved images. However, these two kinds of methods lack flexibility and hold strict constraints on network architectures. In this paper, we propose an image-fusion interpolation method for image super-resolution, which can balance the distortion and visual quality of super-resolved images, based on the optimal transport theory in the wavelet domain. The advantage of our proposed method is that it can be applied to any pretrained DL-based model, without any requirement from the network architecture and parameters. In addition, our proposed method is parameter-free and can run fast without using a GPU. Compared with existing state-of-the-art SISR methods, experiment results show that our proposed method can achieve a better balance between the distortion and visual quality in super-resolved images. [ABSTRACT FROM AUTHOR] |
| Copyright of Neurocomputing is the property of Elsevier B.V. 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: 152899974 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Balanced distortion and perception in single-image super-resolution based on optimal transport in wavelet domain. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Xiao%2C+Jun%22">Xiao, Jun</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Liu%2C+Tianshan%22">Liu, Tianshan</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Zhao%2C+Rui%22">Zhao, Rui</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Lam%2C+Kin-Man%22">Lam, Kin-Man</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> enkmlam@polyu.edu.hk</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Neurocomputing%22">Neurocomputing</searchLink>. Nov2021, Vol. 464, p408-420. 13p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22High+resolution+imaging%22">High resolution imaging</searchLink><br /><searchLink fieldCode="DE" term="%22Perceptual+illusions%22">Perceptual illusions</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+vision%22">Computer vision</searchLink><br /><searchLink fieldCode="DE" term="%22Transport+theory%22">Transport theory</searchLink><br /><searchLink fieldCode="DE" term="%22Wavelets+%28Mathematics%29%22">Wavelets (Mathematics)</searchLink><br /><searchLink fieldCode="DE" term="%22Interpolation+algorithms%22">Interpolation algorithms</searchLink><br /><searchLink fieldCode="DE" term="%22Image+fusion%22">Image fusion</searchLink><br /><searchLink fieldCode="DE" term="%22Running+speed%22">Running speed</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Single image super-resolution (SISR) is a classic ill-posed problem in computer vision. In recent years, deep-learning-based (DL-based) models have achieved promising results with the SISR problem. However, most existing methods suffer from an intrinsic trade-off between distortion and perceptual quality. To satisfy the requirements in different real-world situations, the balance of distortion and visual quality for image super-resolution is a critical issue. In DL-based models, the uses of hybrid loss (i.e., the combination of the distortion loss and the perceptual loss) and network interpolation are two common approaches to balancing the distortion and perceptual quality of super-resolved images. However, these two kinds of methods lack flexibility and hold strict constraints on network architectures. In this paper, we propose an image-fusion interpolation method for image super-resolution, which can balance the distortion and visual quality of super-resolved images, based on the optimal transport theory in the wavelet domain. The advantage of our proposed method is that it can be applied to any pretrained DL-based model, without any requirement from the network architecture and parameters. In addition, our proposed method is parameter-free and can run fast without using a GPU. Compared with existing state-of-the-art SISR methods, experiment results show that our proposed method can achieve a better balance between the distortion and visual quality in super-resolved images. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Neurocomputing is the property of Elsevier B.V. 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=152899974 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1016/j.neucom.2021.08.073 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 13 StartPage: 408 Subjects: – SubjectFull: High resolution imaging Type: general – SubjectFull: Perceptual illusions Type: general – SubjectFull: Computer vision Type: general – SubjectFull: Transport theory Type: general – SubjectFull: Wavelets (Mathematics) Type: general – SubjectFull: Interpolation algorithms Type: general – SubjectFull: Image fusion Type: general – SubjectFull: Running speed Type: general Titles: – TitleFull: Balanced distortion and perception in single-image super-resolution based on optimal transport in wavelet domain. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Xiao, Jun – PersonEntity: Name: NameFull: Liu, Tianshan – PersonEntity: Name: NameFull: Zhao, Rui – PersonEntity: Name: NameFull: Lam, Kin-Man IsPartOfRelationships: – BibEntity: Dates: – D: 13 M: 11 Text: Nov2021 Type: published Y: 2021 Identifiers: – Type: issn-print Value: 09252312 Numbering: – Type: volume Value: 464 Titles: – TitleFull: Neurocomputing Type: main |
| ResultId | 1 |
