Academic Journal
Weighted least square filter via deep unsupervised learning.
| Τίτλος: | Weighted least square filter via deep unsupervised learning. |
|---|---|
| Συγγραφείς: | Yang, Yang, Wu, Dan, Zeng, Lanling, Li, Zhuoran |
| Πηγή: | Multimedia Tools & Applications; Mar2024, Vol. 83 Issue 11, p31361-31377, 17p |
| Περίληψη: | The weighted least square (WLS) filter is a popular edge-preserving image smoother that is particularly useful for detail enhancing and HDR tone mapping. However, it suffers from limited edge-preserving capability and high computational cost. Existing deep learning-based filters under the WLS framework are mostly based on supervised learning. They improve the efficiency but not the quality. In this paper, we propose a novel edge-preserving filter under the weighted least square framework based on deep unsupervised learning. According to the spatial-varying smoothing property of the edge-preserving filter, we propose a lightweight fully convolution neural network based on dilated convolutions with varying expanding factors. The proposed filter fully makes use of the 2D neighborhood information, thus it is able to suppress various artifacts. Thanks to the highly optimized framework for deep learning, the proposed filter is highly efficient, enabling the processing of 720P images at interactive rates (≈ 12 fps) on a modern desktop. Experimental results indicate that the proposed filter achieves the state-of-the-art smoothing quality. Therefore, our filter benefits a variety of tasks in the field of image processing and computer graphics. [ABSTRACT FROM AUTHOR] |
| Copyright of Multimedia Tools & Applications 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.) | |
| Βάση Δεδομένων: | Complementary Index |
| FullText | Links: – Type: other Text: Availability: 0 CustomLinks: – Url: https://dx.doi.org/doi:10.1007/s11042-023-16844-2 Name: EDS - Springer Nature Journals (s7799221) Category: fullText Text: View record at Springer |
|---|---|
| Header | DbId: edb DbLabel: Complementary Index An: 175934236 RelevancyScore: 950 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 949.951782226563 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Weighted least square filter via deep unsupervised learning. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Yang%2C+Yang%22">Yang, Yang</searchLink><br /><searchLink fieldCode="AR" term="%22Wu%2C+Dan%22">Wu, Dan</searchLink><br /><searchLink fieldCode="AR" term="%22Zeng%2C+Lanling%22">Zeng, Lanling</searchLink><br /><searchLink fieldCode="AR" term="%22Li%2C+Zhuoran%22">Li, Zhuoran</searchLink> – Name: TitleSource Label: Source Group: Src Data: Multimedia Tools & Applications; Mar2024, Vol. 83 Issue 11, p31361-31377, 17p – Name: Abstract Label: Abstract Group: Ab Data: The weighted least square (WLS) filter is a popular edge-preserving image smoother that is particularly useful for detail enhancing and HDR tone mapping. However, it suffers from limited edge-preserving capability and high computational cost. Existing deep learning-based filters under the WLS framework are mostly based on supervised learning. They improve the efficiency but not the quality. In this paper, we propose a novel edge-preserving filter under the weighted least square framework based on deep unsupervised learning. According to the spatial-varying smoothing property of the edge-preserving filter, we propose a lightweight fully convolution neural network based on dilated convolutions with varying expanding factors. The proposed filter fully makes use of the 2D neighborhood information, thus it is able to suppress various artifacts. Thanks to the highly optimized framework for deep learning, the proposed filter is highly efficient, enabling the processing of 720P images at interactive rates (≈ 12 fps) on a modern desktop. Experimental results indicate that the proposed filter achieves the state-of-the-art smoothing quality. Therefore, our filter benefits a variety of tasks in the field of image processing and computer graphics. [ABSTRACT FROM AUTHOR] – Name: Abstract Label: Group: Ab Data: <i>Copyright of Multimedia Tools & Applications 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=edb&AN=175934236 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1007/s11042-023-16844-2 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 17 StartPage: 31361 Titles: – TitleFull: Weighted least square filter via deep unsupervised learning. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Yang, Yang – PersonEntity: Name: NameFull: Wu, Dan – PersonEntity: Name: NameFull: Zeng, Lanling – PersonEntity: Name: NameFull: Li, Zhuoran IsPartOfRelationships: – BibEntity: Dates: – D: 28 M: 03 Text: Mar2024 Type: published Y: 2024 Identifiers: – Type: issn-print Value: 13807501 Numbering: – Type: volume Value: 83 – Type: issue Value: 11 Titles: – TitleFull: Multimedia Tools & Applications Type: main |
| ResultId | 1 |