HDR-CNF: single-image high dynamic range imaging based on conditional normalizing flows.
Saved in:
| Title: | HDR-CNF: single-image high dynamic range imaging based on conditional normalizing flows. |
|---|---|
| Authors: | Peng, Kai-Wei1 (AUTHOR), Chiang, Jui-Chiu2,3 (AUTHOR) rachel@ccu.edu.tw, Chen, Sau-Gee1 (AUTHOR), Lin, Yu-Shan2 (AUTHOR) |
| Source: | Multimedia Tools & Applications. Jul2025, Vol. 84 Issue 25, p29491-29511. 21p. |
| Subjects: | High dynamic range imaging, Image reconstruction, Image quality analysis, Feature extraction, Image processing, Loss functions (Statistics) |
| Abstract: | In this paper, we present HDR-CNF, a novel method for reconstructing high dynamic range (HDR) images from single low dynamic range (LDR) images using conditional normalizing flows. Our approach takes advantage of the invertibility provided by normalizing flows and leverages the stability of negative log-likelihood loss to efficiently transform the conditional distribution of HDR images given LDR images into a Gaussian distribution. During inference, we successfully generate an HDR image by sampling from the Gaussian distribution along with the corresponding LDR image. To conditionally input the LDR image, we employ a feature extraction network to extract rich features, enhancing the network's ability to generate high-quality HDR images. Furthermore, we introduce a cycle consistency loss to ensure that the generated HDR images closely resemble the authentic HDR images. Comparative evaluations demonstrate the superiority of our method over existing HDR imaging techniques. Our approach excels in reconstructing well-exposed LDR images into satisfactory HDR images and enhances slightly under-exposed or over-exposed LDR images, outperforming other methods in terms of image quality. In addition to performance evaluations, we conduct a comprehensive analysis of the complexity of our network architecture. Our results showcase impressive performance across various evaluation metrics, providing compelling evidence of the effectiveness of HDR-CNF in HDR image reconstruction. [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.) | |
| 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: 186986648 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: HDR-CNF: single-image high dynamic range imaging based on conditional normalizing flows. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Peng%2C+Kai-Wei%22">Peng, Kai-Wei</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Chiang%2C+Jui-Chiu%22">Chiang, Jui-Chiu</searchLink><relatesTo>2,3</relatesTo> (AUTHOR)<i> rachel@ccu.edu.tw</i><br /><searchLink fieldCode="AR" term="%22Chen%2C+Sau-Gee%22">Chen, Sau-Gee</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Lin%2C+Yu-Shan%22">Lin, Yu-Shan</searchLink><relatesTo>2</relatesTo> (AUTHOR) – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Multimedia+Tools+%26+Applications%22">Multimedia Tools & Applications</searchLink>. Jul2025, Vol. 84 Issue 25, p29491-29511. 21p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22High+dynamic+range+imaging%22">High dynamic range imaging</searchLink><br /><searchLink fieldCode="DE" term="%22Image+reconstruction%22">Image reconstruction</searchLink><br /><searchLink fieldCode="DE" term="%22Image+quality+analysis%22">Image quality analysis</searchLink><br /><searchLink fieldCode="DE" term="%22Feature+extraction%22">Feature extraction</searchLink><br /><searchLink fieldCode="DE" term="%22Image+processing%22">Image processing</searchLink><br /><searchLink fieldCode="DE" term="%22Loss+functions+%28Statistics%29%22">Loss functions (Statistics)</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: In this paper, we present HDR-CNF, a novel method for reconstructing high dynamic range (HDR) images from single low dynamic range (LDR) images using conditional normalizing flows. Our approach takes advantage of the invertibility provided by normalizing flows and leverages the stability of negative log-likelihood loss to efficiently transform the conditional distribution of HDR images given LDR images into a Gaussian distribution. During inference, we successfully generate an HDR image by sampling from the Gaussian distribution along with the corresponding LDR image. To conditionally input the LDR image, we employ a feature extraction network to extract rich features, enhancing the network's ability to generate high-quality HDR images. Furthermore, we introduce a cycle consistency loss to ensure that the generated HDR images closely resemble the authentic HDR images. Comparative evaluations demonstrate the superiority of our method over existing HDR imaging techniques. Our approach excels in reconstructing well-exposed LDR images into satisfactory HDR images and enhances slightly under-exposed or over-exposed LDR images, outperforming other methods in terms of image quality. In addition to performance evaluations, we conduct a comprehensive analysis of the complexity of our network architecture. Our results showcase impressive performance across various evaluation metrics, providing compelling evidence of the effectiveness of HDR-CNF in HDR image reconstruction. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright 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=egs&AN=186986648 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1007/s11042-024-20237-4 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 21 StartPage: 29491 Subjects: – SubjectFull: High dynamic range imaging Type: general – SubjectFull: Image reconstruction Type: general – SubjectFull: Image quality analysis Type: general – SubjectFull: Feature extraction Type: general – SubjectFull: Image processing Type: general – SubjectFull: Loss functions (Statistics) Type: general Titles: – TitleFull: HDR-CNF: single-image high dynamic range imaging based on conditional normalizing flows. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Peng, Kai-Wei – PersonEntity: Name: NameFull: Chiang, Jui-Chiu – PersonEntity: Name: NameFull: Chen, Sau-Gee – PersonEntity: Name: NameFull: Lin, Yu-Shan IsPartOfRelationships: – BibEntity: Dates: – D: 25 M: 07 Text: Jul2025 Type: published Y: 2025 Identifiers: – Type: issn-print Value: 13807501 Numbering: – Type: volume Value: 84 – Type: issue Value: 25 Titles: – TitleFull: Multimedia Tools & Applications Type: main |
| ResultId | 1 |
