Self‐Calibrating Fisheye Lens Aberrations for Novel View Synthesis.
Saved in:
| Title: | Self‐Calibrating Fisheye Lens Aberrations for Novel View Synthesis. |
|---|---|
| Authors: | Xiang, Jinhui1 (AUTHOR) 2211100285@nbu.edu.cn, Li, Yuqi1 (AUTHOR) liyuqi1@nbu.edu.cn, Li, Jiabao2 (AUTHOR) jiabaol6@uci.edu, Zheng, Wenxing1 (AUTHOR) 2311100098@nbu.edu.cn, Fu, Qiang3 (AUTHOR) qiang.fu@kaust.edu.sa |
| Source: | Computer Graphics Forum. Sep2025, Vol. 44 Issue 6, p1-14. 14p. |
| Subjects: | Optical aberrations, Three-dimensional imaging, Hemispherical photography, Optimization algorithms, Acquisition of data, Machine learning, Rendering (Computer graphics) |
| Abstract: | Neural rendering techniques, such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3D‐GS), have led to significant advancements in scene reconstruction and novel view synthesis (NVS). These methods assume the use of an ideal pinhole model, which is free from lens distortion and optical aberrations. However, fisheye lenses introduce unavoidable aberrations due to their wide‐angle design and complex manufacturing, leading to multi‐view inconsistencies that compromise scene reconstruction quality. In this paper, we propose an end‐to‐end framework that integrates a standard 3D reconstruction pipeline with our lens aberration model to simultaneously calibrate lens aberrations and reconstruct 3D scenes. By modelling the real imaging process and jointly optimising both tasks, our framework eliminates the impact of aberration‐induced inconsistencies on reconstruction. Additionally, we propose a curriculum learning approach that ensures stable optimisation and high‐quality reconstruction results, even in the presence of multiple aberrations. To address the limitations of existing benchmarks, we introduce AbeRec, a dataset composed of scenes captured with lenses exhibiting severe aberrations. Extensive experiments on both existing public datasets and our proposed dataset demonstrate that our method not only significantly outperforms previous state‐of‐the‐art methods on fisheye lenses with severe aberrations but also generalises well to scenes captured by non‐fisheye lenses. Code and datasets are available at https://github.com/CPREgroup/Calibrating‐Fisheye‐Lens‐Aberration‐for‐NVS. [ABSTRACT FROM AUTHOR] |
| Copyright of Computer Graphics Forum is the property of Wiley-Blackwell 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: 188175304 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Self‐Calibrating Fisheye Lens Aberrations for Novel View Synthesis. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Xiang%2C+Jinhui%22">Xiang, Jinhui</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> 2211100285@nbu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Li%2C+Yuqi%22">Li, Yuqi</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> liyuqi1@nbu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Li%2C+Jiabao%22">Li, Jiabao</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> jiabaol6@uci.edu</i><br /><searchLink fieldCode="AR" term="%22Zheng%2C+Wenxing%22">Zheng, Wenxing</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> 2311100098@nbu.edu.cn</i><br /><searchLink fieldCode="AR" term="%22Fu%2C+Qiang%22">Fu, Qiang</searchLink><relatesTo>3</relatesTo> (AUTHOR)<i> qiang.fu@kaust.edu.sa</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Computer+Graphics+Forum%22">Computer Graphics Forum</searchLink>. Sep2025, Vol. 44 Issue 6, p1-14. 14p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Optical+aberrations%22">Optical aberrations</searchLink><br /><searchLink fieldCode="DE" term="%22Three-dimensional+imaging%22">Three-dimensional imaging</searchLink><br /><searchLink fieldCode="DE" term="%22Hemispherical+photography%22">Hemispherical photography</searchLink><br /><searchLink fieldCode="DE" term="%22Optimization+algorithms%22">Optimization algorithms</searchLink><br /><searchLink fieldCode="DE" term="%22Acquisition+of+data%22">Acquisition of data</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Rendering+%28Computer+graphics%29%22">Rendering (Computer graphics)</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Neural rendering techniques, such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3D‐GS), have led to significant advancements in scene reconstruction and novel view synthesis (NVS). These methods assume the use of an ideal pinhole model, which is free from lens distortion and optical aberrations. However, fisheye lenses introduce unavoidable aberrations due to their wide‐angle design and complex manufacturing, leading to multi‐view inconsistencies that compromise scene reconstruction quality. In this paper, we propose an end‐to‐end framework that integrates a standard 3D reconstruction pipeline with our lens aberration model to simultaneously calibrate lens aberrations and reconstruct 3D scenes. By modelling the real imaging process and jointly optimising both tasks, our framework eliminates the impact of aberration‐induced inconsistencies on reconstruction. Additionally, we propose a curriculum learning approach that ensures stable optimisation and high‐quality reconstruction results, even in the presence of multiple aberrations. To address the limitations of existing benchmarks, we introduce AbeRec, a dataset composed of scenes captured with lenses exhibiting severe aberrations. Extensive experiments on both existing public datasets and our proposed dataset demonstrate that our method not only significantly outperforms previous state‐of‐the‐art methods on fisheye lenses with severe aberrations but also generalises well to scenes captured by non‐fisheye lenses. Code and datasets are available at https://github.com/CPREgroup/Calibrating‐Fisheye‐Lens‐Aberration‐for‐NVS. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Computer Graphics Forum is the property of Wiley-Blackwell 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=188175304 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1111/cgf.70148 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 14 StartPage: 1 Subjects: – SubjectFull: Optical aberrations Type: general – SubjectFull: Three-dimensional imaging Type: general – SubjectFull: Hemispherical photography Type: general – SubjectFull: Optimization algorithms Type: general – SubjectFull: Acquisition of data Type: general – SubjectFull: Machine learning Type: general – SubjectFull: Rendering (Computer graphics) Type: general Titles: – TitleFull: Self‐Calibrating Fisheye Lens Aberrations for Novel View Synthesis. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Xiang, Jinhui – PersonEntity: Name: NameFull: Li, Yuqi – PersonEntity: Name: NameFull: Li, Jiabao – PersonEntity: Name: NameFull: Zheng, Wenxing – PersonEntity: Name: NameFull: Fu, Qiang IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 09 Text: Sep2025 Type: published Y: 2025 Identifiers: – Type: issn-print Value: 01677055 Numbering: – Type: volume Value: 44 – Type: issue Value: 6 Titles: – TitleFull: Computer Graphics Forum Type: main |
| ResultId | 1 |
