A Super-Resolution Framework for High-Accuracy Multiview Reconstruction.
Saved in:
| Title: | A Super-Resolution Framework for High-Accuracy Multiview Reconstruction. |
|---|---|
| Authors: | Goldlücke, Bastian1 bastian.goldluecke@iwr.uni-heidelberg.de, Aubry, Mathieu2 mathieu.aubry@in.tum.de, Kolev, Kalin3 kalin.kolev@inf.ethz.ch, Cremers, Daniel2 cremers@tum.de |
| Source: | International Journal of Computer Vision. Jan2014, Vol. 106 Issue 2, p172-191. 20p. 10 Color Photographs, 5 Diagrams, 3 Charts, 1 Graph. |
| Subjects: | Geometry problems & exercises, Graphic methods, Mathematical optimization, Maps, Three-dimensional imaging |
| Abstract: | We present a variational framework to estimate super-resolved texture maps on a 3D geometry model of a surface from multiple images. Given the calibrated images and the reconstructed geometry, the proposed functional is convex in the super-resolution texture. Using a conformal atlas of the surface, we transform the model from the curved geometry to the flat charts and solve it using state-of-the-art and provably convergent primal-dual algorithms. In order to improve image alignment and quality of the texture, we extend the functional to also optimize for a normal displacement map on the surface as well as the camera calibration parameters. Since the sub-problems for displacement and camera parameters are non-convex, we revert to relaxation schemes in order to robustly estimate a minimizer via sequential convex programming. Experimental results confirm that the proposed super-resolution framework allows to recover textured models with significantly higher level-of-detail than the individual input images. [ABSTRACT FROM AUTHOR] |
| Copyright of International Journal of Computer Vision 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 | Links: – Type: pdflink Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 93646745 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: A Super-Resolution Framework for High-Accuracy Multiview Reconstruction. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Goldlücke%2C+Bastian%22">Goldlücke, Bastian</searchLink><relatesTo>1</relatesTo><i> bastian.goldluecke@iwr.uni-heidelberg.de</i><br /><searchLink fieldCode="AR" term="%22Aubry%2C+Mathieu%22">Aubry, Mathieu</searchLink><relatesTo>2</relatesTo><i> mathieu.aubry@in.tum.de</i><br /><searchLink fieldCode="AR" term="%22Kolev%2C+Kalin%22">Kolev, Kalin</searchLink><relatesTo>3</relatesTo><i> kalin.kolev@inf.ethz.ch</i><br /><searchLink fieldCode="AR" term="%22Cremers%2C+Daniel%22">Cremers, Daniel</searchLink><relatesTo>2</relatesTo><i> cremers@tum.de</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22International+Journal+of+Computer+Vision%22">International Journal of Computer Vision</searchLink>. Jan2014, Vol. 106 Issue 2, p172-191. 20p. 10 Color Photographs, 5 Diagrams, 3 Charts, 1 Graph. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Geometry+problems+%26+exercises%22">Geometry problems & exercises</searchLink><br /><searchLink fieldCode="DE" term="%22Graphic+methods%22">Graphic methods</searchLink><br /><searchLink fieldCode="DE" term="%22Mathematical+optimization%22">Mathematical optimization</searchLink><br /><searchLink fieldCode="DE" term="%22Maps%22">Maps</searchLink><br /><searchLink fieldCode="DE" term="%22Three-dimensional+imaging%22">Three-dimensional imaging</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: We present a variational framework to estimate super-resolved texture maps on a 3D geometry model of a surface from multiple images. Given the calibrated images and the reconstructed geometry, the proposed functional is convex in the super-resolution texture. Using a conformal atlas of the surface, we transform the model from the curved geometry to the flat charts and solve it using state-of-the-art and provably convergent primal-dual algorithms. In order to improve image alignment and quality of the texture, we extend the functional to also optimize for a normal displacement map on the surface as well as the camera calibration parameters. Since the sub-problems for displacement and camera parameters are non-convex, we revert to relaxation schemes in order to robustly estimate a minimizer via sequential convex programming. Experimental results confirm that the proposed super-resolution framework allows to recover textured models with significantly higher level-of-detail than the individual input images. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of International Journal of Computer Vision 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=93646745 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1007/s11263-013-0654-8 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 20 StartPage: 172 Subjects: – SubjectFull: Geometry problems & exercises Type: general – SubjectFull: Graphic methods Type: general – SubjectFull: Mathematical optimization Type: general – SubjectFull: Maps Type: general – SubjectFull: Three-dimensional imaging Type: general Titles: – TitleFull: A Super-Resolution Framework for High-Accuracy Multiview Reconstruction. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Goldlücke, Bastian – PersonEntity: Name: NameFull: Aubry, Mathieu – PersonEntity: Name: NameFull: Kolev, Kalin – PersonEntity: Name: NameFull: Cremers, Daniel IsPartOfRelationships: – BibEntity: Dates: – D: 15 M: 01 Text: Jan2014 Type: published Y: 2014 Identifiers: – Type: issn-print Value: 09205691 Numbering: – Type: volume Value: 106 – Type: issue Value: 2 Titles: – TitleFull: International Journal of Computer Vision Type: main |
| ResultId | 1 |
