A super-resolution framework for high-accuracy multiview reconstruction
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,...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article (Journal) |
| Language: | English |
| Published: |
2014
|
| In: |
International journal of computer vision
Year: 2013, Volume: 106, Issue: 2, Pages: 172-191 |
| ISSN: | 1573-1405 |
| DOI: | 10.1007/s11263-013-0654-8 |
| Online Access: | Resolving-System, lizenzpflichtig, Volltext: https://doi.org/10.1007/s11263-013-0654-8 Verlag, lizenzpflichtig, Volltext: https://link.springer.com/article/10.1007%2Fs11263-013-0654-8 
|
| Author Notes: | Bastian Goldlücke, Mathieu Aubry, Kalin Kolev, Daniel Cremers |
| Summary: | 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. |
|---|---|
| Item Description: | Published online: 25 August 2013 Gesehen am 06.10.2020 |
| Physical Description: | Online Resource |
| ISSN: | 1573-1405 |
| DOI: | 10.1007/s11263-013-0654-8 |