A super-resolution framework for high-accuracy multiview reconstruction
Goldluecke B, Aubry M, Kolev K, Cremers D (2014)
Publication Type: Journal article
Publication year: 2014
Journal
Book Volume: 106
Pages Range: 172-191
Journal Issue: 2
DOI: 10.1007/s11263-013-0654-8
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. © 2013 Springer Science+Business Media New York.
Involved external institutions
Ruprecht-Karls-Universität Heidelberg
Germany (DE)
Technische Universität München (TUM)
Germany (DE)
Eidgenössische Technische Hochschule Zürich (ETHZ) / Swiss Federal Institute of Technology in Zurich
Switzerland (CH)
Germany (DE)
Technische Universität München (TUM)
Germany (DE)
Eidgenössische Technische Hochschule Zürich (ETHZ) / Swiss Federal Institute of Technology in Zurich
Switzerland (CH)
How to cite
APA:
Goldluecke, B., Aubry, M., Kolev, K., & Cremers, D. (2014). A super-resolution framework for high-accuracy multiview reconstruction. International Journal of Computer Vision, 106(2), 172-191. https://dx.doi.org/10.1007/s11263-013-0654-8
MLA:
Goldluecke, Bastian, et al. "A super-resolution framework for high-accuracy multiview reconstruction." International Journal of Computer Vision 106.2 (2014): 172-191.
BibTeX: Download