Details
| Original language | English |
|---|---|
| Title of host publication | Proceedings |
| Subtitle of host publication | 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 |
| Publisher | IEEE Computer Society |
| Pages | 1837-1845 |
| Number of pages | 9 |
| ISBN (electronic) | 9781467388504 |
| Publication status | Published - 9 Dec 2016 |
| Event | 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016 - Las Vegas, United States Duration: 26 Jun 2016 → 1 Jul 2016 |
Publication series
| Name | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition |
|---|---|
| Volume | 2016-December |
| ISSN (Print) | 1063-6919 |
Abstract
The main challenge in Super Resolution (SR) is to discover the mapping between the low-and high-resolution manifolds of image patches, a complex ill-posed problem which has recently been addressed through piecewise linear regression with promising results. In this paper we present a novel regression-based SR algorithm that benefits from an extended knowledge of the structure of both manifolds. We propose a transform that collapses the 16 variations induced from the dihedral group of transforms (i.e. rotations, vertical and horizontal reflections) and antipodality (i.e. diametrically opposed points in the unitary sphere) into a single primitive. The key idea of our transform is to study the different dihedral elements as a group of symmetries within the high-dimensional manifold. We obtain the respective set of mirror-symmetry axes by means of a frequency analysis of the dihedral elements, and we use them to collapse the redundant variability through a modified symmetry distance. The experimental validation of our algorithm shows the effectiveness of our approach, which obtains competitive quality with a dictionary of as little as 32 atoms (reducing other methods' dictionaries by at least a factor of 32) and further pushing the state-of-the-art with a 1024 atoms dictionary.
ASJC Scopus subject areas
- Computer Science(all)
- Software
- Computer Science(all)
- Computer Vision and Pattern Recognition
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
Proceedings: 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016. IEEE Computer Society, 2016. p. 1837-1845 7780572 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 2016-December).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - PSyCo
T2 - 29th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016
AU - Perez-Pellitero, Eduardo
AU - Salvador, Jordi
AU - Ruiz-Hidalgo, Javier
AU - Rosenhahn, Bodo
PY - 2016/12/9
Y1 - 2016/12/9
N2 - The main challenge in Super Resolution (SR) is to discover the mapping between the low-and high-resolution manifolds of image patches, a complex ill-posed problem which has recently been addressed through piecewise linear regression with promising results. In this paper we present a novel regression-based SR algorithm that benefits from an extended knowledge of the structure of both manifolds. We propose a transform that collapses the 16 variations induced from the dihedral group of transforms (i.e. rotations, vertical and horizontal reflections) and antipodality (i.e. diametrically opposed points in the unitary sphere) into a single primitive. The key idea of our transform is to study the different dihedral elements as a group of symmetries within the high-dimensional manifold. We obtain the respective set of mirror-symmetry axes by means of a frequency analysis of the dihedral elements, and we use them to collapse the redundant variability through a modified symmetry distance. The experimental validation of our algorithm shows the effectiveness of our approach, which obtains competitive quality with a dictionary of as little as 32 atoms (reducing other methods' dictionaries by at least a factor of 32) and further pushing the state-of-the-art with a 1024 atoms dictionary.
AB - The main challenge in Super Resolution (SR) is to discover the mapping between the low-and high-resolution manifolds of image patches, a complex ill-posed problem which has recently been addressed through piecewise linear regression with promising results. In this paper we present a novel regression-based SR algorithm that benefits from an extended knowledge of the structure of both manifolds. We propose a transform that collapses the 16 variations induced from the dihedral group of transforms (i.e. rotations, vertical and horizontal reflections) and antipodality (i.e. diametrically opposed points in the unitary sphere) into a single primitive. The key idea of our transform is to study the different dihedral elements as a group of symmetries within the high-dimensional manifold. We obtain the respective set of mirror-symmetry axes by means of a frequency analysis of the dihedral elements, and we use them to collapse the redundant variability through a modified symmetry distance. The experimental validation of our algorithm shows the effectiveness of our approach, which obtains competitive quality with a dictionary of as little as 32 atoms (reducing other methods' dictionaries by at least a factor of 32) and further pushing the state-of-the-art with a 1024 atoms dictionary.
UR - http://www.scopus.com/inward/record.url?scp=84986292291&partnerID=8YFLogxK
U2 - 10.1109/cvpr.2016.203
DO - 10.1109/cvpr.2016.203
M3 - Conference contribution
AN - SCOPUS:84986292291
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 1837
EP - 1845
BT - Proceedings
PB - IEEE Computer Society
Y2 - 26 June 2016 through 1 July 2016
ER -