Antipodally Invariant Metrics For Fast Regression-Based Super-Resolution
Eduardo Pérez-Pellitero (Leibniz Universität Hannover, Technicolor)
Jordi Salvador (Technicolor)
Javier Ruiz-Hidalgo (Universitat Politècnica de Catalunya)
Bodo Rosenhahn (Leibniz Universität Hannover)
IEEE Transactions on Image Processing, 2016 (accepted)
Here you can access the pre-print version of the paper. UPDATE. Now you can find more resources about this project in Eduardo's site!
Abstract
Dictionary-based Super-Resolution algorithms usually select dictionary atoms based on distance or similarity metrics. Although the optimal selection of nearest neighbors is of central importance for such methods, the impact of using proper metrics for Super-Resolution (SR) has been overlooked in the literature, mainly due to the vast usage of Euclidean distance. In this paper we present a very fast regression-based algorithm which builds on densely populated anchored neighborhoods and sublinear search structures. We perform a study of the nature of the features commonly used for SR, observing that those features usually lie in the unitary hypersphere, where every point has a diametrically opposite one, i.e. its antipode, with same module and angle, but opposite direction. Even though we validate the benefits of using antipodally invariant metrics, most of the binary splits use Euclidean distance, which does not handle antipodes optimally. In order to benefit from both worlds, we propose a simple yet effective Antipodally Invariant Transform (AIT) that can be easily included in the Euclidean distance calculation.
We modify the original Spherical Hashing algorithm with this metric in our Antipodally Invariant Spherical Hashing scheme, obtaining the same performance as a pure antipodally invariant metric. We round up our contributions with a novel feature transform that obtains a better coarse approximation of the input
image thanks to Iterative Back Projection. Our method, which we name Antipodally Invariant Super-Resolution (AIS), improves quality (PSNR) and is faster than most state-of-the-art alternatives.
BibTeX
@article{PerezPellitero2016b,author = {P\'erez-Pellitero, E. and Salvador, J. and Ruiz-Hidalgo, J. and Rosenhahn, B.},
title = {{Antipodally Invariant Metrics For Fast Regression-Based Super-Resolution}},
journal = {{IEEE} Trans. on Image Processing},
volume = {volume},
number = {number},
pages = {first-last},
year = {2016},
doi = {address},
}
