Fast Super-Resolution via Dense Local Training and Inverse Regressor Search
Eduardo Pérez-Pellitero (Technicolor)
Jordi Salvador (Technicolor)
Iban Torres (Technicolor)
Javier Ruiz-Hidalgo (Universitat Politècnica de Catalunya)
Bodo Rosenhahn (Leibniz Universität Hannover)
Proceedings of the Asian Conference on Computer Vision, 2014
The supplementary material can be accessed from here and the conference poster from here.
Abstract
Regression-based Super-Resolution (SR) addresses the upscaling problem
by learning a mapping function (i.e. regressor) from the low-resolution
to the high-resolution manifold. Under the locally linear assumption,
this complex non-linear mapping can be properly modeled by a set of
linear regressors distributed across the manifold. In such methods,
most of the testing time is spent searching for the right regressor
within this trained set. In this paper we propose a novel inverse-search
approach for regression-based SR. Instead of performing a search from
the image to the dictionary of regressors, the search is done inversely
from the regressors dictionary to the image patches. We approximate
this framework by applying spherical hashing to both image and regressors,
which reduces the inverse search into computing a trained function,
whose complexity is close to O(1). Additionally, we propose an
improved training scheme for SR linear regressors which improves perceived
and objective quality. By merging both contributions we improve both
speed and quality compared to the state-of-the-art.
BibTeX
@inproceedings { PerezPellitero2014,
author = {P\'erez-Pellitero, E. and Salvador, J. and Torres, I. and Ruiz-Hidalgo, J, and Rosenhahn, B.},
title = {{Fast Super-Resolution via Dense Local Training and Inverse Regressor Search}},
booktitle = {Proc. Asian Conf. on Computer Vision},
pages = {first--last},
year = {2014},
}
