Introduction - If you have any usage issues, please Google them yourself
In this paper, we propose a novel method for solv-
ing single-image super-resolution problems. Given a
low-resolution image as input, we recover its high-
resolution counterpart using a set of training exam-
ples. While this formulation resembles other learning-
based methods for super-resolution, our method has
been inspired by recent manifold learning methods, par-
ticularly locally linear embedding (LLE). Speci?cally,
small image patches in the low- and high-resolution
images form manifolds with similar local geometry in
two distinct feature spaces. As in LLE, local geometry
is characterized by how a feature vector correspond-
ing to a patch can be reconstructed by its neighbors
in the feature space. Besides using the training image
pairs to estimate the high-resolution embedding, we
also enforce local compatibility and smoothness con-
straints between patches in the target high-resolution
image through overlapping. Experiments show that our
method is very ?exible