Single
image super-resolution (SR) aims at generating a plausible and visually
pleasing high-resolution (HR) image from a low-resolution (LR) input. In this
paper, we propose an effective single image SR algorithm by using collaborative
representation and exploiting non-local self-similarity of natural images. In
particular, the collaborative-representation-based method is
applied to build the so-called self-projection matrices from a training
set of HR images. Then the learned self-projection matrices are
used to establish the collaborative-representation-based regularization
(CRR), which is responsible for introducing the external HR information.
Furthermore, to guarantee a reliable estimation of the HR image, the non- local
low-rank regularization (NLR) which exploits internal prior of images is also
taken into consideration. Since the CRR term and NLR term are complementary,
they are assembled together to form a new reconstruction-based framework for SR
recovery. Finally, to implement the proposed framework, an iterative algorithm is designed to gradually improve the quality of the SR
results. Extensive experimental results indicate that the proposed approach is
capable of delivering higher quality of SR results than several
state-of-the-art SR methods.
Index
Terms—Super-resolution, Collaborative representation, Non-local self-similarity
Regularization.
To facilitate further evaluation and
exploration of the method proposed in the above paper, we publish the source
code at this link.
You are free to use the source code provided
that (1) you clearly cite the source; and (2) you do not make any
redistribution of the code.