Image Super-Resolution via Dual-Dictionary Learning And Sparse Representation

by   Jian Zhang, et al.

Learning-based image super-resolution aims to reconstruct high-frequency (HF) details from the prior model trained by a set of high- and low-resolution image patches. In this paper, HF to be estimated is considered as a combination of two components: main high-frequency (MHF) and residual high-frequency (RHF), and we propose a novel image super-resolution method via dual-dictionary learning and sparse representation, which consists of the main dictionary learning and the residual dictionary learning, to recover MHF and RHF respectively. Extensive experimental results on test images validate that by employing the proposed two-layer progressive scheme, more image details can be recovered and much better results can be achieved than the state-of-the-art algorithms in terms of both PSNR and visual perception.


page 2

page 3

page 4


Joint Dictionary Learning for Example-based Image Super-resolution

In this paper, we propose a new joint dictionary learning method for exa...

Image Super-resolution via Feature-augmented Random Forest

Recent random-forest (RF)-based image super-resolution approaches inheri...

Learning Priors in High-frequency Domain for Inverse Imaging Reconstruction

Ill-posed inverse problems in imaging remain an active research topic in...

Extracting Super-resolution Structures inside a Single Molecule or Overlapped Molecules from One Blurred Image

In some super-resolution techniques, adjacent points are illuminated at ...

Local Patch Classification Based Framework for Single Image Super-Resolution

Recent learning-based super-resolution (SR) methods often focus on the d...

Hybrid Function Sparse Representation towards Image Super Resolution

Sparse representation with training-based dictionary has been shown succ...

Sparsity-based Color Image Super Resolution via Exploiting Cross Channel Constraints

Sparsity constrained single image super-resolution (SR) has been of much...