Example-based Super-resolution Algorithm Research Articles

Multiple Sequential Regularized Extreme Learning Machines for Single Image Super Resolution

In this letter, we propose an example-based super-resolution algorithm based on multiple neural networks trained sequentially using the method online sequential regularized extreme learning machine. In order to train multiple networks, we divide the training samples into clusters using local gradient information, and a distinct network is trained for each cluster. We add another layer of learning by training linear kernels to reshape the network output patches into full images. Also, we employ a fast reconstruction scheme before and after the learning stage. Experiments show that the proposed method generates comparable or better results when compared to important works of the literature, without the need for specialized hardware, large training datasets, and extensive training time.

Super Resolution of Light Field Images Using Linear Subspace Projection of Patch-Volumes

Light field imaging has emerged as a very promising technology in the field of computational photography. Cameras are becoming commercially available for capturing real-world light fields. However, capturing high spatial resolution light fields remains technologically challenging, and the images rendered from real light fields have today a significantly lower spatial resolution compared to traditional two-dimensional (2-D) cameras. This paper describes an example-based super-resolution algorithm for light fields, which allows the increase of the spatial resolution of the different views in a consistent manner across all subaperture images of the light field. The algorithm learns linear projections between subspaces of reduced dimension in which reside patch-volumes extracted from the light field. The method is extended to cope with angular super-resolution, where 2-D patches of intermediate subaperture images are approximated from neighboring subaperture images using multivariate ridge regression. Experimental results show significant quality improvement when compared to state-of-the-art single-image super-resolution methods applied on each view separately, as well as when compared to a recent light field super-resolution techniques based on deep learning.

Multi-example feature-constrained back-projection method for image super-resolution

Example-based super-resolution algorithms, which predict unknown high-resolution image information using a relationship model learnt from known high- and low-resolution image pairs, have attracted considerable interest in the field of image processing. In this paper, we propose a multi-example feature-constrained back-projection method for image super-resolution. Firstly, we take advantage of a feature-constrained polynomial interpolation method to enlarge the low-resolution image. Next, we consider low-frequency images of different resolutions to provide an example pair. Then, we use adaptive kNN search to find similar patches in the low-resolution image for every image patch in the high-resolution low-frequency image, leading to a regression model between similar patches to be learnt. The learnt model is applied to the low-resolution high-frequency image to produce high-resolution high-frequency information. An iterative back-projection algorithm is used as the final step to determine the final high-resolution image. Experimental results demonstrate that our method improves the visual quality of the high-resolution image.

An Example-based Super-Resolution Algorithm for Multi-Spectral Remote Sensing Images

This paper proposes an example-based super-resolution algorithm for multi-spectral remote sensing images. The underlying idea of this algorithm is to learn a matrix-based implicit prior from a set of high-resolution training examples to model the relation between LR and HR images. The matrix-based implicit prior is learned as a regression operator using conjugate decent method. The direct relation between LR and HR image is obtained from the regression operator and it is used to super-resolve low-resolution multi-spectral remote sensing images. A detailed performance evaluation is carried out to validate the strength of the proposed algorithm.

Example-based super-resolution via social images

A novel image patch based example-based super-resolution algorithm is proposed for benefitting from social image data. The proposed algorithm is designed based on matrix-value operator learning techniques where the image patches are understood as the matrices and the single-image super-resolution is treated as a problem of learning a matrix-value operator. Taking advantage of the matrix trick, the proposed algorithm is so fast that it could be trained on social image data. To our knowledge, the proposed algorithm is the fastest single-image super-resolution algorithm when both training and test time are considered. Experimental results have shown the efficiency and the competitive performance of the proposed algorithm to most of state-of-the-art single-image super-resolution algorithms.

Super-resolution algorithm exploiting multiple dictionaries based on local image structures

We propose an example-based superresolution algorithm that adaptively exploits multiple dictionaries based on local image structures. Noise, irregularities, and blurred textures are noticeable artifacts in the reconstructed image due to a shortage of relevant examples and false exploration in the dictionary. These artifacts are emphasized during successive enhancement. We alleviate the artifacts by constructing multiple dictionaries coupled with different sharpness levels during the learning phase. We exploit these dictionaries adaptively based on local image structures during the synthesis phase. Experimental results show that the proposed algorithm provides more detailed images with significantly reduced artifacts while consuming only 8.6% of storage capacity and 0.25% of CPU running time in comparison with a typical example-based superresolution algorithm based on neighbor embedding.