Single Image Super-resolution Reconstruction Research Articles

Multitask dictionary learning and sparse representation based single-image super-resolution reconstruction

Recent researches have shown that the sparse representation based technology can lead to state of art super-resolution image reconstruction (SRIR) result. It relies on the idea that the low-resolution (LR) image patches can be regarded as down sampled version of high-resolution (HR) images, whose patches are assumed to have a sparser presentation with respect to a dictionary of prototype patches. In order to avoid a large training patches database and obtain more accurate recovery of HR images, in this paper we introduce the concept of examples-aided redundant dictionary learning into the single-image super-resolution reconstruction, and propose a multiple dictionaries learning scheme inspired by multitask learning. Compact redundant dictionaries are learned from samples classified by K-means clustering in order to provide each sample a more appropriate dictionary for image reconstruction. Compared with the available SRIR methods, the proposed method has the following characteristics: (1) introducing the example patches-aided dictionary learning in the sparse representation based SRIR, in order to reduce the intensive computation complexity brought by enormous dictionary, (2) using the multitask learning and prior from HR image examples to reconstruct similar HR images to obtain better reconstruction result and (3) adopting the offline dictionaries learning and online reconstruction, making a rapid reconstruction possible. Some experiments are taken on testing the proposed method on some natural images, and the results show that a small set of randomly chosen raw patches from training images and small number of atoms can produce good reconstruction result. Both the visual result and the numerical guidelines prove its superiority to some start-of-art SRIR methods.

Blind Single-Image Super-Resolution Reconstruction Based on Motion Blur

Blind image super-resolution reconstruction is one of the hot and difficult problem in image processing. a framework of blind single-image super-resolution reconstruction algorithm is proposed. In the low-resolution imaging model, the processes of motion blur, down-sampling, and noise are considered. The parameter of motion blur is estimated through an error-parameter analysis method. Utilizing Wiener filtering image restoration algorithm, an error-parameter curve at different motion distance is generated, from which the motion distance of the motion point spread function (PSF) can be estimated approximately. The super-resolution image is reconstructed through the iterative back projection (IBP) algorithm. The experimental results show that motion PSF estimation plays an important role on the quality of the SR reconstructed image, and also demonstrate the effectiveness of the proposed algorithm.

Phase regularisation for single image super-resolution reconstruction

A novel single image super-resolution reconstruction algorithm is proposed. Based on the geometrical model on the phases of complex wavelet coefficients of the image, a new image prior model leads to a powerful regularisation strategy for image super-resolution reconstruction, which is applicable to general image structures. Experimental results show that the method is effective at preserving the visual detailed information.

Wavelet Domain Image Super-Resolution Reconstruction Based on Image Pyramid and Cycle-Spinning

On the base of the analysis of single image super-resolution reconstruction, wavelet domain super-resolution reconstruction based on image Pyramid and cycle-spinning is proposed in the paper. The algorithm consists of the following parts: the predictive high-resolution image are obtained by a LR image based on laplacian pyramid method; the discrete wavelet transform is used for predictive high-resolution image to obtain the high-frequency wavelet coefficients; a high-resolution image is obtained by the inverse wavelet transform; Finally the cycle-spinning method is used to reduce ringing. The proposed algorithm avoids the application of iterative method, reduces the complexity of calculation and applies to large dimension low-resolution images. The results show the proposed approach has succeeded in obtaining a high-resolution image with a high peak signal-to-noise ratio and good visual quality.

Single-Frame Image Super-resolution through Contourlet Learning

We propose a learning-based, single-image super-resolution reconstruction technique using the contourlet transform, which is capable of capturing the smoothness along contoursmaking use of directional decompositions. The contourlet coefficients at finer scales of the unknown high-resolution image are learned locally from a set of high-resolution training images, the inverse contourlet transform of which recovers the super-resolved image. In effect, we learn the high-resolution representation of an oriented edge primitive from the training data. Our experiments show that the proposed approach outperforms standard interpolation techniques as well as a standard (Cartesian) wavelet-based learning both visually and in terms of the PSNR values, especially for images with arbitrarily oriented edges.