Single-frame Image Super-resolution Research Articles

Single-frame super-resolution for remote sensing images based on improved deep recursive residual network

Single-frame image super-resolution (SISR) technology in remote sensing is improving fast from a performance point of view. Deep learning methods have been widely used in SISR to improve the details of rebuilt images and speed up network training. However, these supervised techniques usually tend to overfit quickly due to the models’ complexity and the lack of training data. In this paper, an Improved Deep Recursive Residual Network (IDRRN) super-resolution model is proposed to decrease the difficulty of network training. The deep recursive structure is configured to control the model parameter number while increasing the network depth. At the same time, the short-path recursive connections are used to alleviate the gradient disappearance and enhance the feature propagation. Comprehensive experiments show that IDRRN has a better improvement in both quantitation and visual perception.

Single image super-resolution via non-local normalized graph Laplacian regularization: A self-similarity tribute

The process of producing a high-resolution image given a single low-resolution noisy measurement is called single-frame image super-resolution (SISR). Historically, many fractal-based schemes have been proposed in the literature to address the SISR problem. Many conventional interpolation schemes fail to preserve important edge information of natural images and cannot be used blindly for resolution enhancement. Generally, a-priori constraints are required in the process of high resolution image approximation. We model the SISR problem as an energy minimization procedure which balances data fidelity and a regularization term. The regularization term will implicitly incorporate natural image redundancy via a normalized graph Laplacian operator, as a self-similarity based prior. This operator applies a non-local kernel similarity measure due to the choice of a non-local operator for the weight assignment. The data fidelity term is modelled as a likelihood estimator that is scaled using a sharpening term composed from the normalized graph Laplacian operator. Finally, a conjugate gradient scheme is used to minimize the objective functional. Promising results on resolution enhancement for a variety of digital images will be presented.

Performance Analysis of Wavelet Transforms for Learning based Single frame Image Super-resolution

super resolution concept has been introduced for image enhancement in various applications. Image enhancement is crucial operation essential for reducing different possible degradations of the captured image. More sophisticated techniques are already proposed. Wavelet transform based algorithms are widely used in many applications. Wavelet transform/s is used to extrapolate missing high frequency components which improve the efficiency of an algorithm. In this paper for super resolving the images, wavelet coefficients of the unknown high resolution image are learnt from a set of high resolution training images in wavelet domain. The performance of different discrete orthogonal and a biorthogonal wavelets have been evaluated on different class of images in terms of MSE and PSNR. The outcome of this work suggests that use of db4 wavelet transform is appropriate for super resolution technique. The PSNR obtained with this transform outfits for other wavelet transforms.

Vehicle license plate super-resolution using soft learning prior

This paper proposes a new algorithm to perform single-frame image super-resolution (SR) of vehicle license plate (VLP) using soft learning prior. Conventional single-frame SR/interpolation methods ...

Directionally adaptive single frame image super resolution

The single image super resolution recovers missing high resolution details so as to reconstruct a high resolution image from a single low resolution image. This paper proposes a novel directionally adaptive, learning-based, single image super resolution method using multiple direction wavelet transform, called directionlets. Here, critically sampled directionlets are used to capture directional features effectively and to extract edge information along different directions from a set of available high resolution images. This information is used as the training set for super resolving a low resolution input image. The directionlet coefficients at finer scales of its high resolution image are learned locally from this training set and the inverse directionlet transform recovers the super resolved high resolution image. The simulation results showed that the proposed directionlet approach outperforms standard interpolation techniques like cubic spline interpolation as well as standard wavelet-based learning, both visually and in terms of the mean squared error (MSE) values. The SNR scores for cubic spline interpolation, wavelet and directionlet method are 13.6998 dB, 23.8324 dB and 30.8654 dB respectively for Barbara.

Single Frame Image Super Resolution Using Learned Directionlets

In this paper, a new directionally adaptive, learning based, single image super resolution method using multiple direction wavelet transform, called Directionlets is presented. This method uses directionlets to effectively capture directional features and to extract edge information along different directions of a set of available high resolution images .This information is used as the training set for super resolving a low resolution input image and the Directionlet coefficients at finer scales of its high-resolution image are learned locally from this training set and the inverse Directionlet transform recovers the super-resolved high resolution image. The simulation results showed that the proposed approach outperforms standard interpolation techniques like Cubic spline interpolation as well as standard Wavelet-based learning, both visually and in terms of the mean squared error (mse) values. This method gives good result with aliased images also .

Example Based Single-Frame Image Super-Resolution by Support Vector Regression

As many other inverse problems, single-frame image super-resolution is an ill-posed problem. The problem has been approached in the context of machine learning. However, the proposed method in this paper is different from other learning based methods regarding how the input/output are formulated as well as how the learning is done. The assumption behind example based methods is the local similarity across seemingly different images. The assumption is illustrated by examples of image coding. Because of the differences in formulating the input/output and the implementation of Support Vector Regression (SVR), it is shown that the proposed approach outperforms the competing SVR method and the kernel regression method in terms of Peak Signal-to-Noise Ratio (PSNR), objective measurements of image quality. Since example based approaches are based on training, in which we know exactly what the output shall be. Therefore, it is proper to objectively measure the performance since the trained model is expected to “correctly” restore the image rather than to enhance the image, e.g. sharpening.

Single frame image super-resolution: should we process locally or globally?

In this paper we study the usefulness of different local and global, learning-based, single-frame image super-resolution reconstruction techniques in handling three specific tasks, namely, de-blurring, de-noising and alias removal. We start with the global, iterative Papoulis---Gerchberg method for super-resolving a scene. Next we describe a PCA-based global method which faithfully reproduces a super-resolved image from a blurred and noisy low resolution input. We also study several multi-resolution processing schemes for super-resolution where the best edges are learned locally from an image database. We show that the PCA-based global method is efficient in handling blur and noise in the data. The local methods are adept in capturing the edges properly. However, both local and global approaches cannot properly handle the aliasing present in the low resolution observation. Hence we propose an alias removal technique by designing an alias-free upsampling scheme. Here the unknown high frequency components of the given partially aliased (low resolution) image is generated by minimizing the total variation of the interpolant subject to the constraint that part of alias free spectral components in the low resolution observation are known precisely and under the assumption of sparsity in the data.

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.