Super Resolution Imaging Needs Better Registration for Better Quality Results

Deep Feature Blend Attention: A New Frontier in Super Resolution Image Generation

Due to the factors like processing power limitations and channel capabilities images are often down sampled and transmitted at low bit rates resulting in a low resolution compressed image. High resolution images can be reconstructed from several blurred, noisy and down sampled low resolution images using a computational process know as super resolution reconstruction. Super-resolution is the process of combining multiple aliased low-quality images to produce a high resolution, high-quality image. The problem of recovering a high resolution image progressively from a sequence of low resolution compressed images is considered. In this paper we propose a novel DCT based progressive image display algorithm by stressing on the encoding and decoding process. At the encoder we consider a set of low resolution images which are corrupted by additive white Gaussian noise and motion blur. The low resolution images are compressed using 8 by 8 blocks DCT and noise is filtered using our proposed novel zonal filter. Multiframe fusion is performed in order to obtain a single noise free image. At the decoder the image is reconstructed progressively by transmitting the coarser image first followed by the detail image. And finally a super resolution image is reconstructed by applying our proposed novel adaptive interpolation technique. We have performed both objective and subjective analysis of the reconstructed image, and the resultant image has better super resolution factor, and a higher ISNR and PSNR. A comparative study done with Iterative Back Projection (IBP) and Projection on to Convex Sets (POCS),Papoulis Grechberg, FFT based Super resolution Reconstruction shows that our method has out performed the previous contributions.

The topic of super-resolution image reconstruction has recently received considerable attention within the research area. Super-resolution image reconstruction methods attempt to create a single high-resolution image from a number of low-resolution images (or a video sequence). The Bayesian maximum a posteriori (MAP) estimation method is widely used for super-resolution image reconstruction. So far, existing super-resolution reconstruction methods are all confronted with the problem of slow convergence and expensive computation. To satisfy the requirement of real-time application, we propose a high-efficiency super-resolution reconstruction algorithm that solves two key bottlenecks in the multi-frame MAP framework. The first breakthrough is to select the Armijo rule to identify the step length instead of the exact line search. The second one is to approximately compute the gradient of the MAP objective function using analytic representation instead of numerical calculation. Experimental results show that the proposed algorithm is applicable to real-time super-resolution reconstruction of low-resolution image sequences.

Super-resolution (SR) techniques are used in PET imaging to generate a high-resolution image by combining multiple low-resolution images that have been acquired from different points of view (POVs). The number of low-resolution images used defines the processing time and memory storage necessary to generate the SR image. In this paper, the authors propose two optimized SR implementations (ISR-1 and ISR-2) that require only a subset of the low-resolution images (two sides and diagonal of the image matrix, respectively), thereby reducing the overall processing time and memory storage. In an N x N matrix of low-resolution images, ISR-1 would be generated using images from the two sides of the N x N matrix, while ISR-2 would be generated from images across the diagonal of the image matrix. The objective of this paper is to investigate whether the two proposed SR methods can achieve similar performance in contrast and signal-to-noise ratio (SNR) as the SR image generated from a complete set of low-resolution images (CSR) using simulation and experimental studies. A simulation, a point source, and a NEMA/IEC phantom study were conducted for this investigation. In each study, 4 (2 x 2) or 16 (4 x 4) low-resolution images were reconstructed from the same acquired data set while shifting the reconstruction grid to generate images from different POVs. SR processing was then applied in each study to combine all as well as two different subsets of the low-resolution images to generate the CSR, ISR-1, and ISR-2 images, respectively. For reference purpose, a native reconstruction (NR) image using the same matrix size as the three SR images was also generated. The resultant images (CSR, ISR-1, ISR-2, and NR) were then analyzed using visual inspection, line profiles, SNR plots, and background noise spectra. The simulation study showed that the contrast and the SNR difference between the two ISR images and the CSR image were on average 0.4% and 0.3%, respectively. Line profiles of the point source study showed that the three SR images exhibited similar signal amplitudes and FWHM. The NEMA/IEC study showed that the average difference in SNR among the three SR images was 2.1% with respect to one another and they contained similar noise structure. ISR-1 and ISR-2 can be used to replace CSR, thereby reducing the total SR processing time and memory storage while maintaining similar contrast, resolution, SNR, and noise structure.

Superresolution (SR) image reconstruction is a technique to obtain a high-resolution (HR) image from a set of low-resolution images. Compact High Resolution Imaging Spectrometer (CHRIS)/Project for On-Board Autonomy (Proba) is a transitional hyperspectral-oriented satellite which acquires multiple angular images of the same scene. The angular images acquired within a very short period of time are ideal for SR operation. Recent developments point to the possibility of a SR-enhanced CHRIS data set at higher resolution. Apparently, the additional details are valuable information for many applications. This letter presents the preliminary evaluation of the SR CHRIS images for ecotope mapping and subpixel classification of sealed surface using two different scenes in Belgium. Accuracy obtained from SR CHRIS images is comparable to that of the original CHRIS, but with significantly more detail in the final classification map. In view of the demands for HR hyperspectral data sets, SR operation can be an interesting option to mitigate the lower spatial resolution of the current and future spaceborne hyperspectral images. Properties such as quick revisiting time and angular acquisition of a hyperspectral satellite are important for the success of SR operations.

The paper proposes an image super resolution reconstruction (SRR) algorithm based on Undecimated Morphological Wavelet (UMW). As UMW can maintain more gradient information and eliminate more artificial blocks, it is used to decompose low resolution (LR) images. High frequency coefficients from the decomposition contain the gradients that reflect the horizontal, vertical, and diagonal domain information. Then both the low frequency and high frequency coefficients are interpolated to produce an extended group of coefficient sequence. Finally, the extended coefficients are fused and using inverse transformation to produce a super resolution image. Experimental results show that that the proposed algorithm have good performance in the image reconstruction quality and the computational efficiency.

Coping with the limited spatial resolution of images, which is caused by the physical limitations of image sensors, is the objective of this thesis. Initially, an effort to model the scanner function when generating a document copy by means of simple models is made. In a task of scanner function simulation the proposed model should be preferred over the Gaussian and Cauchy models met in bibliography as it is equivalent in performance, simpler in implementation and does not present any dependence on certain scanner characteristics. Afterwards, new methods for improving images spatial resolution are formulated. A nonuniform interpolation method for Super-Resolution (SR) image reconstruction is proposed. Experimentation proves that the proposed method employing Kriging interpolation predominates over the method which creates the high-resolution grid by means of the weighted nearest neighbor interpolation that is a conventional interpolation technique. Also, three new methods for stochastic regularized SR image reconstruction are presented. The Tukey error norm in combination with the Bilateral Total Variation (BTV) regularization, the Lorentzian error norm in combination with the BTV regularization and the Huber error norm combined with the BTV regularization are the three proposed methods. An additional novelty is the direct comparison of the three estimators Tukey, Lorentzian and Huber in the task of super-resolution image reconstruction, thus in rejecting outliers. The performance of the proposed methods proves superior to that of a regularized SR technique met in bibliography. Experimental results verify the robust statistics theory. Moreover, a novel study which considers the effect of each one of the data-fidelity and regularization terms on the SR image reconstruction result is carried out. The conclusions reached help to select an effective SR image reconstruction method, among several potential ones, for a given low-resolution sequence of frames. Finally, an image interpolation method employing a neural network is proposed. The presented training procedure results in the network learning the scanner point spread function. Experimental results prove that the proposed technique predominates over the classical algorithms of bicubic and spline interpolation. The proposed method is novel as it treats, for the first time, the issue of the training data presentation order to the neural network input.

Multi-frame Super-Resolution (SR) image reconstruction creates a single High-Resolution (HR) image from a sequence of Low-Resolution (LR) frames. Apart from resolution increment, blurring and noise removal is also achieved. In stochastic regularized methods, the SR problem is formulated by means of two terms, the data-fidelity term and the regularization term. In the present work, a novel estimator named Var − norm has been proposed for utilization in the data-fidelity term. This estimator presents a simple mathematical form based on the variance of the SR estimation error, i.e. on the difference between the estimated LR frame and the corresponding measured LR frame. The introduced Var − norm estimator is combined with the Bilateral Total Variation (BTV) regularization to formulate a novel SR method. The SR performance of the proposed method is directly compared with that of two SR techniques existing in the literature. Experimentation proves that the proposed method outperforms the existing methods.

Super Resolution (SR) is an interesting topic in video and image research. Super resolution image reconstruction (SRR) is one of the commonest SR technologies and has been proposed in many forms. SRR reconstructs a highresolution image from multiple low-resolution images. However, the low-resolution images require an aliasing process prior to reconstruction. The present paper analyzes SRR in the frequency domain, and demonstrates that SRR is unsuitable for general applications.

Social media network is inseparable from image recognition, and image super-resolution (SR) reconstruction plays an important role in image recognition. The changes of scale and geometry are rarely considered in the image super-resolution reconstruction based on deep learning over the years, we introduce a super-resolution reconstruction network based on deformable convolutional network. We replace the ordinary convolution with the deformable convolution to pretend the geometric deformation and extract abundant local features. The image super-resolution reconstruction is usually based on the conventional convolutional neural network (CNN). Most CNN-based SR models do not utilize the features of the original low resolution (LR) image as much as possible, resulting in lower performance. After introducing the idea of deformable convolution, though the complexity is increased, the recognition accuracy is obviously raised.

This paper proposes a new algorithm to integrate image registration into image super-resolution (SR). Image SR is a process to reconstruct a high-resolution (HR) image by fusing multiple low-resolution (LR) images. A critical step in image SR is accurate registration of the LR images or, in other words, effective estimation of motion parameters. Conventional SR algorithms assume either the estimated motion parameters by existing registration methods to be error-free or the motion parameters are known a priori. This assumption, however, is impractical in many applications, as most existing registration algorithms still experience various degrees of errors, and the motion parameters among the LR images are generally unknown a priori. In view of this, this paper presents a new framework that performs simultaneous image registration and HR image reconstruction. As opposed to other current methods that treat image registration and HR reconstruction as disjoint processes, the new framework enables image registration and HR reconstruction to be estimated simultaneously and improved progressively. Further, unlike most algorithms that focus on the translational motion model, the proposed method adopts a more generic motion model that includes both translation as well as rotation. An iterative scheme is developed to solve the arising nonlinear least squares problem. Experimental results show that the proposed method is effective in performing image registration and SR for simulated as well as real-life images.

Image super-resolution (SR) can be seen as finding a nonlinear mapping between low-resolution (LR) image and high-resolution (HR) image. Convolutional neural networks (CNN) based image SR methods have achieved great success based on features extracted from pretrained networks. However, the previous works less consider multiscale features. In this paper, we propose a SR cascaded multi-column convolutional neural network (SRCMCN) to recover HR image by learning multi-scale features from the corresponding LR image. Compared to existing CNN based image SR methods, the proposed method directly takes the original LR image as input to learn the residual between interpolated LR image and corresponding HR image, which will reduce the computational cost of convolution due to the small input size. Besides, in order to achieve high-quality reconstruction, we optimize our networks using mean absolute error (MAE) loss function. Experimental results demonstrate that our proposed method outperforms several state-of-the-art image SR methods in terms of both reconstructed image quality and computational efficiency.

Superresolution (SR) image reconstruction is able to overcome the resolution limit of camera imaging system through integrating information of multiple low resolution (LR) images that the perceived resolution of the reconstruction image is much higher than that of the individual image. Since the ill-posed SR reconstruction problem can be regularized within a Bayesian context by adopting a priori image model, we propose a hybrid Bayesian method for image reconstruction, which firstly estimates the unknown point spread function (PSF) and an approximation for the original ideal image, and then sets up the Huber Markov Random Field (HMRF) image prior model and assesses its tuning parameter using maximum likelihood (ML) estimator, finally computes the regularized solution automatically. Hybrid Bayesian estimates computed on simulation images, satellite images and video sequence show dramatic visual and quantitative improvements over bilinear interpolation and Maximum A Posteriori reconstruction results with sharp edges, correctly restored textures and a high PSNR improvement.

Spatial resolution of image is a critical index of image quality, and also is an important parameter in the area of image application. However, there are many factors which can lower and degenerate the quality of images in the process of capturing images. An effective solution to this problem is the super-resolution image reconstruction, that means reconstructing a high resolution (HR) image from some low resolution (LR) images, and eliminating the additive noise and blur which is caused by the size of the detector and optical at the same time. In this paper,one of project of convex set method for reconstructing a super-resolution image from multiframe undersampling images is introduced.First,a very important factor-the model of the process of imaging in spatial domain iterative method for super-resolution image reconstruction is mentioned. Next the reconstruction model and its steps are introduced through introducing the theory of project of convex set method. At last, the technique is available by experiments. The result indicates the project of convex set method for super-resolution image reconstruction has preferable effect on multiframe undersampling remote sensing images, and the technique of super-resolution image reconstruction can used in lots of fields such as remote sensing, computer vision, public security, physic imaging and so on.

Super-resolution of cardiac magnetic resonance images using Laplacian Pyramid based on Generative Adversarial Networks