An improved iterative back projection algorithm based on ringing artifacts suppression

FDSR: An Interpretable Frequency Division Stepwise Process Based Single-Image Super-Resolution Network

Deep learning has excelled in single-image super-resolution (SISR) applications, yet the lack of interpretability in most deep learning-based SR networks hinders their applicability, especially in fields like medical imaging that require transparent computation. To address these problems, we present an interpretable frequency division SR network that operates in the image frequency domain. It comprises a frequency division module and a step-wise reconstruction method, which divides the image into different frequencies and performs reconstruction accordingly. We develop a frequency division loss function to ensure that each reconstruction module (ReM) operates solely at one image frequency. These methods establish an interpretable framework for SR networks, visualizing the image reconstruction process and reducing the black box nature of SR networks. Additionally, we revisited the subpixel layer upsampling process by deriving its inverse process and designing a displacement generation module. This interpretable upsampling process incorporates subpixel information and is similar to pre-upsampling frameworks. Furthermore, we develop a new ReM based on interpretable Hessian attention to enhance network performance. Extensive experiments demonstrate that our network, without the frequency division loss, outperforms state-of-the-art methods qualitatively and quantitatively. The inclusion of the frequency division loss enhances the network's interpretability and robustness, and only slightly decreases the PSNR and SSIM metrics by an average of 0.48 dB and 0.0049, respectively.

Closed-Loop Residual Attention Network for Single Image Super-Resolution

Recent research on single image super-resolution (SISR) using convolutional neural networks (CNNs) with the utilization of residual structures and attention mechanisms to utilize image features has demonstrated excellent performance. However, previous SISR techniques mainly integrated extracted image features within a deep or wide network architecture, ignoring the interaction between multiscale features and the diversity of features. At the same time, SISR is also a typical ill-posed problem in that it allows for several predictions for a given LR image. These problems limit the great learning ability of CNNs. To solve these problems, we propose a closed-loop residual attention network (CLRAN) to extract and interact with all the available diversity of features features efficiently and limit the space of possible function solutions. Specifically, we design an enhanced residual attention block (ERA) to extract features, and it dynamically assigns weight to the internal attention branches. The ERA combines multi-scale block (MSB) and enhanced attention mechanism (EAM) base on the residual module. The MSB adaptively detects multiscale image features of different scales by using different 3 × 3 convolution kernels. The EAM combines multi-spectral channel attention (MSCA) and spatial attention (SA). Therefore, the EAM extracts different frequency component information and spatial information to utilize the diversity features. Furthermore, we apply the progressive network architecture and learn an additional map for model monitoring, which forms a closed-loop with the mapping already learned by the LR to HR function. Extensive experiments demonstrate that our CLRAN outperforms the state-of-the-art SISR methods on public datasets for both ×4 and ×8, proving its accuracy and visual perception.

Super-Resolution Network with Information Distillation and Multi-Scale Attention for Medical CT Image

The CT image is an important reference for clinical diagnosis. However, due to the external influence and equipment limitation in the imaging, the CT image often has problems such as blurring, a lack of detail and unclear edges, which affect the subsequent diagnosis. In order to obtain high-quality medical CT images, we propose an information distillation and multi-scale attention network (IDMAN) for medical CT image super-resolution reconstruction. In a deep residual network, instead of only adding the convolution layer repeatedly, we introduce information distillation to make full use of the feature information. In addition, in order to better capture information and focus on more important features, we use a multi-scale attention block with multiple branches, which can automatically generate weights to adjust the network. Through these improvements, our model effectively solves the problems of insufficient feature utilization and single attention source, improves the learning ability and expression ability, and thus can reconstruct the higher quality medical CT image. We conduct a series of experiments; the results show that our method outperforms the previous algorithms and has a better performance of medical CT image reconstruction in the objective evaluation and visual effect.

Multi-Path Deep CNN with Residual Inception Network for Single Image Super-Resolution

Recent research on single-image super-resolution (SISR) using deep convolutional neural networks has made a breakthrough and achieved tremendous performance. Despite their significant progress, numerous convolutional neural networks (CNN) are limited in practical applications, owing to the requirement of the heavy computational cost of the model. This paper proposes a multi-path network for SISR, known as multi-path deep CNN with residual inception network for single image super-resolution. In detail, a residual/ResNet block with an Inception block supports the main framework of the entire network architecture. In addition, remove the batch normalization layer from the residual network (ResNet) block and max-pooling layer from the Inception block to further reduce the number of parameters to preventing the over-fitting problem during the training. Moreover, a conventional rectified linear unit (ReLU) is replaced with Leaky ReLU activation function to speed up the training process. Specifically, we propose a novel two upscale module, which adopts three paths to upscale the features by jointly using deconvolution and upsampling layers, instead of using single deconvolution layer or upsampling layer alone. The extensive experimental results on image super-resolution (SR) using five publicly available test datasets, which show that the proposed model not only attains the higher score of peak signal-to-noise ratio/structural similarity index matrix (PSNR/SSIM) but also enables faster and more efficient calculations against the existing image SR methods. For instance, we improved our method in terms of overall PSNR on the SET5 dataset with challenging upscale factor 8× as 1.88 dB over the baseline bicubic method and reduced computational cost in terms of number of parameters 62% by deeply-recursive convolutional neural network (DRCN) method.

A Lightweight Dense Connected Approach with Attention on Single Image Super-Resolution

In recent years, neural networks for single image super-resolution (SISR) have applied more profound and deeper network structures to extract extra image details, which brings difficulties in model training. To deal with deep model training problems, researchers utilize dense skip connections to promote the model’s feature representation ability by reusing deep features of different receptive fields. Benefiting from the dense connection block, SRDensenet has achieved excellent performance in SISR. Despite the fact that the dense connected structure can provide rich information, it will also introduce redundant and useless information. To tackle this problem, in this paper, we propose a Lightweight Dense Connected Approach with Attention for Single Image Super-Resolution (LDCASR), which employs the attention mechanism to extract useful information in channel dimension. Particularly, we propose the recursive dense group (RDG), consisting of Dense Attention Blocks (DABs), which can obtain more significant representations by extracting deep features with the aid of both dense connections and the attention module, making our whole network attach importance to learning more advanced feature information. Additionally, we introduce the group convolution in DABs, which can reduce the number of parameters to 0.6 M. Extensive experiments on benchmark datasets demonstrate the superiority of our proposed method over five chosen SISR methods.

Noise-Robust Iterative Back-Projection

Noisy image super-resolution (SR) is a significant challenging process due to the smoothness caused by denoising. Iterative back-projection (IBP) can be helpful in further enhancing the reconstructed SR image, but there is no clean reference image available. This paper proposes a novel back-projection algorithm for noisy image SR. Its main goal is to pursuit the consistency between LR and SR images. We aim to estimate the clean reconstruction error to be back-projected, using the noisy and denoised reconstruction errors. We formulate a new cost function on the principal component analysis (PCA) transform domain to estimate the clean reconstruction error. In the data term of the cost function, noisy and denoised reconstruction errors are combined in a region-adaptive manner using texture probability. In addition, the sparsity constraint is incorporated into the regularization term, based on the Laplacian characteristics of the reconstruction error. Finally, we propose an eigenvector estimation method to minimize the effect of noise. The experimental results demonstrate that the proposed method can perform back-projection in a more noise-robust manner than the conventional IBP, and harmoniously work with any other SR methods as a post-processing.