Deep Learned Singular Residual Network for Super Resolution Reconstruction

Single image super resolution(SISR)techniques produce images of high resolution(HR)as output from input images of low resolution(LR).Motivated by the effectiveness of deep learning methods,we provide a framework based on deep learning to achieve super resolution(SR)by utilizing deep singular-residual neural network(DSRNN)in training phase.Residuals are obtained from the difference between HR and LR images to generate LR-residual example pairs.Singular value decomposition(SVD)is applied to each LR-residual image pair to decompose into subbands of low and high frequency components.Later,DSRNN is trained on these subbands through input and output channels by optimizing the weights and biases of the network.With fewer layers in DSRNN,the influence of exploding gradients is reduced.This speeds up the learning process and also improves accuracy by using skip connections.The trained DSRNN parameters yield residuals to recover the HR subbands in the testing phase.Experimental analysis shows that the proposed method results in superior performance to existingmethods in terms of subjective quality.Extensive testing results on popular benchmark datasets such as set5,set14,and urban100 for a scaling factor of 4 show the effectiveness of the proposed method across different qualitative evaluation metrics.

Arbitrary Scale Super Resolution Network for Satellite Imagery

Recently,satellite imagery has been widely applied in many areas.However,due to the limitations of hardware equipment and transmission bandwidth,the images received on the ground have low resolution and weak texture.In addition,since ground terminals have various resolutions and real-time playing requirements,it is essential to achieve arbitrary scale super-resolution(SR)of satellite images.In this paper,we propose an arbitrary scale SR network for satellite image reconstruction.First,we propose an arbitrary upscale module for satellite imagery that can map low-resolution satellite image features to arbitrary scale enlarged SR outputs.Second,we design an edge reinforcement module to enhance the highfrequency details in satellite images through a twobranch network.Finally,extensive upsample experiments on WHU-RS19 and NWPU-RESISC45 datasets and subsequent image segmentation experiments both show the superiority of our method over the counterparts.

Super Resolution Perception for Improving Data Completeness in Smart Grid State Estimation

The smart grid is an evolving critical infrastructure,which combines renewable energy and the most advanced information and communication technologies to provide more economic and secure power supply services.To cope with the intermittency of ever-increasing renewable energy and ensure the security of the smart grid,state estimation,which serves as a basic tool for understanding the true states of a smart grid,should be performed with high frequency.More complete system state data are needed to support high-frequency state estimation.The data completeness problem for smart grid state estimation is therefore studied in this paper.The problem of improving data completeness by recovering highfrequency data from low-frequency data is formulated as a super resolution perception(SRP)problem in this paper.A novel machine-learning-based SRP approach is thereafter proposed.The proposed method,namely the Super Resolution Perception Net for State Estimation(SRPNSE),consists of three steps:feature extraction,information completion,and data reconstruction.Case studies have demonstrated the effectiveness and value of the proposed SRPNSE approach in recovering high-frequency data from low-frequency data for the state estimation.

A Regularized Super Resolution Algorithm for Generalized Gaussian Noise

In this paper,an iterative regularized super resolution (SR) algorithm considering non-Gaussian noise is proposed.Based on the assumption of a generalized Gaussian distribution for the contaminating noise,an lp norm is adopted to measure the data fidelity term in the cost function.In the meantime,a regularization functional defined in terms of the desired high resolution (HR) image is employed,which allows for the simultaneous determination of its value and the partly reconstructed image at each iteration step.The convergence is thoroughly studied.Simulation results show the effectiveness of the proposed algorithm as well as its superiority to conventional SR methods.

Super Resolution Sensing Technique for Distributed Resource Monitoring on Edge Clouds

With the vigorous development of mobile networks,the number of devices at the network edge is growing rapidly and the massive amount of data generated by the devices brings a huge challenge of response latency and communication burden.Existing resource monitoring systems are widely deployed in cloud data centers,but it is difficult for traditional resource monitoring solutions to handle the massive data generated by thousands of edge devices.To address these challenges,we propose a super resolution sensing(SRS)method for distributed resource monitoring,which can be used to recover reliable and accurate high‑frequency data from low‑frequency sampled resource monitoring data.Experiments based on the proposed SRS model are also conducted and the experimental results show that it can effectively reduce the errors generated when recovering low‑frequency monitoring data to high‑frequency data,and verify the effectiveness and practical value of applying SRS method for resource monitoring on edge clouds.

Multiframe Blind Super Resolution Imaging Based on Blind Deconvolution

As an ill-posed problem, multiframe blind super resolution imaging recovers a high resolution image from a group of low resolution images with some degradations when the information of blur kernel is limited. Note that the quality of the recovered image is influenced more by the accuracy of blur estimation than an advanced regularization. We study the traditional model of the multiframe super resolution and modify it for blind deblurring. Based on the analysis, we proposed two algorithms. The first one is based on the total variation blind deconvolution algorithm and formulated as a functional for optimization with the regularization of blur. Based on the alternating minimization and the gradient descent algorithm, the high resolution image and the unknown blur kernel are estimated iteratively. By using the median shift and add operator, the second algorithm is more robust to the outlier influence. The MSAA initialization simplifies the interpolation process to reconstruct the blurred high resolution image for blind deblurring and improves the accuracy of blind super resolution imaging. The experimental results demonstrate the superiority and accuracy of our novel algorithms.

MTF Measurement of EBCCD Imaging System by Using Super Resolution Technique

Existing methods of measurement MTF for discrete imaging system are analysed. A slit target is frequently used to measure the MTF for an imaging system. Usually there are four methods to measure the MTF for a discrete imaging system by using a slit. These methods have something imperfect respectively. But for the discrete imaging systems of under sampling it is difficult to reproduce this type of target properly since frequencies above Nyquist are folded into those below Nyquist, resulting in aliasing effect. To tackle the aliasing problem, a super resolution technique is introduced into our measurement, which gives MTF values both above and below Nyquist more accurately.

A Novel AlphaSRGAN for Underwater Image Super Resolution

Obtaining clear images of underwater scenes with descriptive details is an arduous task.Conventional imaging techniques fail to provide clear cut features and attributes that ultimately result in object recognition errors.Consequently,a need for a system that produces clear images for underwater image study has been necessitated.To overcome problems in resolution and to make better use of the Super-Resolution(SR)method,this paper introduces a novel method that has been derived from the Alpha Generative Adversarial Network(AlphaGAN)model,named Alpha Super Resolution Generative Adversarial Network(AlphaSRGAN).The model put forth in this paper helps in enhancing the quality of underwater imagery and yields images with greater resolution and more concise details.Images undergo pre-processing before they are fed into a generator network that optimizes and reforms the structure of the network while enhancing the stability of the network that acts as the generator.After the images are processed by the generator network,they are passed through an adversarial method for training models.The dataset used in this paper to learn Single Image Super Resolution(SISR)is the USR 248 dataset.Training supervision is performed by an unprejudiced function that simultaneously scrutinizes and improves the image quality.Appraisal of images is done with reference to factors like local style information,global content and color.The dataset USR 248 which has a huge collection of images has been used for the study is composed of three collections of images—high(640×480)and low(80×60,160×120,and 320×240).Paired instances of different sizes—2×,4×and 8×—are also present in the dataset.Parameters like Mean Opinion Score(MOS),Peak Signal-to-Noise Ratio(PSNR),Structural Similarity(SSIM)and Underwater Image Quality Measure(UIQM)scores have been compared to validate the improved efficiency of our model when compared to existing works.

Meta-Learning Multi-Scale Radiology Medical Image Super-Resolution

High-resolution medical images have important medical value,but are difficult to obtain directly.Limited by hardware equipment and patient’s physical condition,the resolution of directly acquired medical images is often not high.Therefore,many researchers have thought of using super-resolution algorithms for secondary processing to obtain high-resolution medical images.However,current super-resolution algorithms only work on a single scale,and multiple networks need to be trained when super-resolution images of different scales are needed.This definitely raises the cost of acquiring high-resolution medical images.Thus,we propose a multi-scale superresolution algorithm using meta-learning.The algorithm combines a metalearning approach with an enhanced depth of residual super-resolution network to design a meta-upscale module.The meta-upscale module utilizes the weight prediction property of meta-learning and is able to perform the super-resolution task of medical images at any scale.Meanwhile,we design a non-integer mapping relation for super-resolution,which allows the network to be trained under non-integer magnification requirements.Compared to the state-of-the-art single-image super-resolution algorithm on computed tomography images of the pelvic region.The meta-learning multiscale superresolution algorithm obtained a surpassing of about 2%at a smaller model volume.Testing on different parts proves the high generalizability of our algorithm.Multi-scale super-resolution algorithms using meta-learning can compensate for hardware device defects and reduce secondary harm to patients while obtaining high-resolution medical images.It can be of great use in imaging related fields.

Two-Stage Point Cloud Super Resolution with Local Interpolation and Readjustment via Outer-Product Neural Network

This paper proposes a two-stage point cloud super resolution framework that combines local interpolation and deep neural network based readjustment. For the first stage, the authors apply a local interpolation method to increase the density and uniformity of the target point cloud. For the second stage, the authors employ an outer-product neural network to readjust the position of points that are inserted at the first stage. Comparison examples are given to demonstrate that the proposed framework achieves a better accuracy than existing state-of-art approaches, such as PU-Net, Point Net and DGCNN(Source code is available at https://github.com/qwerty1319/PC-SR).

Face Super-resolution Reconstruction and Recognition Using Non-local Similarity Dictionary Learning Based Algorithm

One of the challenges of face recognition in surveillance is the low resolution of face region. Therefore many superresolution(SR) face reconstruction methods are proposed to produce a high-resolution face image from one or a set of low-resolution face images. However, existing dictionary learning based algorithms are sensitive to noise and very time-consuming.In this paper, we define and prove the multi-scale linear combination consistency. In order to improve the performance of SR, we propose a novel SR face reconstruction method based on nonlocal similarity and multi-scale linear combination consistency(NLS-MLC). We further proposed a new recognition approach for very low resolution face images based on resolution scale invariant feature(RSIF). A series of experiments are conducted on two public face image databases to test feasibility of our proposed methods. Experimental results show that the proposed SR method is more robust and computationally effective in face hallucination, and the recognition accuracy of RSIF is higher than some state-of-art algorithms.

Improved Network for Face Recognition Based on Feature Super Resolution Method

Low-resolution face images can be found in many practical applications. For example, faces captured from surveillance videos are typically in small sizes. Existing face recognition deep networks, trained on high-resolution images, perform poorly in recognizing low-resolution faces. In this work, an improved multi-branch network is proposed by combining ResNet and feature super-resolution modules. ResNet is for recognizing high-resolution facial images and extracting features from both high-and low-resolution images.Feature super-resolution modules are inserted before the classifier of ResNet for low-resolution facial images. They are used to increase feature resolution. The proposed method is effective and simple. Experimental results show that the recognition accuracy for high-resolution face images is high, and the recognition accuracy for low-resolution face images is improved.

Super-resolution fluorescence polarization microscopy

Fluorescence polarization is related to the dipole orientation of chromophores,making fuores-cence polarization microscopy possible to_reveal structures and functions of tagged cellularorganelles and biological macromolecules.Several recent super resolution techniques have beenapplied to fluorescence polarization microscopy,achieving dipole measurement at nanoscale.In this review,we summarize both difraction limited and super resolution fluorescence polari-zation microscopy techniques,as well as their applications in biological imaging.

Super-resolution filtered ghost imaging with compressed sensing

A filtered ghost imaging(GI)protocol is proposed that enables the Rayleigh diffraction limit to be exceeded in an intensity correlation system;a super-resolution reconstructed image is achieved by low-pass filtering of the measured intensities.In a lensless GI experiment performed with spatial bandpass filtering,the spatial resolution can exceed the Rayleigh diffraction bound by more than a factor of 10.The resolution depends on the bandwidth of the filter,and the relationship between the two is investigated and discussed.In combination with compressed sensing programming,not only high resolution can be maintained but also image quality can be improved,while a much lower sampling number is sufficient.

Data Matching of Solar Images Super-Resolution Based on Deep Learning

The images captured by different observation station have different resolutions.The Helioseismic and Magnetic Imager(HMI:a part of the NASA Solar Dynamics Observatory SDO)has low-precision but wide coverage.And the Goode Solar Telescope(GST,formerly known as the New Solar Telescope)at Big Bear Solar Observatory(BBSO)solar images has high precision but small coverage.The super-resolution can make the captured images become clearer,so it is wildly used in solar image processing.The traditional super-resolution methods,such as interpolation,often use single image’s feature to improve the image’s quality.The methods based on deep learning-based super-resolution image reconstruction algorithms have better quality,but small-scale features often become ambiguous.To solve this problem,a transitional amplification network structure is proposed.The network can use the two types images relationship to make the images clear.By adding a transition image with almost no difference between the source image and the target image,the transitional amplification training procedure includes three parts:transition image acquisition,transition network training with source images and transition images,and amplification network training with transition images and target images.In addition,the traditional evaluation indicators based on structural similarity(SSIM)and peak signal-to-noise ratio(PSNR)calculate the difference in pixel values and perform poorly in cross-type image reconstruction.The method based on feature matching can effectively evaluate the similarity and clarity of features.The experimental results show that the quality index of the reconstructed image is consistent with the visual effect.

Comparison of density and positioning accuracy of PS extracted from super-resolution PSI with those from traditional PSI

In the application of persistent scatterer interferometry(PSI),deformation information is extracted from persistent scatterer(PS)points.Thus,the density and position of PS points are critical for PSI.To increase the PS density,a time-series InSAR chain termed as"super-resolution persistent scatterer interferometry"(SR-PSI)is proposed.In this study,we investigate certain important properties of SR-PSI.First,we review the main workflow and dataflow of SR-PSI.It is shown that in the implementation of the Capon algorithm,the diagonal loading(DL)approach should be only used when the condition number of the covariance matrix is sufficiently high to reduce the discontinuities between the joint images.We then discuss the density and positioning accuracy of PS when compared with traditional PSI.The theory and experimental results indicate that SR-PSI can increase the PS density in urban areas.However,it is ineffective for the rural areas,which should be an important consideration for the engineering application of SR-PSI.Furthermore,we validate that the positioning accuracy of PS can be improved by SRPSI via simulations.

A new near-field phase-correction method for superlens

A new phase-correction method in a realistic loss superlens imaging system is theoretically predicted. The image resolution is enhanced using the near-field active phase-correction method. Resolvable separation between two slits has been significantly improved to λ/20 for the symmetrical superlens system and λ/12 for unsymmetrical system.

Asymmetric Loss Based on Image Properties for Deep Learning-Based Image Restoration

Deep learning techniques have significantly improved image restoration tasks in recent years.As a crucial compo-nent of deep learning,the loss function plays a key role in network optimization and performance enhancement.However,the currently prevalent loss functions assign equal weight to each pixel point during loss calculation,which hampers the ability to reflect the roles of different pixel points and fails to exploit the image’s characteristics fully.To address this issue,this study proposes an asymmetric loss function based on the image and data characteristics of the image recovery task.This novel loss function can adjust the weight of the reconstruction loss based on the grey value of different pixel points,thereby effectively optimizing the network training by differentially utilizing the grey information from the original image.Specifically,we calculate a weight factor for each pixel point based on its grey value and combine it with the reconstruction loss to create a new loss function.This ensures that pixel points with smaller grey values receive greater attention,improving network recovery.In order to verify the effectiveness of the proposed asymmetric loss function,we conducted experimental tests in the image super-resolution task.The experimental results show that the model with the introduction of asymmetric loss weights improves all the indexes of the processing results without increasing the training time.In the typical super-resolution network SRCNN,by introducing asymmetric weights,it is possible to improve the peak signal-to-noise ratio(PSNR)by up to about 0.5%,the structural similarity index(SSIM)by up to about 0.3%,and reduce the root-mean-square error(RMSE)by up to about 1.7%with essentially no increase in training time.In addition,we also further tested the performance of the proposed method in the denoising task to verify the potential applicability of the method in the image restoration task.

Hawk‐eye‐inspired perception algorithm of stereo vision for obtaining orchard 3D point cloud navigation map

The binocular stereo vision is the lowest cost sensor for obtaining 3D information.Considering the weakness of long‐distance measurement and stability,the improvement of accuracy and stability of stereo vision is urgently required for application of precision agriculture.To address the challenges of stereo vision long‐distance measurement and stable perception without hardware upgrade,inspired by hawk eyes,higher resolution perception and the adaptive HDR(High Dynamic Range)were introduced in this paper.Simulating the function from physiological structure of‘deep fovea’and‘shallow fovea’of hawk eye,the higher resolution reconstruction method in this paper was aimed at ac-curacy improving.Inspired by adjustment of pupils,the adaptive HDR method was proposed for high dynamic range optimisation and stable perception.In various light conditions,compared with default stereo vision,the accuracy of proposed algorithm was improved by 28.0%evaluated by error ratio,and the stability was improved by 26.56%by disparity accuracy.For fixed distance measurement,the maximum improvement was 78.6%by standard deviation.Based on the hawk‐eye‐inspired perception algorithm,the point cloud of orchard was improved both in quality and quantity.The hawk‐eye‐inspired perception algorithm contributed great advance in binocular 3D point cloud recon-struction in orchard navigation map.

Reference Image Guided Super-Resolution via Progressive Channel Attention Networks

In recent years,the convolutional neural networks(CNNs)for single image super-resolution(SISR)are becoming more and more complex,and it is more challenging to improve the SISR performance.In contrast,the reference image guided super-resolution(RefSR)is an effective strategy to boost the SR(super-resolution)performance.In RefSR,the introduced high-resolution(HR)references can facilitate the high-frequency residual prediction process.According to the best of our knowledge,the existing CNN-based RefSR methods treat the features from the references and the low-resolution(LR)input equally by simply concatenating them together.However,the HR references and the LR inputs contribute differently to the final SR results.Therefore,we propose a progressive channel attention network(PCANet)for RefSR.There are two technical contributions in this paper.First,we propose a novel channel attention module(CAM),which estimates the channel weighting parameter by weightedly averaging the spatial features instead of using global averaging.Second,considering that the residual prediction process can be improved when the LR input is enriched with more details,we perform super-resolution progressively,which can take advantage of the reference images in multi-scales.Extensive quantitative and qualitative evaluations on three benchmark datasets,which represent three typical scenarios for RefSR,demonstrate that our method is superior to the state-of-the-art SISR and RefSR methods in terms of PSNR(Peak Signal-to-Noise Ratio)and SSIM(Structural Similarity).