PSMFNet:Lightweight Partial Separation and Multiscale Fusion Network for Image Super-Resolution

The employment of deep convolutional neural networks has recently contributed to significant progress in single image super-resolution(SISR)research.However,the high computational demands of most SR techniques hinder their applicability to edge devices,despite their satisfactory reconstruction performance.These methods commonly use standard convolutions,which increase the convolutional operation cost of the model.In this paper,a lightweight Partial Separation and Multiscale Fusion Network(PSMFNet)is proposed to alleviate this problem.Specifically,this paper introduces partial convolution(PConv),which reduces the redundant convolution operations throughout the model by separating some of the features of an image while retaining features useful for image reconstruction.Additionally,it is worth noting that the existing methods have not fully utilized the rich feature information,leading to information loss,which reduces the ability to learn feature representations.Inspired by self-attention,this paper develops a multiscale feature fusion block(MFFB),which can better utilize the non-local features of an image.MFFB can learn long-range dependencies from the spatial dimension and extract features from the channel dimension,thereby obtaining more comprehensive and rich feature information.As the role of the MFFB is to capture rich global features,this paper further introduces an efficient inverted residual block(EIRB)to supplement the local feature extraction ability of PSMFNet.A comprehensive analysis of the experimental results shows that PSMFNet maintains a better performance with fewer parameters than the state-of-the-art models.

Multi-prior physics-enhanced neural network enables pixel super-resolution and twin-imagefree phase retrieval from single-shot hologram

Digital in-line holographic microscopy(DIHM)is a widely used interference technique for real-time reconstruction of living cells’morphological information with large space-bandwidth product and compact setup.However,the need for a larger pixel size of detector to improve imaging photosensitivity,field-of-view,and signal-to-noise ratio often leads to the loss of sub-pixel information and limited pixel resolution.Additionally,the twin-image appearing in the reconstruction severely degrades the quality of the reconstructed image.The deep learning(DL)approach has emerged as a powerful tool for phase retrieval in DIHM,effectively addressing these challenges.However,most DL-based strategies are datadriven or end-to-end net approaches,suffering from excessive data dependency and limited generalization ability.Herein,a novel multi-prior physics-enhanced neural network with pixel super-resolution(MPPN-PSR)for phase retrieval of DIHM is proposed.It encapsulates the physical model prior,sparsity prior and deep image prior in an untrained deep neural network.The effectiveness and feasibility of MPPN-PSR are demonstrated by comparing it with other traditional and learning-based phase retrieval methods.With the capabilities of pixel super-resolution,twin-image elimination and high-throughput jointly from a single-shot intensity measurement,the proposed DIHM approach is expected to be widely adopted in biomedical workflow and industrial measurement.

Hyperspectral Image Super-Resolution Meets Deep Learning:A Survey and Perspective

Hyperspectral image super-resolution,which refers to reconstructing the high-resolution hyperspectral image from the input low-resolution observation,aims to improve the spatial resolution of the hyperspectral image,which is beneficial for subsequent applications.The development of deep learning has promoted significant progress in hyperspectral image super-resolution,and the powerful expression capabilities of deep neural networks make the predicted results more reliable.Recently,several latest deep learning technologies have made the hyperspectral image super-resolution method explode.However,a comprehensive review and analysis of the latest deep learning methods from the hyperspectral image super-resolution perspective is absent.To this end,in this survey,we first introduce the concept of hyperspectral image super-resolution and classify the methods from the perspectives with or without auxiliary information.Then,we review the learning-based methods in three categories,including single hyperspectral image super-resolution,panchromatic-based hyperspectral image super-resolution,and multispectral-based hyperspectral image super-resolution.Subsequently,we summarize the commonly used hyperspectral dataset,and the evaluations for some representative methods in three categories are performed qualitatively and quantitatively.Moreover,we briefly introduce several typical applications of hyperspectral image super-resolution,including ground object classification,urban change detection,and ecosystem monitoring.Finally,we provide the conclusion and challenges in existing learning-based methods,looking forward to potential future research directions.

IRMIRS:Inception-ResNet-Based Network for MRI Image Super-Resolution

Medical image super-resolution is a fundamental challenge due to absorption and scattering in tissues.These challenges are increasing the interest in the quality of medical images.Recent research has proven that the rapid progress in convolutional neural networks(CNNs)has achieved superior performance in the area of medical image super-resolution.However,the traditional CNN approaches use interpolation techniques as a preprocessing stage to enlarge low-resolution magnetic resonance(MR)images,adding extra noise in the models and more memory consumption.Furthermore,conventional deep CNN approaches used layers in series-wise connection to create the deeper mode,because this later end layer cannot receive complete information and work as a dead layer.In this paper,we propose Inception-ResNet-based Network for MRI Image Super-Resolution known as IRMRIS.In our proposed approach,a bicubic interpolation is replaced with a deconvolution layer to learn the upsampling filters.Furthermore,a residual skip connection with the Inception block is used to reconstruct a high-resolution output image from a low-quality input image.Quantitative and qualitative evaluations of the proposed method are supported through extensive experiments in reconstructing sharper and clean texture details as compared to the state-of-the-art methods.

A modified OMP method for multi-orbit three dimensional ISAR imaging of the space target

The conventional two dimensional(2D)inverse synthetic aperture radar(ISAR)imaging fails to provide the targets'three dimensional(3D)information.In this paper,a 3D ISAR imaging method for the space target is proposed based on mutliorbit observation data and an improved orthogonal matching pursuit(OMP)algorithm.Firstly,the 3D scattered field data is converted into a set of 2D matrix by stacking slices of the 3D data along the elevation direction dimension.Then,an improved OMP algorithm is applied to recover the space target's amplitude information via the 2D matrix data.Finally,scattering centers can be reconstructed with specific three dimensional locations.Numerical simulations are provided to demonstrate the effectiveness and superiority of the proposed 3D imaging method.

Super-Resolution Imaging of Mammograms Based on the Super-Resolution Convolutional Neural Network

Purpose: To apply and evaluate a super-resolution scheme based on the super-resolution convolutional neural network (SRCNN) for enhancing image resolution in digital mammograms. Materials and Methods: A total of 711 mediolateral oblique (MLO) images including breast lesions were sampled from the Curated Breast Imaging Subset of the Digital Database for Screening Mammography (CBIS-DDSM). We first trained the super-resolution convolutional neural network (SRCNN), which is a deep-learning based super-resolution method. Using this trained SRCNN, high-resolution images were reconstructed from low-resolution images. We compared the image quality of the super-resolution method and that obtained using the linear interpolation methods (nearest neighbor and bilinear interpolations). To investigate the relationship between the image quality of the SRCNN-processed images and the clinical features of the mammographic lesions, we compared the image quality yielded by implementing the SRCNN, in terms of the breast density, the Breast Imaging-Reporting and Data System (BI-RADS) assessment, and the verified pathology information. For quantitative evaluation, peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) were measured to assess the image restoration quality and the perceived image quality. Results: The super-resolution image quality yielded by the SRCNN was significantly higher than that obtained using linear interpolation methods (p p Conclusion: SRCNN can significantly outperform conventional interpolation methods for enhancing image resolution in digital mammography. SRCNN can significantly improve the image quality of magnified mammograms, especially in dense breasts, high-risk BI-RADS assessment groups, and pathology-verified malignant cases.

Polarimetric super-resolution algorithm for radar range imaging via spatial smoothing processing

A full-polarimetric super-resolution algorithm with spatial smoothing processing is presented for one-dimensional（1-D）radar imaging.The coherence between scattering centers is minimized by using spatial smoothing processing（SSP）.Then the range and polarimetric scattering matrix of the scattering centers are estimated.The impact of different lengths of the smoothing window on the imaging quality is mainly analyzed with different signal-to-noise ratios（SNR）.Simulation and experimental results show that an improved radar super-resolution range profile and more precise estimation can be obtained by adjusting the length of the smoothing window under different SNR conditions.

Near-field multiple super-resolution imaging from Mikaelian lens to generalized Maxwell's fish-eye lens

Super-resolution imaging is vital for optical applications, such as high capacity information transmission, real-time bio-molecular imaging, and nanolithography. In recent years, technologies and methods of super-resolution imaging have attracted much attention. Different kinds of novel lenses, from the superlens to the super-oscillatory lens, have been designed and fabricated to break through the diffraction limit. However, the effect of the super-resolution imaging in these lenses is not satisfactory due to intrinsic loss, aberration, large sidebands, and so on. Moreover, these lenses also cannot realize multiple super-resolution imaging. In this research, we introduce the solid immersion mechanism to Mikaelian lens(ML) for multiple super-resolution imaging. The effect is robust and valid for broadband frequencies. Based on conformal transformation optics as a bridge linking the solid immersion ML and generalized Maxwell's fish-eye lens(GMFEL), we also discovered the effect of multiple super-resolution imaging in the solid immersion GMFEL.

Super-resolution imaging in glycoscience: New developments and challenges

Carbohydrates on cell surfaces play a crucial role in a wide variety of biological processes,including cell adhesion,recognition and signaling,viral and bacterial infection,in°ammation and metastasis.However,owing to the large diversity and complexity of carbohydrate structure and nongenetically synthesis,glycoscience is the least understood¯eld compared with genomics and proteomics.Although the structures and functions of carbohydrates have been investigated by various conventional analysis methods,the distribution and role of carbohydrates in cell membranes remain elusive.This review focuses on the developments and challenges of super-resolution imaging in glycoscience through introduction of imaging principle and the available°uorescent probes for super-resolution imaging,the labeling strategies of carbohydrates,and the recent applications of super-resolution imaging in glycoscience,which will promote the super-resolution imaging technology as a promising tool to provide new insights into the study of glycoscience.

基于特征提取的ISAR成像欺骗干扰评估方法研究

雷达成像欺骗干扰是雷达对抗装备的一种重要干扰手段,在弹载、机载等多种武器平台上具有广泛应用。在分析ISAR成像欺骗干扰技术的基础上,研究了ISAR图像特性的提取方法,提出了一种基于ISAR图像特征提取的雷达成像欺骗干扰效果评估方法,解决了雷达对抗装备成像欺骗干扰能力评估难题,可为相关雷达干扰对抗试验及评估等提供参考。

Contrastive Learning for Blind Super-Resolution via A Distortion-Specific Network

Previous deep learning-based super-resolution(SR)methods rely on the assumption that the degradation process is predefined(e.g.,bicubic downsampling).Thus,their performance would suffer from deterioration if the real degradation is not consistent with the assumption.To deal with real-world scenarios,existing blind SR methods are committed to estimating both the degradation and the super-resolved image with an extra loss or iterative scheme.However,degradation estimation that requires more computation would result in limited SR performance due to the accumulated estimation errors.In this paper,we propose a contrastive regularization built upon contrastive learning to exploit both the information of blurry images and clear images as negative and positive samples,respectively.Contrastive regularization ensures that the restored image is pulled closer to the clear image and pushed far away from the blurry image in the representation space.Furthermore,instead of estimating the degradation,we extract global statistical prior information to capture the character of the distortion.Considering the coupling between the degradation and the low-resolution image,we embed the global prior into the distortion-specific SR network to make our method adaptive to the changes of distortions.We term our distortion-specific network with contrastive regularization as CRDNet.The extensive experiments on synthetic and realworld scenes demonstrate that our lightweight CRDNet surpasses state-of-the-art blind super-resolution approaches.

A fast decoupled ISAR high-resolution imaging method using structural sparse information under low SNR

Inverse synthetic aperture radar (ISAR) image can be represented and reconstructed by sparse recovery (SR) approaches. However, the existing SR algorithms, which are used for ISAR imaging, have suffered from high computational cost and poor imaging quality under a low signal to noise ratio (SNR) condition. This paper proposes a fast decoupled ISAR imaging method by exploiting the inherent structural sparse information of the targets. Firstly, the ISAR imaging problem is decoupled into two sub-problems. One is range direction imaging and the other is azimuth direction focusing. Secondly, an efficient two-stage SR method is proposed to obtain higher resolution range profiles by using jointly sparse information. Finally, the residual linear Bregman iteration via fast Fourier transforms (RLBI-FFT) is proposed to perform the azimuth focusing on low SNR efficiently. Theoretical analysis and simulation results show that the proposed method has better performence to efficiently implement higher-resolution ISAR imaging under the low SNR condition.

Research on spatial-variant property of bistatic ISAR imaging plane of space target

The imaging plane of inverse synthetic aperture radar （ISAR） is the projection plane of the target. When taking an image using the range-Doppler theory, the imaging plane may have a spatial-variant property, which causes the change of scatter＇s projection position and results in migration through resolution cells, In this study, we focus on the spatial-variant property of the imaging plane of a three-axis-stabilized space target. The innovative contributions are as follows. 1） The target motion model in orbit is provided based on a two-body model. 2） The instantaneous imaging plane is determined by the method of vector analysis. 3） Three Euler angles are introduced to describe the spatial-variant property of the imaging plane, and the image quality is analyzed. The simulation results confirm the analysis of the spatial-variant property. The research in this study is significant for the selection of the imaging segment, and provides the evidence for the following data processing and compensation algorithm.

ISAR imaging based on improved phase retrieval algorithm

Traditional inverse synthetic aperture radar(ISAR)imaging methods for maneuvering targets have low resolution and poor capability of noise suppression. An ISAR imaging method of maneuvering targets based on phase retrieval is proposed,which can provide a high-resolution and focused map of the spatial distribution of scatterers on the target. According to theoretical derivation, the modulus of raw data from the maneuvering target is not affected by radial motion components for ISAR imaging system, so the phase retrieval algorithm can be used for ISAR imaging problems. However, the traditional phase retrieval algorithm will be not applicable to ISAR imaging under the condition of random noise. To solve this problem, an algorithm is put forward based on the range Doppler(RD) algorithm and oversampling smoothness(OSS) phase retrieval algorithm. The algorithm captures the target information in order to reduce the influence of the random phase on ISAR echoes, and then applies OSS for focusing imaging based on prior information of the RD algorithm. The simulated results demonstrate the validity of this algorithm, which cannot only obtain high resolution imaging for high speed maneuvering targets under the condition of random noise, but also substantially improve the success rate of the phase retrieval algorithm.

某型舰载机目标的ISAR成像算法研究

逆合成孔径雷达(ISAR)成像技术因其能够提供目标的高分辨率二维图像,已经成为军事侦察、地球观测和灾害监测等领域的重要工具,但是,由于目标的复杂运动,传统的ISAR成像方法往往会出现图像模糊和失真的问题。距离多普勒(RD)算法通过对雷达回波数据进行二维傅里叶变换,可以有效地抑制目标的复杂运动对ISAR图像的影响,从而获得更清晰、更精确的图像,然而,在处理目标加速度和微动方面存在局限性。文中首先说明了ISAR的成像原理,介绍了运动补偿中的包络对齐,在此基础上,提出一种改进的包络对齐方法,通过某卫星成像对该算法进行验证,证明了该方法的适用性和灵活性,运用改进的包络对齐方法对某型舰载机成像,发现该方法可以有效地提高ISAR图像的质量和分辨率。

A probability theory for filtered ghost imaging

Based on probability density functions,we present a theoretical model to explain filtered ghost imaging(FGI)we first proposed and experimentally demonstrated in 2017[Opt.Lett.425290(2017)].An analytic expression for the joint intensity probability density functions of filtered random speckle fields is derived according to their probability distributions.Moreover,the normalized second-order intensity correlation functions are calculated for the three cases of low-pass,bandpass and high-pass filterings to study the resolution and visibility in the FGI system.Numerical simulations show that the resolution and visibility predicted by our model agree well with the experimental results,which also explains why FGI can achieve a super-resolution image and better visibility than traditional ghost imaging.

Deep-learning-based methods for super-resolution fluorescence microscopy

The algorithm used for reconstruction or resolution enhancement is one of the factors affectingthe quality of super-resolution images obtained by fluorescence microscopy.Deep-learning-basedalgorithms have achieved stateof-the-art performance in super-resolution fluorescence micros-copy and are becoming increasingly attractive.We firstly introduce commonly-used deep learningmodels,and then review the latest applications in terms of the net work architectures,the trainingdata and the loss functions.Additionally,we discuss the challenges and limits when using deeplearning to analyze the fluorescence microscopic data,and suggest ways to improve the reliability and robustness of deep learning applications.

Super-resolution reconstruction of synthetic-aperture radar image using adaptive-threshold singular value decomposition technique

A super-resolution reconstruction approach of （SVD） technique was presented, and its performance was radar image using an adaptive-threshold singular value decomposition analyzed, compared and assessed detailedly. First, radar imaging model and super-resolution reconstruction mechanism were outlined. Then, the adaptive-threshold SVD super-resolution algorithm, and its two key aspects, namely the determination method of point spread function （PSF） matrix T and the selection scheme of singular value threshold, were presented. Finally, the super-resolution algorithm was demonstrated successfully using the measured synthetic-aperture radar （SAR） images, and a Monte Carlo assessment was carried out to evaluate the performance of the algorithm by using the input/output signal-to-noise ratio （SNR）. Five versions of SVD algorithms, namely 1 ） using all singular values, 2） using the top 80% singular values, 3） using the top 50% singular values, 4） using the top 20% singular values and 5） using singular values s such that S2≥/max（s2）/rinsNR were tested. The experimental results indicate that when the singular value threshold is set as Smax/（rinSNR）1/2, the super-resolution algorithm provides a good compromise between too much noise and too much bias and has good reconstruction results.

Image Super-Resolution Based on Generative Adversarial Networks: A Brief Review

Single image super resolution(SISR)is an important research content in the field of computer vision and image processing.With the rapid development of deep neural networks,different image super-resolution models have emerged.Compared to some traditional SISR methods,deep learning-based methods can complete the super-resolution tasks through a single image.In addition,compared with the SISR methods using traditional convolutional neural networks,SISR based on generative adversarial networks(GAN)has achieved the most advanced visual performance.In this review,we first explore the challenges faced by SISR and introduce some common datasets and evaluation metrics.Then,we review the improved network structures and loss functions of GAN-based perceptual SISR.Subsequently,the advantages and disadvantages of different networks are analyzed by multiple comparative experiments.Finally,we summarize the paper and look forward to the future development trends of GAN-based perceptual SISR.

Single color image super-resolution using sparse representation and color constraint

Color image super-resolution reconstruction based on the sparse representation model usually adopts the regularization norm(e.g.,L1 or L2).These methods have limited ability to keep image texture detail to some extent and are easy to cause the problem of blurring details and color artifacts in color reconstructed images.This paper presents a color super-resolution reconstruction method combining the L2/3 sparse regularization model with color channel constraints.The method converts the low-resolution color image from RGB to YCbCr.The L2/3 sparse regularization model is designed to reconstruct the brightness channel of the input low-resolution color image.Then the color channel-constraint method is adopted to remove artifacts of the reconstructed highresolution image.The method not only ensures the reconstruction quality of the color image details,but also improves the removal ability of color artifacts.The experimental results on natural images validate that our method has improved both subjective and objective evaluation.