Pyramid Separable Channel Attention Network for Single Image Super-Resolution

Single Image Super-Resolution(SISR)technology aims to reconstruct a clear,high-resolution image with more information from an input low-resolution image that is blurry and contains less information.This technology has significant research value and is widely used in fields such as medical imaging,satellite image processing,and security surveillance.Despite significant progress in existing research,challenges remain in reconstructing clear and complex texture details,with issues such as edge blurring and artifacts still present.The visual perception effect still needs further enhancement.Therefore,this study proposes a Pyramid Separable Channel Attention Network(PSCAN)for the SISR task.Thismethod designs a convolutional backbone network composed of Pyramid Separable Channel Attention blocks to effectively extract and fuse multi-scale features.This expands the model’s receptive field,reduces resolution loss,and enhances the model’s ability to reconstruct texture details.Additionally,an innovative artifact loss function is designed to better distinguish between artifacts and real edge details,reducing artifacts in the reconstructed images.We conducted comprehensive ablation and comparative experiments on the Arabidopsis root image dataset and several public datasets.The experimental results show that the proposed PSCAN method achieves the best-known performance in both subjective visual effects and objective evaluation metrics,with improvements of 0.84 in Peak Signal-to-Noise Ratio(PSNR)and 0.017 in Structural Similarity Index(SSIM).This demonstrates that the method can effectively preserve high-frequency texture details,reduce artifacts,and have good generalization performance.

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.

Research on single image super-resolution based on very deep super-resolution convolutional neural network

Single image super-resolution(SISR)is a fundamentally challenging problem because a low-resolution(LR)image can correspond to a set of high-resolution(HR)images,while most are not expected.Recently,SISR can be achieved by a deep learning-based method.By constructing a very deep super-resolution convolutional neural network(VDSRCNN),the LR images can be improved to HR images.This study mainly achieves two objectives:image super-resolution(ISR)and deblurring the image from VDSRCNN.Firstly,by analyzing ISR,we modify different training parameters to test the performance of VDSRCNN.Secondly,we add the motion blurred images to the training set to optimize the performance of VDSRCNN.Finally,we use image quality indexes to evaluate the difference between the images from classical methods and VDSRCNN.The results indicate that the VDSRCNN performs better in generating HR images from LR images using the optimized VDSRCNN in a proper method.

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.

Fast image super-resolution algorithm based on multi-resolution dictionary learning and sparse representation

Sparse representation has attracted extensive attention and performed well on image super-resolution（SR） in the last decade. However, many current image SR methods face the contradiction of detail recovery and artifact suppression. We propose a multi-resolution dictionary learning（MRDL） model to solve this contradiction, and give a fast single image SR method based on the MRDL model. To obtain the MRDL model, we first extract multi-scale patches by using our proposed adaptive patch partition method（APPM）. The APPM divides images into patches of different sizes according to their detail richness. Then, the multiresolution dictionary pairs, which contain structural primitives of various resolutions, can be trained from these multi-scale patches.Owing to the MRDL strategy, our SR algorithm not only recovers details well, with less jag and noise, but also significantly improves the computational efficiency. Experimental results validate that our algorithm performs better than other SR methods in evaluation metrics and visual perception.

Better Visual Image Super-Resolution with Laplacian Pyramid of Generative Adversarial Networks

Although there has been a great breakthrough in the accuracy and speed of super-resolution(SR)reconstruction of a single image by using a convolutional neural network,an important problem remains unresolved:how to restore finer texture details during image super-resolution reconstruction?This paper proposes an Enhanced Laplacian Pyramid Generative Adversarial Network(ELSRGAN),based on the Laplacian pyramid to capture the high-frequency details of the image.By combining Laplacian pyramids and generative adversarial networks,progressive reconstruction of super-resolution images can be made,making model applications more flexible.In order to solve the problem of gradient disappearance,we introduce the Residual-in-Residual Dense Block(RRDB)as the basic network unit.Network capacity benefits more from dense connections,is able to capture more visual features with better reconstruction effects,and removes BN layers to increase calculation speed and reduce calculation complexity.In addition,a loss of content driven by perceived similarity is used instead of content loss driven by spatial similarity,thereby enhancing the visual effect of the super-resolution image,making it more consistent with human visual perception.Extensive qualitative and quantitative evaluation of the baseline datasets shows that the proposed algorithm has higher mean-sort-score(MSS)than any state-of-the-art method and has better visual perception.

Adaptive deep residual network for single image super-resolution

In recent years,deep learning has achieved great success in the field of image processing.In the single image super-resolution(SISR)task,the convolutional neural network(CNN)extracts the features of the image through deeper layers,and has achieved impressive results.In this paper,we propose a single image super-resolution model based on Adaptive Deep Residual named as ADR-SR,which uses the Input Output Same Size(IOSS)structure,and releases the dependence of upsampling layers compared with the existing SR methods.Specifically,the key element of our model is the Adaptive Residual Block(ARB),which replaces the commonly used constant factor with an adaptive residual factor.The experiments prove the effectiveness of our ADR-SR model,which can not only reconstruct images with better visual effects,but also get better objective performances.

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.

Single-Molecule Fluorescence Imaging of Nanocatalysis

Single-molecule fluorescence microscopy(SMFM)has been considered as a powerful tool to study nanocatalysis of single nanoparticles,due to its single-molecule sensitivity and high spatiotemporal resolution.In this review,we discuss recent progresses on investigating nanocatalysis at single-mol-ecule/particle level by using SMFM.The discussion focuses on the applications of single-molecule methods in probing the chemocatalysis,electrocatalysis,photocatalysis and photoelectrocatalysis.Finally,we provide our opinions on limitations and prospects of the single-molecule fluorescence approach for investigating nanocatalysis.

SRResNet Performance Enhancement Using Patch Inputs and Partial Convolution-Based Padding

Due to highly underdetermined nature of Single Image Super-Resolution(SISR)problem,deep learning neural networks are required to be more deeper to solve the problem effectively.One of deep neural networks successful in the Super-Resolution(SR)problem is ResNet which can render the capability of deeper networks with the help of skip connections.However,zero padding(ZP)scheme in the network restricts benefits of skip connections in SRResNet and its performance as the ratio of the number of pure input data to that of zero padded data increases.In this paper.we consider the ResNet with Partial Convolution based Padding(PCP)instead of ZP to solve SR problem.Since training of deep neural networks using patch images is advantageous in many aspects such as the number of training image data and network complexities,patch image based SR performance is compared with single full image based one.The experimental results show that patch based SRResNet SR results are better than single full image based ones and the performance of deep SRResNet with PCP is better than the one with ZP.

基于深度学习的单幅图片超分辨率重构研究进展

图像超分辨率重构技术是一种以一幅或同一场景中的多幅低分辨率图像为输入,结合图像的先验知识重构出一幅高分辨率图像的技术.这一技术能够在不改变现有硬件设备的前提下,有效提高图像分辨率.深度学习近年来在图像领域发展迅猛,它的引入为单幅图片超分辨率重构带来了新的发展前景.本文主要对当前基于深度学习的单幅图片超分辨率重构方法的研究现状和发展趋势进行总结梳理:首先根据不同的网络基础对十几种基于深度学习的单幅图片超分辨率重构的网络模型进行分类介绍,分析这些模型在网络结构、输入信息、损失函数、放大因子以及评价指标等方面的差异;然后给出它们的实验结果,并对实验结果及存在的问题进行总结与分析;最后给出基于深度学习的单幅图片超分辨率重构方法的未来发展方向和存在的挑战.

基于深度学习的单幅图像超分辨率重建方法研究

为了解决基于单幅图像自适应稠密连接超分辨率(ADCSR)算法中的残差单元的融合问题,本文提出了一种基于行稀疏约束l_(0,2)-范数和soft-max运算的新策略.根据ADCSR算法,本文算法分为两部分:BODY和SKIP,前者专注图像的高频特征学习,后者专注低频特征学习.BODY部分中所有自适应密集残差单元(ADRU)的输出,作为初始特征图,可用特征数目l_(0,2)-范数作为活动水平度量,然后利用基于块的平均算子计算最终活动水平图,最后利用soft-max得到融合后特征映射,改进了原ADCSR算法中卷积融合粗糙的缺点,保留了更多的结构信息和特征.此外特征数目l_(0,2)-范数作为字典原子更加精确地获取更高的权重,获得了更优的峰值信噪比PSNR、结构相似性SSIM和视觉效果,计算机实验证明了本文算法的有效性.

基于稀疏贝叶斯估计的单图像超分辨率算法

针对现有超分辨率方法对不同低分辨率图像的超分辨率效果差异较大的问题,提出了一种基于稀疏贝叶斯估计的单图像超分辨率方法。该方法将单图像超分辨率问题看做是回归问题,采用Kronecker脉冲函数作为回归基函数,综合利用图像的局部信息和全局信息寻找特定预测的最优稀疏解决方案,采用贝叶斯方法估计权重,据此重构超分辨率图像。实验结果表明,采用该方法对14幅测试图像运行单图像超分辨率算法,得到的平均峰值信噪比高、方差小、耗时少,证实了该方法的超分辨率效果好、适应性强,且运算效率高。

基于深度学习的单图像超分辨率重建研究综述

为深入了解基于深度学习的单图像超分辨率重建(SISR)的发展,把握当前研究的热点和方向,针对现有基于深度学习的单图像超分辨率重建模型进行了梳理。介绍了相关深度学习算法和基于深度学习的模型以及评价指标,并通过实验对比分析现有模型的性能,其目的在于从本质上了解基于深度学习的单图像超分辨率重建模型的优势;对单图像超分辨率重建的关键问题进行了总结,并对未来的发展趋势进行了展望。

基于改进CycleGAN的视频监控人脸超分辨率恢复算法

针对有监督超分辨率算法训练过程需要大量成对图像、处理真实低分辨率图像视觉恢复效果差等问题,提出了一种基于改进CycleGAN的半监督算法Cycle-SRNet。首先,利用退化模型获得与真实低分辨率人脸相似的图像,用于训练网络参数;其次,通过重建模型恢复出具有真实效果的高分辨率人脸图像;最后引入感知损失函数保持人脸结构相似性,以更好地恢复面部特征。实验结果表明,该算法不需要成对的图像进行网络训练,在视觉效果上能够将模糊的视频监控低分辨率人脸图像恢复成清晰可辨的人脸图像,在FID、PSNR和SSIM指标上超越了SRCNN、SRGAN、CinCGAN等方法。

Optical super-resolution microscopy and its applications in nano-catalysis

The resolution of conventional optical microscopy is only -200 nm, which is becoming less and less sufficient for a variety of applications. In order to surpass the diffraction limited resolution, super-resolution microscopy （SRM） has been developed to achieve a high resolution of one to tens of nanometers. The techniques involved in SRM can be assigned into two broad categories, namely ＂true＂ super-resolution techniques and ＂functional＂ super-resolution techniques. In ＂functional＂ super-resolution techniques, stochastic super-resolution microscopy （SSRM） is widely used due to its low expense, simple operation, and high resolution. The principle process in SSRM is to accumulate the coordinates of many diffraction-limited emitters （e.g., single fluorescent molecules） on the object by localizing the centroids of the point spread functions （PSF）, and then reconstruct the image of the object using these coordinates. When the diffraction-limited emitters take part in a catalytic reaction, the activity distribution and kinetic information about the catalysis by nanoparticles can be obtained by SSRM. SSRM has been applied and exhibited outstanding advantages in several fields of catalysis, such as metal nanoparticle catalysis, molecular sieve catalysis, and photocatalysis. Since SSRM is able to resolve the catalytic activity within one nanoparticle, it promises to accelerate the development and discovery of new and better catalysts. This review will present a brief introduction to SRM, and a detailed description of SSRM and its applications in nano-catalysis.

基于深度学习的单幅图像超分辨率重建算法综述

单幅图像超分辨率(Single image super-resolution,SISR)重建是计算机视觉领域上的一个重要问题,在安防视频监控、飞机航拍以及卫星遥感等方面具有重要的研究意义和应用价值.近年来,深度学习在图像分类、检测、识别等诸多领域中取得了突破性进展,也推动着图像超分辨率重建技术的发展.本文首先介绍单幅图像超分辨率重建的常用公共图像数据集;然后,重点阐述基于深度学习的单幅图像超分辨率重建方向的创新与进展;最后,讨论了单幅图像超分辨率重建方向上存在的困难和挑战,并对未来的发展趋势进行了思考与展望.

基于稀疏神经网络的图像超分辨率重建算法

部分基于深度学习的图像超分辨率重建算法通过扩展网络层的深度来提高网络模型的整体特征表达能力。然而,一味过度地扩展网络的深度会造成网络模型过参数化和复杂化,并且冗余的网络参数会增加特征表达的不稳定性。在LTH剪枝算法基础上改变权重参数并使用均衡学习策略,提出一种适用于图像超分辨率重建任务的神经网络非结构化剪枝算法RLTH。在不改变网络结构和不增加计算复杂度的前提下,通过搜索原始网络模型的最优稀疏子网络排除冗余参数带来的影响,在有限的参数资源中捕获更细粒度和丰富的图像特征,进而提高网络模型的整体特征表达能力。基于Set5、Set14和BSD100测试集的实验结果表明,与原始网络模型和应用LTH剪枝算法相比,应用RLTH算法获得的重建图像PSNR和SSIM均得到提升,且具有更丰富的细节特征,整体和局部轮廓更清晰。

Color centers in wide-bandgap semiconductors for subdiffraction imaging:a review

Solid-state atomic-sized color centers in wide-band-gap semiconductors,such as diamond,silicon carbide,and hexagonal boron nitride,are important platforms for quantum technologies,specifically for single-photon sources and quantum sensing.One of the emerging applications of these quantum emitters is subdiffraction imaging.This capability is provided by the specific photophysical properties of color centers,such as high dipole moments,photostability,and a variety of spectral ranges of the emitters with associated optical and microwave control of their quantum states.We review applications of color centers in traditional super-resolution microscopy and quantum imaging methods,and compare relative performance.The current state and perspectives of their applications in biomedical,chemistry,and material science imaging are outlined.

全局注意力门控残差记忆网络的图像超分重建

目的随着深度卷积神经网络的兴起,图像超分重建算法在精度与速度方面均取得长足进展。然而,目前多数超分重建方法需要较深的网络才能取得良好性能,不仅训练难度大,而且到网络末端浅层特征信息容易丢失,难以充分捕获对超分重建起关键作用的高频细节信息。为此,本文融合多尺度特征充分挖掘超分重建所需的高频细节信息,提出了一种全局注意力门控残差记忆网络。方法在网络前端特征提取部分,利用单层卷积提取浅层特征信息。在网络主体非线性映射部分,级联一组递归的残差记忆模块,每个模块融合多个递归的多尺度残差单元和一个全局注意力门控模块来输出具备多层级信息的特征表征。在网络末端,并联多尺度特征并通过像素重组机制实现高质量的图像放大。结果本文分别在图像超分重建的5个基准测试数据集(Set5、Set14、B100、Urban100和Manga109)上进行评估,在评估指标峰值信噪比(peak signal to noise ratio,PSNR)和结构相似性(structural similarity,SSIM)上相比当前先进的网络模型均获得更优性能,尤其在Manga109测试数据集上本文算法取得的PSNR结果达到39.19 dB,相比当前先进的轻量型算法AWSRN(adaptive weighted super-resolution network)提高0.32 dB。结论本文网络模型在对低分图像进行超分重建时,能够联合学习网络多层级、多尺度特征,充分挖掘图像高频信息,获得高质量的重建结果。