Aiming at the problems of image super-resolution algorithm with many convolutional neural networks, such as large parameters, large computational complexity and blurred image texture, we propose a new algorithm model....Aiming at the problems of image super-resolution algorithm with many convolutional neural networks, such as large parameters, large computational complexity and blurred image texture, we propose a new algorithm model. The classical convolutional neural network is improved, the convolution kernel size is adjusted, and the parameters are reduced;the pooling layer is added to reduce the dimension. Reduced computational complexity, increased learning rate, and reduced training time. The iterative back-projection algorithm is combined with the convolutional neural network to create a new algorithm model. The experimental results show that compared with the traditional facial illusion method, the proposed method can obtain better performance.展开更多
Remote sensing image super-resolution technology is pivotal for enhancing image quality in critical applications including environmental monitoring,urban planning,and disaster assessment.However,traditional methods ex...Remote sensing image super-resolution technology is pivotal for enhancing image quality in critical applications including environmental monitoring,urban planning,and disaster assessment.However,traditional methods exhibit deficiencies in detail recovery and noise suppression,particularly when processing complex landscapes(e.g.,forests,farmlands),leading to artifacts and spectral distortions that limit practical utility.To address this,we propose an enhanced Super-Resolution Generative Adversarial Network(SRGAN)framework featuring three key innovations:(1)Replacement of L1/L2 loss with a robust Charbonnier loss to suppress noise while preserving edge details via adaptive gradient balancing;(2)A multi-loss joint optimization strategy dynamically weighting Charbonnier loss(β=0.5),Visual Geometry Group(VGG)perceptual loss(α=1),and adversarial loss(γ=0.1)to synergize pixel-level accuracy and perceptual quality;(3)A multi-scale residual network(MSRN)capturing cross-scale texture features(e.g.,forest canopies,mountain contours).Validated on Sentinel-2(10 m)and SPOT-6/7(2.5 m)datasets covering 904 km2 in Motuo County,Xizang,our method outperforms the SRGAN baseline(SR4RS)with Peak Signal-to-Noise Ratio(PSNR)gains of 0.29 dB and Structural Similarity Index(SSIM)improvements of 3.08%on forest imagery.Visual comparisons confirm enhanced texture continuity despite marginal Learned Perceptual Image Patch Similarity(LPIPS)increases.The method significantly improves noise robustness and edge retention in complex geomorphology,demonstrating 18%faster response in forest fire early warning and providing high-resolution support for agricultural/urban monitoring.Future work will integrate spectral constraints and lightweight architectures.展开更多
The generation of high-quality,realistic face generation has emerged as a key field of research in computer vision.This paper proposes a robust approach that combines a Super-Resolution Generative Adversarial Network(...The generation of high-quality,realistic face generation has emerged as a key field of research in computer vision.This paper proposes a robust approach that combines a Super-Resolution Generative Adversarial Network(SRGAN)with a Pyramid Attention Module(PAM)to enhance the quality of deep face generation.The SRGAN framework is designed to improve the resolution of generated images,addressing common challenges such as blurriness and a lack of intricate details.The Pyramid Attention Module further complements the process by focusing on multi-scale feature extraction,enabling the network to capture finer details and complex facial features more effectively.The proposed method was trained and evaluated over 100 epochs on the CelebA dataset,demonstrating consistent improvements in image quality and a marked decrease in generator and discriminator losses,reflecting the model’s capacity to learn and synthesize high-quality images effectively,given adequate computational resources.Experimental outcome demonstrates that the SRGAN model with PAM module has outperformed,yielding an aggregate discriminator loss of 0.055 for real,0.043 for fake,and a generator loss of 10.58 after training for 100 epochs.The model has yielded an structural similarity index measure of 0.923,that has outperformed the other models that are considered in the current study for analysis.展开更多
Recently, neighbor embedding based face super-resolution(SR) methods have shown the ability for achieving high-quality face images, those methods are based on the assumption that the same neighborhoods are preserved i...Recently, neighbor embedding based face super-resolution(SR) methods have shown the ability for achieving high-quality face images, those methods are based on the assumption that the same neighborhoods are preserved in both low-resolution(LR) training set and high-resolution(HR) training set. However, due to the "one-to-many" mapping between the LR image and HR ones in practice, the neighborhood relationship of the LR patch in LR space is quite different with that of the HR counterpart, that is to say the neighborhood relationship obtained is not true. In this paper, we explore a novel and effective re-identified K-nearest neighbor(RIKNN) method to search neighbors of LR patch. Compared with other methods, our method uses the geometrical information of LR manifold and HR manifold simultaneously. In particular, it searches K-NN of LR patch in the LR space and refines the searching results by re-identifying in the HR space, thus giving rise to accurate K-NN and improved performance. A statistical analysis of the influence of the training set size and nearest neighbor number is given, experimental results on some public face databases show the superiority of our proposed scheme over state-of-the-art face hallucination approaches in terms of subjective and objective results as well as computational complexity.展开更多
The rapid development of super-resolution microscopy has made it possible to observe subcellular structures and dynamic behaviors in living cells with nanoscale spatial resolution, greatly advancing progress in life s...The rapid development of super-resolution microscopy has made it possible to observe subcellular structures and dynamic behaviors in living cells with nanoscale spatial resolution, greatly advancing progress in life sciences. As hardware technology continues to evolve, the availability of new fluorescent probes with superior performance is becoming increasingly important. In recent years, fluorescent nanoprobes (FNPs) have emerged as highly promising fluorescent probes for bioimaging due to their high brightness and excellent photostability. This paper focuses on the development and applications of FNPs as probes for live-cell super-resolution imaging. It provides an overview of different super-resolution methods, discusses the performance requirements for FNPs in these methods, and reviews the latest applications of FNPs in the super-resolution imaging of living cells. Finally, it addresses the challenges and future outlook in this field.展开更多
Image super-resolution reconstruction technology is currently widely used in medical imaging,video surveillance,and industrial quality inspection.It not only enhances image quality but also improves details and visual...Image super-resolution reconstruction technology is currently widely used in medical imaging,video surveillance,and industrial quality inspection.It not only enhances image quality but also improves details and visual perception,significantly increasing the utility of low-resolution images.In this study,an improved image superresolution reconstruction model based on Generative Adversarial Networks(SRGAN)was proposed.This model introduced a channel and spatial attention mechanism(CSAB)in the generator,allowing it to effectively leverage the information from the input image to enhance feature representations and capture important details.The discriminator was designed with an improved PatchGAN architecture,which more accurately captured local details and texture information of the image.With these enhanced generator and discriminator architectures and an optimized loss function design,this method demonstrated superior performance in image quality assessment metrics.Experimental results showed that this model outperforms traditional methods,presenting more detailed and realistic image details in the visual effects.展开更多
Significant advancements have been achieved in the field of Single Image Super-Resolution(SISR)through the utilization of Convolutional Neural Networks(CNNs)to attain state-of-the-art performance.Recent efforts have e...Significant advancements have been achieved in the field of Single Image Super-Resolution(SISR)through the utilization of Convolutional Neural Networks(CNNs)to attain state-of-the-art performance.Recent efforts have explored the incorporation of Transformers to augment network performance in SISR.However,the high computational cost of Transformers makes them less suitable for deployment on lightweight devices.Moreover,the majority of enhancements for CNNs rely predominantly on small spatial convolutions,thereby neglecting the potential advantages of large kernel convolution.In this paper,the authors propose a Multi-Perception Large Kernel convNet(MPLKN)which delves into the exploration of large kernel convolution.Specifically,the authors have architected a Multi-Perception Large Kernel(MPLK)module aimed at extracting multi-scale features and employ a stepwise feature fusion strategy to seamlessly integrate these features.In addition,to enhance the network's capacity for nonlinear spatial information processing,the authors have designed a Spatial-Channel Gated Feed-forward Network(SCGFN)that is capable of adapting to feature interactions across both spatial and channel dimensions.Experimental results demonstrate that MPLKN outperforms other lightweight image super-resolution models while maintaining a minimal number of parameters and FLOPs.展开更多
Recent Super-Resolution(SR)algorithms often suffer from excessive model complexity,high computational costs,and limited flexibility across varying image scales.To address these challenges,we propose DDNet,a dynamic an...Recent Super-Resolution(SR)algorithms often suffer from excessive model complexity,high computational costs,and limited flexibility across varying image scales.To address these challenges,we propose DDNet,a dynamic and lightweight SR framework designed for arbitrary scaling factors.DDNet integrates a residual learning structure with an Adaptively fusion Feature Block(AFB)and a scale-aware upsampling module,effectively reducing parameter overhead while preserving reconstruction quality.Additionally,we introduce DDNetGAN,an enhanced variant that leverages a relativistic Generative Adversarial Network(GAN)to further improve texture realism.To validate the proposed models,we conduct extensive training using the DIV2K and Flickr2K datasets and evaluate performance across standard benchmarks including Set5,Set14,Urban100,Manga109,and BSD100.Our experiments cover both symmetric and asymmetric upscaling factors and incorporate ablation studies to assess key components.Results show that DDNet and DDNetGAN achieve competitive performance compared with mainstream SR algorithms,demonstrating a strong balance between accuracy,efficiency,and flexibility.These findings highlight the potential of our approach for practical real-world super-resolution applications.展开更多
Blood cells are the most integral part of the body,which are made up of erythrocytes,platelets and white blood cells.The examination of subcellular structures and proteins within blood cells at the nanoscale can provi...Blood cells are the most integral part of the body,which are made up of erythrocytes,platelets and white blood cells.The examination of subcellular structures and proteins within blood cells at the nanoscale can provide valuable insights into the health status of an individual,accurate diagnosis,and efficient treatment strategies for diseases.Super-resolution microscopy(SRM)has recently emerged as a cutting-edge tool for the study of blood cells,providing numerous advantages over traditional methods for examining subcellular structures and proteins.In this paper,we focus on outlining the fundamental principles of various SRM techniques and their applications in both normal and diseased states of blood cells.Furthermore,future prospects of SRM techniques in the analysis of blood cells are also discussed.展开更多
A new scheme of super-resolution optical fluctuation imaging(SOFI)is proposed to broaden its application in the high-order cumulant reconstruction by optimizing blinking characteristics,eliminating noise in raw data a...A new scheme of super-resolution optical fluctuation imaging(SOFI)is proposed to broaden its application in the high-order cumulant reconstruction by optimizing blinking characteristics,eliminating noise in raw data and applying multi-resolution analysis in cumulant reconstruction.A motor-driven rotating mask optical modulation system is designed to adjust the excitation lightfield and allows for fast deployment.Active-modulated fluorescence fluctuation superresolution microscopy with multi-resolution analysis(AMF-MRA-SOFI)demonstrates enhanced resolution ability and reconstruction quality in experiments performed on sample of conventional dyes,achieving a resolution of 100 nm in the fourth order compared to conventional SOFI reconstruction.Furthermore,our approach combining expansion super-resolution achieved a resolution at-57 nm.展开更多
Aiming at the problems such as low reconstruction efficiency,fuzzy texture details,and difficult convergence of reconstruction network face image super-resolution reconstruction algorithms,a new super-resolution recon...Aiming at the problems such as low reconstruction efficiency,fuzzy texture details,and difficult convergence of reconstruction network face image super-resolution reconstruction algorithms,a new super-resolution reconstruction algorithm with residual concern was proposed.Firstly,to solve the influence of redundant and invalid information about the face image super-resolution reconstruction network,an attention mechanism was introduced into the feature extraction module of the network,which improved the feature utilization rate of the overall network.Secondly,to alleviate the problem of gradient disappearance,the adaptive residual was introduced into the network to make the network model easier to converge during training,and features were supplemented according to the needs during training.The experimental results showed that the proposed algorithm had better reconstruction performance,more facial details,and clearer texture in the reconstructed face image than the comparison algorithm.In objective evaluation,the proposed algorithm's peak signalto-noise ratio and structural similarity were also better than other algorithms.展开更多
The evaluation of adsorption states and shale gas content in shale fractures and pores relies on the analysis of these fractures and pores.Scanning electron microscopy images are commonly used for shale analysis;howev...The evaluation of adsorption states and shale gas content in shale fractures and pores relies on the analysis of these fractures and pores.Scanning electron microscopy images are commonly used for shale analysis;however,their low resolution,particularly the loss of high-frequency information at pore edges,presents challenges in analyzing fractures and pores in shale gas reservoirs.This study introduced a novel neural network called the spatial-spectral domain attention network(SSDAN),which employed spatial and spectral domain attention mechanisms to extract features and restore information in parallel.The network generated super-resolution images through a fusion module that included CNN-based spatial blocks for pixel-level image information recovery,spectral blocks to process Fourier transform information of images and enhance high-frequency recovery,and an adaptive vision transformer to process Fourier transform block information,eliminating the need for a preset image size.The SSDAN model demonstrated exceptional performance in comparative experiments on marine shale and marine continental shale datasets,achieving optimal performance on key indicators such as peak signal-to-noise ratio,structural similarity,learned perceptual image patch similarity,and Frechet inception distance while also exhibiting superior visual performance in pore recovery.Ablation experiments further confirmed the effectiveness of the spatial blocks,channel attention,spectral blocks,and frequency loss function in the model.The SSDAN model showed remarkable capability in enhancing the resolution of shale gas reservoir images and restoring high-frequency information at pore edges,thereby validating its effectiveness in unconventional natural gas reservoir analyses.展开更多
Infrared imaging technology has been widely adopted in various fields,such as military reconnaissance,medical diagnosis,and security monitoring,due to its excellent ability to penetrate smoke and fog.However,the preva...Infrared imaging technology has been widely adopted in various fields,such as military reconnaissance,medical diagnosis,and security monitoring,due to its excellent ability to penetrate smoke and fog.However,the prevalent low resolution of infrared images severely limits the accurate interpretation of their contents.In addition,deploying super-resolution models on resource-constrained devices faces significant challenges.To address these issues,this study proposes a lightweight super-resolution network for infrared images based on an adaptive attention mechanism.The network’s dynamic weighting module automatically adjusts the weights of the attention and nonattention branch outputs based on the network’s characteristics at different levels.Among them,the attention branch is further subdivided into pixel attention and brightness-texture attention,which are specialized for extracting the most informative features in infrared images.Meanwhile,the non-attention branch supplements the extraction of those neglected features to enhance the comprehensiveness of the features.Through ablation experiments,we verify the effectiveness of the proposed module.Finally,through experiments on two datasets,FLIR and Thermal101,qualitative and quantitative results demonstrate that the model can effectively recover high-frequency details of infrared images and significantly improve image resolution.In detail,compared with the suboptimal method,we have reduced the number of parameters by 30%and improved the model performance.When the scale factor is 2,the peak signal-tonoise ratio of the test datasets FLIR and Thermal101 is improved by 0.09 and 0.15 dB,respectively.When the scale factor is 4,it is improved by 0.05 and 0.09 dB,respectively.In addition,due to the lightweight design of the network structure,it has a low computational cost.It is suitable for deployment on edge devices,thus effectively enhancing the sensing performance of infrared imaging devices.展开更多
BACKGROUND Deep learning-based super-resolution(SR)reconstruction can obtain high-quality images with more detailed information.AIM To compare multiparametric normal-resolution(NR)and SR magnetic resonance imaging(MRI...BACKGROUND Deep learning-based super-resolution(SR)reconstruction can obtain high-quality images with more detailed information.AIM To compare multiparametric normal-resolution(NR)and SR magnetic resonance imaging(MRI)in predicting the histopathologic grade in hepatocellular carcinoma.METHODS We retrospectively analyzed a total of 826 patients from two medical centers(training 459;validation 196;test 171).T2-weighted imaging,diffusion-weighted imaging,and portal venous phases were collected.Tumor segmentations were conducted automatically by 3D U-Net.Based on generative adversarial network,we utilized 3D SR reconstruction to produce SR MRI.Radiomics models were developed and validated by XGBoost and Catboost.The predictive efficiency was demonstrated by calibration curves,decision curve analysis,area under the curve(AUC)and net reclassification index(NRI).RESULTS We extracted 3045 radiomic features from both NR and SR MRI,retaining 29 and 28 features,respectively.For XGBoost models,SR MRI yielded higher AUC value than NR MRI in the validation and test cohorts(0.83 vs 0.79;0.80 vs 0.78),respectively.Consistent trends were seen in CatBoost models:SR MRI achieved AUCs of 0.89 and 0.80 compared to NR MRI’s 0.81 and 0.76.NRI indicated that the SR MRI models could improve the prediction accuracy by-1.6%to 20.9%compared to the NR MRI models.CONCLUSION Deep learning-based SR MRI could improve the predictive performance of histopathologic grade in HCC.It may be a powerful tool for better stratification management for patients with operable HCC.展开更多
Fluorogen-activating proteins(FAPs)selectively bind to specific fluorophores,inducing fluorescence activation through the inhibition of torsion of fluorophores.This binding-activation mechanism provides a highly speci...Fluorogen-activating proteins(FAPs)selectively bind to specific fluorophores,inducing fluorescence activation through the inhibition of torsion of fluorophores.This binding-activation mechanism provides a highly specific and efficient fluorescence system that minimizes background signals,significantly enhancing the signal-to-noise ratio(SNR)and making it a powerful tool in live-cell imaging.The principle of binding-activation fluorescence is fundamental to point accumulation for imaging in nanoscale topography(PAINT)super-resolution imaging.However,the high binding affinity between traditional FAPfluorophore pairs limits their application in PAINT,thus hindering the rapid and dynamic imaging necessary for high-resolution cellular studies.In this work,we designed malachite green(MG)derivatives with bulky N-substituents to modulate the binding affinity of the MG-d L5^(**)fluorophore-FAP pair.This modification introduces steric hindrance in MG-dL5^(**)system,resulting in reduced binding affinity and practicability for fast,high-resolution PAINT imaging.Among the synthesized derivatives,MG-Pen showed optimal properties,enabling rapid and high-resolution PAINT imaging of dL5^(**)in living cells.This study highlights the potential of MG derivatives optimization in overcoming the limitations of fluorophore-FAP pairs for super-resolution imaging and provides a new approach for enhancing the performance of PAINT in living cell applications.展开更多
Neutron capture event imaging is a novel technique that has the potential to substantially enhance the resolution of existing imaging systems.This study provides a measurement method for neutron capture event distribu...Neutron capture event imaging is a novel technique that has the potential to substantially enhance the resolution of existing imaging systems.This study provides a measurement method for neutron capture event distribution along with multiple reconstruction methods for super-resolution imaging.The proposed technology reduces the point-spread function of an imag-ing system through single-neutron detection and event reconstruction,thereby significantly improving imaging resolution.A single-neutron detection experiment was conducted using a highly practical and efficient^(6)LiF-ZnS scintillation screen of a cold neutron imaging device in the research reactor.In milliseconds of exposure time,a large number of weak light clusters and their distribution in the scintillation screen were recorded frame by frame,to complete single-neutron detection.Several reconstruction algorithms were proposed for the calculations.The location of neutron capture was calculated using several processing methods such as noise removal,filtering,spot segmentation,contour analysis,and local positioning.The proposed algorithm achieved a higher imaging resolution and faster reconstruction speed,and single-neutron super-resolution imaging was realized by combining single-neutron detection experiments and reconstruction calculations.The results show that the resolution of the 100μm thick^(6)LiF-ZnS scintillation screen can be improved from 125 to 40 microns.This indicates that the proposed single-neutron detection and calculation method is effective and can significantly improve imaging resolution.展开更多
Deep convolutional neural networks(CNNs)have demonstrated remarkable performance in video super-resolution(VSR).However,the ability of most existing methods to recover fine details in complex scenes is often hindered ...Deep convolutional neural networks(CNNs)have demonstrated remarkable performance in video super-resolution(VSR).However,the ability of most existing methods to recover fine details in complex scenes is often hindered by the loss of shallow texture information during feature extraction.To address this limitation,we propose a 3D Convolutional Enhanced Residual Video Super-Resolution Network(3D-ERVSNet).This network employs a forward and backward bidirectional propagation module(FBBPM)that aligns features across frames using explicit optical flow through lightweight SPyNet.By incorporating an enhanced residual structure(ERS)with skip connections,shallow and deep features are effectively integrated,enhancing texture restoration capabilities.Furthermore,3D convolution module(3DCM)is applied after the backward propagation module to implicitly capture spatio-temporal dependencies.The architecture synergizes these components where FBBPM extracts aligned features,ERS fuses hierarchical representations,and 3DCM refines temporal coherence.Finally,a deep feature aggregation module(DFAM)fuses the processed features,and a pixel-upsampling module(PUM)reconstructs the high-resolution(HR)video frames.Comprehensive evaluations on REDS,Vid4,UDM10,and Vim4 benchmarks demonstrate well performance including 30.95 dB PSNR/0.8822 SSIM on REDS and 32.78 dB/0.8987 on Vim4.3D-ERVSNet achieves significant gains over baselines while maintaining high efficiency with only 6.3M parameters and 77ms/frame runtime(i.e.,20×faster than RBPN).The network’s effectiveness stems from its task-specific asymmetric design that balances explicit alignment and implicit fusion.展开更多
Monitoring the dynamics of cellular pseudopodia at nanoscale has become essential for understanding their diverse and complex functions in living cells.This is made possible by combining single-molecule localization m...Monitoring the dynamics of cellular pseudopodia at nanoscale has become essential for understanding their diverse and complex functions in living cells.This is made possible by combining single-molecule localization microscopy(SMLM)with self-blinking dyes.However,existing self-blinking dyes often face limitations,such as nonspecific blinking and low photostability,which can bring background noise and yield erroneous localization signals,hindering their effectiveness for nanoscale visualization.Here,we present a method for long-term SMLM imaging of cellular pseudopodia dynamics using a blinkogenic probe that exhibits self-blinking activation upon molecular recognition.This approach enabled the precise tracking of various pseudopodia structures,including filopodia,lamellipodia,and(tunneling nanotubes)-nanoscale(TNTs),in living cells.We monitored the growth and fusion of filopodia,as well as the extension and shrinkage of lamellipodia,in real-time.Additionally,we identified two distinct fusion modes between filopodia and lamellipodia and captured the formation of TNTs and their interactions with filopodia,demonstrating the probe's utility in visualizing real-time pseudopodia dynamics at nanoscale.展开更多
This study proposes a new component of the composite loss function minimised during training of the Super-Resolution(SR)algorithms—the normalised structural similarity index loss LSSIMN,which has the potential to imp...This study proposes a new component of the composite loss function minimised during training of the Super-Resolution(SR)algorithms—the normalised structural similarity index loss LSSIMN,which has the potential to improve the natural appearance of reconstructed images.Deep learning-based super-resolution(SR)algorithms reconstruct high-resolution images from low-resolution inputs,offering a practical means to enhance image quality without requiring superior imaging hardware,which is particularly important in medical applications where diagnostic accuracy is critical.Although recent SR methods employing convolutional and generative adversarial networks achieve high pixel fidelity,visual artefacts may persist,making the design of the loss function during training essential for ensuring reliable and naturalistic image reconstruction.Our research shows on two models—SR and Invertible Rescaling Neural Network(IRN)—trained on multiple benchmark datasets that the function LSSIMN significantly contributes to the visual quality,preserving the structural fidelity on the reference datasets.The quantitative analysis of results while incorporating LSSIMN shows that including this loss function component has a mean 2.88%impact on the improvement of the final structural similarity of the reconstructed images in the validation set,in comparison to leaving it out and 0.218%in comparison when this component is non-normalised.展开更多
文摘Aiming at the problems of image super-resolution algorithm with many convolutional neural networks, such as large parameters, large computational complexity and blurred image texture, we propose a new algorithm model. The classical convolutional neural network is improved, the convolution kernel size is adjusted, and the parameters are reduced;the pooling layer is added to reduce the dimension. Reduced computational complexity, increased learning rate, and reduced training time. The iterative back-projection algorithm is combined with the convolutional neural network to create a new algorithm model. The experimental results show that compared with the traditional facial illusion method, the proposed method can obtain better performance.
基金supported by China Postdoctoral Science Foundation(2015M582355)the Doctor Scientific Research Start Project from Hubei University of Science and Technology(BK1418)National Natural Science Foundation of China(61271256)
基金This study was supported by:Inner Mongolia Academy of Forestry Sciences Open Research Project(Grant No.KF2024MS03)The Project to Improve the Scientific Research Capacity of the Inner Mongolia Academy of Forestry Sciences(Grant No.2024NLTS04)The Innovation and Entrepreneurship Training Program for Undergraduates of Beijing Forestry University(Grant No.X202410022268).
文摘Remote sensing image super-resolution technology is pivotal for enhancing image quality in critical applications including environmental monitoring,urban planning,and disaster assessment.However,traditional methods exhibit deficiencies in detail recovery and noise suppression,particularly when processing complex landscapes(e.g.,forests,farmlands),leading to artifacts and spectral distortions that limit practical utility.To address this,we propose an enhanced Super-Resolution Generative Adversarial Network(SRGAN)framework featuring three key innovations:(1)Replacement of L1/L2 loss with a robust Charbonnier loss to suppress noise while preserving edge details via adaptive gradient balancing;(2)A multi-loss joint optimization strategy dynamically weighting Charbonnier loss(β=0.5),Visual Geometry Group(VGG)perceptual loss(α=1),and adversarial loss(γ=0.1)to synergize pixel-level accuracy and perceptual quality;(3)A multi-scale residual network(MSRN)capturing cross-scale texture features(e.g.,forest canopies,mountain contours).Validated on Sentinel-2(10 m)and SPOT-6/7(2.5 m)datasets covering 904 km2 in Motuo County,Xizang,our method outperforms the SRGAN baseline(SR4RS)with Peak Signal-to-Noise Ratio(PSNR)gains of 0.29 dB and Structural Similarity Index(SSIM)improvements of 3.08%on forest imagery.Visual comparisons confirm enhanced texture continuity despite marginal Learned Perceptual Image Patch Similarity(LPIPS)increases.The method significantly improves noise robustness and edge retention in complex geomorphology,demonstrating 18%faster response in forest fire early warning and providing high-resolution support for agricultural/urban monitoring.Future work will integrate spectral constraints and lightweight architectures.
基金supported by the National Research Foundation of Korea(NRF)grant funded by the Korea government(*MSIT)(No.2018R1A5A7059549).
文摘The generation of high-quality,realistic face generation has emerged as a key field of research in computer vision.This paper proposes a robust approach that combines a Super-Resolution Generative Adversarial Network(SRGAN)with a Pyramid Attention Module(PAM)to enhance the quality of deep face generation.The SRGAN framework is designed to improve the resolution of generated images,addressing common challenges such as blurriness and a lack of intricate details.The Pyramid Attention Module further complements the process by focusing on multi-scale feature extraction,enabling the network to capture finer details and complex facial features more effectively.The proposed method was trained and evaluated over 100 epochs on the CelebA dataset,demonstrating consistent improvements in image quality and a marked decrease in generator and discriminator losses,reflecting the model’s capacity to learn and synthesize high-quality images effectively,given adequate computational resources.Experimental outcome demonstrates that the SRGAN model with PAM module has outperformed,yielding an aggregate discriminator loss of 0.055 for real,0.043 for fake,and a generator loss of 10.58 after training for 100 epochs.The model has yielded an structural similarity index measure of 0.923,that has outperformed the other models that are considered in the current study for analysis.
基金supported by the National Natural Science Foundation of China(61172173,61303114,61271256,61272544,U1304615,U1404618)the National High Technology Research and Development Program of China(863 Program)No.2013AA014602
文摘Recently, neighbor embedding based face super-resolution(SR) methods have shown the ability for achieving high-quality face images, those methods are based on the assumption that the same neighborhoods are preserved in both low-resolution(LR) training set and high-resolution(HR) training set. However, due to the "one-to-many" mapping between the LR image and HR ones in practice, the neighborhood relationship of the LR patch in LR space is quite different with that of the HR counterpart, that is to say the neighborhood relationship obtained is not true. In this paper, we explore a novel and effective re-identified K-nearest neighbor(RIKNN) method to search neighbors of LR patch. Compared with other methods, our method uses the geometrical information of LR manifold and HR manifold simultaneously. In particular, it searches K-NN of LR patch in the LR space and refines the searching results by re-identifying in the HR space, thus giving rise to accurate K-NN and improved performance. A statistical analysis of the influence of the training set size and nearest neighbor number is given, experimental results on some public face databases show the superiority of our proposed scheme over state-of-the-art face hallucination approaches in terms of subjective and objective results as well as computational complexity.
基金supported by the following grants:National Natural Science Foundation of China(grant nos.92354305,32271428,and 32201132)National Key R&D Program of China(grant no.2022YFC3401100)+1 种基金Fund for Knowledge Innovation of Wuhan Science and Technology Bureau(grant no.2022020801010558)Director Fund of WNLO.
文摘The rapid development of super-resolution microscopy has made it possible to observe subcellular structures and dynamic behaviors in living cells with nanoscale spatial resolution, greatly advancing progress in life sciences. As hardware technology continues to evolve, the availability of new fluorescent probes with superior performance is becoming increasingly important. In recent years, fluorescent nanoprobes (FNPs) have emerged as highly promising fluorescent probes for bioimaging due to their high brightness and excellent photostability. This paper focuses on the development and applications of FNPs as probes for live-cell super-resolution imaging. It provides an overview of different super-resolution methods, discusses the performance requirements for FNPs in these methods, and reviews the latest applications of FNPs in the super-resolution imaging of living cells. Finally, it addresses the challenges and future outlook in this field.
文摘Image super-resolution reconstruction technology is currently widely used in medical imaging,video surveillance,and industrial quality inspection.It not only enhances image quality but also improves details and visual perception,significantly increasing the utility of low-resolution images.In this study,an improved image superresolution reconstruction model based on Generative Adversarial Networks(SRGAN)was proposed.This model introduced a channel and spatial attention mechanism(CSAB)in the generator,allowing it to effectively leverage the information from the input image to enhance feature representations and capture important details.The discriminator was designed with an improved PatchGAN architecture,which more accurately captured local details and texture information of the image.With these enhanced generator and discriminator architectures and an optimized loss function design,this method demonstrated superior performance in image quality assessment metrics.Experimental results showed that this model outperforms traditional methods,presenting more detailed and realistic image details in the visual effects.
文摘Significant advancements have been achieved in the field of Single Image Super-Resolution(SISR)through the utilization of Convolutional Neural Networks(CNNs)to attain state-of-the-art performance.Recent efforts have explored the incorporation of Transformers to augment network performance in SISR.However,the high computational cost of Transformers makes them less suitable for deployment on lightweight devices.Moreover,the majority of enhancements for CNNs rely predominantly on small spatial convolutions,thereby neglecting the potential advantages of large kernel convolution.In this paper,the authors propose a Multi-Perception Large Kernel convNet(MPLKN)which delves into the exploration of large kernel convolution.Specifically,the authors have architected a Multi-Perception Large Kernel(MPLK)module aimed at extracting multi-scale features and employ a stepwise feature fusion strategy to seamlessly integrate these features.In addition,to enhance the network's capacity for nonlinear spatial information processing,the authors have designed a Spatial-Channel Gated Feed-forward Network(SCGFN)that is capable of adapting to feature interactions across both spatial and channel dimensions.Experimental results demonstrate that MPLKN outperforms other lightweight image super-resolution models while maintaining a minimal number of parameters and FLOPs.
基金supported by Sichuan Science and Technology Program[2023YFSY0026,2023YFH0004].
文摘Recent Super-Resolution(SR)algorithms often suffer from excessive model complexity,high computational costs,and limited flexibility across varying image scales.To address these challenges,we propose DDNet,a dynamic and lightweight SR framework designed for arbitrary scaling factors.DDNet integrates a residual learning structure with an Adaptively fusion Feature Block(AFB)and a scale-aware upsampling module,effectively reducing parameter overhead while preserving reconstruction quality.Additionally,we introduce DDNetGAN,an enhanced variant that leverages a relativistic Generative Adversarial Network(GAN)to further improve texture realism.To validate the proposed models,we conduct extensive training using the DIV2K and Flickr2K datasets and evaluate performance across standard benchmarks including Set5,Set14,Urban100,Manga109,and BSD100.Our experiments cover both symmetric and asymmetric upscaling factors and incorporate ablation studies to assess key components.Results show that DDNet and DDNetGAN achieve competitive performance compared with mainstream SR algorithms,demonstrating a strong balance between accuracy,efficiency,and flexibility.These findings highlight the potential of our approach for practical real-world super-resolution applications.
基金supported by the following grants:National Key R&D Program of China(Grant no.2022YFC3401100)National Natural Science Foundation of China(Grant nos.32271428,92054110,32201132 and 31600692).
文摘Blood cells are the most integral part of the body,which are made up of erythrocytes,platelets and white blood cells.The examination of subcellular structures and proteins within blood cells at the nanoscale can provide valuable insights into the health status of an individual,accurate diagnosis,and efficient treatment strategies for diseases.Super-resolution microscopy(SRM)has recently emerged as a cutting-edge tool for the study of blood cells,providing numerous advantages over traditional methods for examining subcellular structures and proteins.In this paper,we focus on outlining the fundamental principles of various SRM techniques and their applications in both normal and diseased states of blood cells.Furthermore,future prospects of SRM techniques in the analysis of blood cells are also discussed.
基金supported by the National Natural Science Foundation of China(62175034,62175036,32271510)the National Key R&D Program of China(2021YFF0502900)+2 种基金the Science and Technology Research Program of Shanghai(Grant No.19DZ2282100)the Shanghai Key Laboratory of Metasurfaces for Light Manipulation(23dz2260100)the Shanghai Engineering Technology Research Center of Hair Medicine(19DZ2250500).
文摘A new scheme of super-resolution optical fluctuation imaging(SOFI)is proposed to broaden its application in the high-order cumulant reconstruction by optimizing blinking characteristics,eliminating noise in raw data and applying multi-resolution analysis in cumulant reconstruction.A motor-driven rotating mask optical modulation system is designed to adjust the excitation lightfield and allows for fast deployment.Active-modulated fluorescence fluctuation superresolution microscopy with multi-resolution analysis(AMF-MRA-SOFI)demonstrates enhanced resolution ability and reconstruction quality in experiments performed on sample of conventional dyes,achieving a resolution of 100 nm in the fourth order compared to conventional SOFI reconstruction.Furthermore,our approach combining expansion super-resolution achieved a resolution at-57 nm.
基金supported by National Natural Science Foundation of China(No.62063014)。
文摘Aiming at the problems such as low reconstruction efficiency,fuzzy texture details,and difficult convergence of reconstruction network face image super-resolution reconstruction algorithms,a new super-resolution reconstruction algorithm with residual concern was proposed.Firstly,to solve the influence of redundant and invalid information about the face image super-resolution reconstruction network,an attention mechanism was introduced into the feature extraction module of the network,which improved the feature utilization rate of the overall network.Secondly,to alleviate the problem of gradient disappearance,the adaptive residual was introduced into the network to make the network model easier to converge during training,and features were supplemented according to the needs during training.The experimental results showed that the proposed algorithm had better reconstruction performance,more facial details,and clearer texture in the reconstructed face image than the comparison algorithm.In objective evaluation,the proposed algorithm's peak signalto-noise ratio and structural similarity were also better than other algorithms.
基金the National Natural Science Foundation(NNSF)of China under Grant 41927801.
文摘The evaluation of adsorption states and shale gas content in shale fractures and pores relies on the analysis of these fractures and pores.Scanning electron microscopy images are commonly used for shale analysis;however,their low resolution,particularly the loss of high-frequency information at pore edges,presents challenges in analyzing fractures and pores in shale gas reservoirs.This study introduced a novel neural network called the spatial-spectral domain attention network(SSDAN),which employed spatial and spectral domain attention mechanisms to extract features and restore information in parallel.The network generated super-resolution images through a fusion module that included CNN-based spatial blocks for pixel-level image information recovery,spectral blocks to process Fourier transform information of images and enhance high-frequency recovery,and an adaptive vision transformer to process Fourier transform block information,eliminating the need for a preset image size.The SSDAN model demonstrated exceptional performance in comparative experiments on marine shale and marine continental shale datasets,achieving optimal performance on key indicators such as peak signal-to-noise ratio,structural similarity,learned perceptual image patch similarity,and Frechet inception distance while also exhibiting superior visual performance in pore recovery.Ablation experiments further confirmed the effectiveness of the spatial blocks,channel attention,spectral blocks,and frequency loss function in the model.The SSDAN model showed remarkable capability in enhancing the resolution of shale gas reservoir images and restoring high-frequency information at pore edges,thereby validating its effectiveness in unconventional natural gas reservoir analyses.
基金funded in part by theHenan ProvinceKeyR&DProgramProject,“Research and Application Demonstration of Class Ⅱ Superlattice Medium Wave High Temperature Infrared Detector Technology”under Grant No.231111210400.
文摘Infrared imaging technology has been widely adopted in various fields,such as military reconnaissance,medical diagnosis,and security monitoring,due to its excellent ability to penetrate smoke and fog.However,the prevalent low resolution of infrared images severely limits the accurate interpretation of their contents.In addition,deploying super-resolution models on resource-constrained devices faces significant challenges.To address these issues,this study proposes a lightweight super-resolution network for infrared images based on an adaptive attention mechanism.The network’s dynamic weighting module automatically adjusts the weights of the attention and nonattention branch outputs based on the network’s characteristics at different levels.Among them,the attention branch is further subdivided into pixel attention and brightness-texture attention,which are specialized for extracting the most informative features in infrared images.Meanwhile,the non-attention branch supplements the extraction of those neglected features to enhance the comprehensiveness of the features.Through ablation experiments,we verify the effectiveness of the proposed module.Finally,through experiments on two datasets,FLIR and Thermal101,qualitative and quantitative results demonstrate that the model can effectively recover high-frequency details of infrared images and significantly improve image resolution.In detail,compared with the suboptimal method,we have reduced the number of parameters by 30%and improved the model performance.When the scale factor is 2,the peak signal-tonoise ratio of the test datasets FLIR and Thermal101 is improved by 0.09 and 0.15 dB,respectively.When the scale factor is 4,it is improved by 0.05 and 0.09 dB,respectively.In addition,due to the lightweight design of the network structure,it has a low computational cost.It is suitable for deployment on edge devices,thus effectively enhancing the sensing performance of infrared imaging devices.
基金Supported by AI+Health Collaborative Innovation Cultivation Project of Beijing City,No.Z221100003522005.
文摘BACKGROUND Deep learning-based super-resolution(SR)reconstruction can obtain high-quality images with more detailed information.AIM To compare multiparametric normal-resolution(NR)and SR magnetic resonance imaging(MRI)in predicting the histopathologic grade in hepatocellular carcinoma.METHODS We retrospectively analyzed a total of 826 patients from two medical centers(training 459;validation 196;test 171).T2-weighted imaging,diffusion-weighted imaging,and portal venous phases were collected.Tumor segmentations were conducted automatically by 3D U-Net.Based on generative adversarial network,we utilized 3D SR reconstruction to produce SR MRI.Radiomics models were developed and validated by XGBoost and Catboost.The predictive efficiency was demonstrated by calibration curves,decision curve analysis,area under the curve(AUC)and net reclassification index(NRI).RESULTS We extracted 3045 radiomic features from both NR and SR MRI,retaining 29 and 28 features,respectively.For XGBoost models,SR MRI yielded higher AUC value than NR MRI in the validation and test cohorts(0.83 vs 0.79;0.80 vs 0.78),respectively.Consistent trends were seen in CatBoost models:SR MRI achieved AUCs of 0.89 and 0.80 compared to NR MRI’s 0.81 and 0.76.NRI indicated that the SR MRI models could improve the prediction accuracy by-1.6%to 20.9%compared to the NR MRI models.CONCLUSION Deep learning-based SR MRI could improve the predictive performance of histopathologic grade in HCC.It may be a powerful tool for better stratification management for patients with operable HCC.
基金supported by the National Natural Science Foundation of China(Nos.22225806,22078314,22278394,22378385)Dalian Institute of Chemical Physics(Nos.DICPI202142,DICPI202436)。
文摘Fluorogen-activating proteins(FAPs)selectively bind to specific fluorophores,inducing fluorescence activation through the inhibition of torsion of fluorophores.This binding-activation mechanism provides a highly specific and efficient fluorescence system that minimizes background signals,significantly enhancing the signal-to-noise ratio(SNR)and making it a powerful tool in live-cell imaging.The principle of binding-activation fluorescence is fundamental to point accumulation for imaging in nanoscale topography(PAINT)super-resolution imaging.However,the high binding affinity between traditional FAPfluorophore pairs limits their application in PAINT,thus hindering the rapid and dynamic imaging necessary for high-resolution cellular studies.In this work,we designed malachite green(MG)derivatives with bulky N-substituents to modulate the binding affinity of the MG-d L5^(**)fluorophore-FAP pair.This modification introduces steric hindrance in MG-dL5^(**)system,resulting in reduced binding affinity and practicability for fast,high-resolution PAINT imaging.Among the synthesized derivatives,MG-Pen showed optimal properties,enabling rapid and high-resolution PAINT imaging of dL5^(**)in living cells.This study highlights the potential of MG derivatives optimization in overcoming the limitations of fluorophore-FAP pairs for super-resolution imaging and provides a new approach for enhancing the performance of PAINT in living cell applications.
基金supported by the National Natural Science Foundation of China(Nos.12205271,12075217,U20B2011,and 51978218)Sichuan Science and Technology Program(No.2019ZDZX0010)the National Key R&D Program of China(No.2022YFA1604002).
文摘Neutron capture event imaging is a novel technique that has the potential to substantially enhance the resolution of existing imaging systems.This study provides a measurement method for neutron capture event distribution along with multiple reconstruction methods for super-resolution imaging.The proposed technology reduces the point-spread function of an imag-ing system through single-neutron detection and event reconstruction,thereby significantly improving imaging resolution.A single-neutron detection experiment was conducted using a highly practical and efficient^(6)LiF-ZnS scintillation screen of a cold neutron imaging device in the research reactor.In milliseconds of exposure time,a large number of weak light clusters and their distribution in the scintillation screen were recorded frame by frame,to complete single-neutron detection.Several reconstruction algorithms were proposed for the calculations.The location of neutron capture was calculated using several processing methods such as noise removal,filtering,spot segmentation,contour analysis,and local positioning.The proposed algorithm achieved a higher imaging resolution and faster reconstruction speed,and single-neutron super-resolution imaging was realized by combining single-neutron detection experiments and reconstruction calculations.The results show that the resolution of the 100μm thick^(6)LiF-ZnS scintillation screen can be improved from 125 to 40 microns.This indicates that the proposed single-neutron detection and calculation method is effective and can significantly improve imaging resolution.
基金supported in part by the Basic and Applied Basic Research Foundation of Guangdong Province[2025A1515011566]in part by the State Key Laboratory for Novel Software Technology,Nanjing University[KFKT2024B08]+1 种基金in part by Leading Talents in Gusu Innovation and Entrepreneurship[ZXL2023170]in part by the Basic Research Programs of Taicang 2024,[TC2024JC32].
文摘Deep convolutional neural networks(CNNs)have demonstrated remarkable performance in video super-resolution(VSR).However,the ability of most existing methods to recover fine details in complex scenes is often hindered by the loss of shallow texture information during feature extraction.To address this limitation,we propose a 3D Convolutional Enhanced Residual Video Super-Resolution Network(3D-ERVSNet).This network employs a forward and backward bidirectional propagation module(FBBPM)that aligns features across frames using explicit optical flow through lightweight SPyNet.By incorporating an enhanced residual structure(ERS)with skip connections,shallow and deep features are effectively integrated,enhancing texture restoration capabilities.Furthermore,3D convolution module(3DCM)is applied after the backward propagation module to implicitly capture spatio-temporal dependencies.The architecture synergizes these components where FBBPM extracts aligned features,ERS fuses hierarchical representations,and 3DCM refines temporal coherence.Finally,a deep feature aggregation module(DFAM)fuses the processed features,and a pixel-upsampling module(PUM)reconstructs the high-resolution(HR)video frames.Comprehensive evaluations on REDS,Vid4,UDM10,and Vim4 benchmarks demonstrate well performance including 30.95 dB PSNR/0.8822 SSIM on REDS and 32.78 dB/0.8987 on Vim4.3D-ERVSNet achieves significant gains over baselines while maintaining high efficiency with only 6.3M parameters and 77ms/frame runtime(i.e.,20×faster than RBPN).The network’s effectiveness stems from its task-specific asymmetric design that balances explicit alignment and implicit fusion.
基金supported by the National Natural Science Foundation of China(Nos.22225806,22078314,22278394,22378385)Dalian Institute of Chemical Physics(Nos.DICPI202227,DICPI202436)。
文摘Monitoring the dynamics of cellular pseudopodia at nanoscale has become essential for understanding their diverse and complex functions in living cells.This is made possible by combining single-molecule localization microscopy(SMLM)with self-blinking dyes.However,existing self-blinking dyes often face limitations,such as nonspecific blinking and low photostability,which can bring background noise and yield erroneous localization signals,hindering their effectiveness for nanoscale visualization.Here,we present a method for long-term SMLM imaging of cellular pseudopodia dynamics using a blinkogenic probe that exhibits self-blinking activation upon molecular recognition.This approach enabled the precise tracking of various pseudopodia structures,including filopodia,lamellipodia,and(tunneling nanotubes)-nanoscale(TNTs),in living cells.We monitored the growth and fusion of filopodia,as well as the extension and shrinkage of lamellipodia,in real-time.Additionally,we identified two distinct fusion modes between filopodia and lamellipodia and captured the formation of TNTs and their interactions with filopodia,demonstrating the probe's utility in visualizing real-time pseudopodia dynamics at nanoscale.
基金support from the following institutional grant.Internal Grant Agency of the Faculty of Economics and Management,Czech University of Life Sciences Prague,grant no.2023A0004(https://iga.pef.czu.cz/,accessed on 6 June 2025).
文摘This study proposes a new component of the composite loss function minimised during training of the Super-Resolution(SR)algorithms—the normalised structural similarity index loss LSSIMN,which has the potential to improve the natural appearance of reconstructed images.Deep learning-based super-resolution(SR)algorithms reconstruct high-resolution images from low-resolution inputs,offering a practical means to enhance image quality without requiring superior imaging hardware,which is particularly important in medical applications where diagnostic accuracy is critical.Although recent SR methods employing convolutional and generative adversarial networks achieve high pixel fidelity,visual artefacts may persist,making the design of the loss function during training essential for ensuring reliable and naturalistic image reconstruction.Our research shows on two models—SR and Invertible Rescaling Neural Network(IRN)—trained on multiple benchmark datasets that the function LSSIMN significantly contributes to the visual quality,preserving the structural fidelity on the reference datasets.The quantitative analysis of results while incorporating LSSIMN shows that including this loss function component has a mean 2.88%impact on the improvement of the final structural similarity of the reconstructed images in the validation set,in comparison to leaving it out and 0.218%in comparison when this component is non-normalised.
