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
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
Although Convolutional Neural Networks(CNNs)have significantly improved the development of image Super-Resolution(SR)technology in recent years,the existing SR methods for SAR image with large scale factors have rarel...Although Convolutional Neural Networks(CNNs)have significantly improved the development of image Super-Resolution(SR)technology in recent years,the existing SR methods for SAR image with large scale factors have rarely been studied due to technical difficulty.A more efficient method is to obtain comprehensive information to guide the SAR image reconstruction.Indeed,the co-registered High-Resolution(HR)optical image has been successfully applied to enhance the quality of SAR image due to its discriminative characteristics.Inspired by this,we propose a novel Optical-Guided Super-Resolution Network(OGSRN)for SAR image with large scale factors.Specifically,our proposed OGSRN consists of two sub-nets:a SAR image SuperResolution U-Net(SRUN)and a SAR-to-Optical Residual Translation Network(SORTN).The whole process during training includes two stages.In stage-1,the SR SAR images are reconstructed by the SRUN.And an Enhanced Residual Attention Module(ERAM),which is comprised of the Channel Attention(CA)and Spatial Attention(SA)mechanisms,is constructed to boost the representation ability of the network.In stage-2,the output of the stage-1 and its corresponding HR SAR images are translated to optical images by the SORTN,respectively.And then the differences between SR images and HR images are computed in the optical space to obtain feedback information that can reduce the space of possible SR solution.After that,we can use the optimized SRUN to directly produce HR SAR image from Low-Resolution(LR)SAR image in the testing phase.The experimental results show that under the guidance of optical image,our OGSRN can achieve excellent performance in both quantitative assessment metrics and visual quality.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
Unmanned aerial vehicle(UAV)-borne gamma-ray spectrum survey plays a crucial role in geological mapping,radioactive mineral exploration,and environmental monitoring.However,raw data are often compromised by flight and...Unmanned aerial vehicle(UAV)-borne gamma-ray spectrum survey plays a crucial role in geological mapping,radioactive mineral exploration,and environmental monitoring.However,raw data are often compromised by flight and instrument background noise,as well as detector resolution limitations,which affect the accuracy of geological interpretations.This study aims to explore the application of the Real-ESRGAN algorithm in the super-resolution reconstruction of UAV-borne gamma-ray spectrum images to enhance spatial resolution and the quality of geological feature visualization.We conducted super-resolution reconstruction experiments with 2×,4×and 6×magnification using the Real-ESRGAN algorithm,comparing the results with three other mainstream algorithms(SRCNN,SRGAN,FSRCNN)to verify the superiority in image quality.The experimental results indicate that Real-ESRGAN achieved a structural similarity index(SSIM)value of 0.950 at 2×magnification,significantly higher than the other algorithms,demonstrating its advantage in detail preservation.Furthermore,Real-ESRGAN effectively reduced ringing and overshoot artifacts,enhancing the clarity of geological structures and mineral deposit sites,thus providing high-quality visual information for geological exploration.展开更多
Existing imaging techniques cannot simultaneously achieve high resolution and a wide field of view,and manual multi-mineral segmentation in shale lacks precision.To address these limitations,we propose a comprehensive...Existing imaging techniques cannot simultaneously achieve high resolution and a wide field of view,and manual multi-mineral segmentation in shale lacks precision.To address these limitations,we propose a comprehensive framework based on generative adversarial network(GAN)for characterizing pore structure properties of shale,which incorporates image augmentation,super-resolution reconstruction,and multi-mineral auto-segmentation.Using real 2D and 3D shale images,the framework was assessed through correlation function,entropy,porosity,pore size distribution,and permeability.The application results show that this framework enables the enhancement of 3D low-resolution digital cores by a scale factor of 8,without paired shale images,effectively reconstructing the unresolved fine-scale pores under a low resolution,rather than merely denoising,deblurring,and edge clarification.The trained GAN-based segmentation model effectively improves manual multi-mineral segmentation results,resulting in a strong resemblance to real samples in terms of pore size distribution and permeability.This framework significantly improves the characterization of complex shale microstructures and can be expanded to other heterogeneous porous media,such as carbonate,coal,and tight sandstone reservoirs.展开更多
The application of image super-resolution(SR)has brought significant assistance in the medical field,aiding doctors to make more precise diagnoses.However,solely relying on a convolutional neural network(CNN)for image...The application of image super-resolution(SR)has brought significant assistance in the medical field,aiding doctors to make more precise diagnoses.However,solely relying on a convolutional neural network(CNN)for image SR may lead to issues such as blurry details and excessive smoothness.To address the limitations,we proposed an algorithm based on the generative adversarial network(GAN)framework.In the generator network,three different sizes of convolutions connected by a residual dense structure were used to extract detailed features,and an attention mechanism combined with dual channel and spatial information was applied to concentrate the computing power on crucial areas.In the discriminator network,using InstanceNorm to normalize tensors sped up the training process while retaining feature information.The experimental results demonstrate that our algorithm achieves higher peak signal-to-noise ratio(PSNR)and structural similarity index measure(SSIM)compared to other methods,resulting in an improved visual quality.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
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
The tradeoff between efficiency and model size of the convolutional neural network(CNN)is an essential issue for applications of CNN-based algorithms to diverse real-world tasks.Although deep learning-based methods ha...The tradeoff between efficiency and model size of the convolutional neural network(CNN)is an essential issue for applications of CNN-based algorithms to diverse real-world tasks.Although deep learning-based methods have achieved significant improvements in image super-resolution(SR),current CNNbased techniques mainly contain massive parameters and a high computational complexity,limiting their practical applications.In this paper,we present a fast and lightweight framework,named weighted multi-scale residual network(WMRN),for a better tradeoff between SR performance and computational efficiency.With the modified residual structure,depthwise separable convolutions(DS Convs)are employed to improve convolutional operations’efficiency.Furthermore,several weighted multi-scale residual blocks(WMRBs)are stacked to enhance the multi-scale representation capability.In the reconstruction subnetwork,a group of Conv layers are introduced to filter feature maps to reconstruct the final high-quality image.Extensive experiments were conducted to evaluate the proposed model,and the comparative results with several state-of-the-art algorithms demonstrate the effectiveness of WMRN.展开更多
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 achieve...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.展开更多
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 ...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.展开更多
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 ...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.展开更多
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 res...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.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
A novel channel attention residual network(CAN)for SISR has been proposed to rescale pixel-wise features by explicitly modeling interdependencies between channels and encoding where the visual attention is located.The...A novel channel attention residual network(CAN)for SISR has been proposed to rescale pixel-wise features by explicitly modeling interdependencies between channels and encoding where the visual attention is located.The backbone of CAN is channel attention block(CAB).The proposed CAB combines cosine similarity block(CSB)and back-projection gating block(BG).CSB fully considers global spatial information of each channel and computes the cosine similarity between each channel to obtain finer channel statistics than the first-order statistics.For further exploration of channel attention,we introduce effective back-projection to the gating mechanism and propose BG.Meanwhile,we adopt local and global residual connections in SISR which directly convey most low-frequency information to the final SR outputs and valuable high-frequency components are allocated more computational resources through channel attention mechanism.Extensive experiments show the superiority of the proposed CAN over the state-of-the-art methods on benchmark datasets in both accuracy and visual quality.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
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 r...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.展开更多
The diagnosis of COVID-19 requires chest computed tomography(CT).High-resolution CT images can provide more diagnostic information to help doctors better diagnose the disease,so it is of clinical importance to study s...The diagnosis of COVID-19 requires chest computed tomography(CT).High-resolution CT images can provide more diagnostic information to help doctors better diagnose the disease,so it is of clinical importance to study super-resolution(SR)algorithms applied to CT images to improve the reso-lution of CT images.However,most of the existing SR algorithms are studied based on natural images,which are not suitable for medical images;and most of these algorithms improve the reconstruction quality by increasing the network depth,which is not suitable for machines with limited resources.To alleviate these issues,we propose a residual feature attentional fusion network for lightweight chest CT image super-resolution(RFAFN).Specifically,we design a contextual feature extraction block(CFEB)that can extract CT image features more efficiently and accurately than ordinary residual blocks.In addition,we propose a feature-weighted cascading strategy(FWCS)based on attentional feature fusion blocks(AFFB)to utilize the high-frequency detail information extracted by CFEB as much as possible via selectively fusing adjacent level feature information.Finally,we suggest a global hierarchical feature fusion strategy(GHFFS),which can utilize the hierarchical features more effectively than dense concatenation by progressively aggregating the feature information at various levels.Numerous experiments show that our method performs better than most of the state-of-the-art(SOTA)methods on the COVID-19 chest CT dataset.In detail,the peak signal-to-noise ratio(PSNR)is 0.11 dB and 0.47 dB higher on CTtest1 and CTtest2 at×3 SR compared to the suboptimal method,but the number of parameters and multi-adds are reduced by 22K and 0.43G,respectively.Our method can better recover chest CT image quality with fewer computational resources and effectively assist in COVID-19.展开更多
Image super resolution is an important field of computer research.The current mainstream image super-resolution technology is to use deep learning to mine the deeper features of the image,and then use it for image res...Image super resolution is an important field of computer research.The current mainstream image super-resolution technology is to use deep learning to mine the deeper features of the image,and then use it for image restoration.However,most of these models mentioned above only trained the images in a specific scale and do not consider the relationships between different scales of images.In order to utilize the information of images at different scales,we design a cascade network structure and cascaded super-resolution convolutional neural networks.This network contains three cascaded FSRCNNs.Due to each sub FSRCNN can process a specific scale image,our network can simultaneously exploit three scale images,and can also use the information of three different scales of images.Experiments on multiple datasets confirmed that the proposed network can achieve better performance for image SR.展开更多
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 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.61771319,62076165 and 61871154)the Natural Science Foundation of Guangdong Province,China(No.2019A1515011307)+1 种基金Shenzhen Science and Technology Project,China(Nos.JCYJ20180507182259896 and 20200826154022001)the other project(Nos.2020KCXTD004 and WDZC20195500201)。
文摘Although Convolutional Neural Networks(CNNs)have significantly improved the development of image Super-Resolution(SR)technology in recent years,the existing SR methods for SAR image with large scale factors have rarely been studied due to technical difficulty.A more efficient method is to obtain comprehensive information to guide the SAR image reconstruction.Indeed,the co-registered High-Resolution(HR)optical image has been successfully applied to enhance the quality of SAR image due to its discriminative characteristics.Inspired by this,we propose a novel Optical-Guided Super-Resolution Network(OGSRN)for SAR image with large scale factors.Specifically,our proposed OGSRN consists of two sub-nets:a SAR image SuperResolution U-Net(SRUN)and a SAR-to-Optical Residual Translation Network(SORTN).The whole process during training includes two stages.In stage-1,the SR SAR images are reconstructed by the SRUN.And an Enhanced Residual Attention Module(ERAM),which is comprised of the Channel Attention(CA)and Spatial Attention(SA)mechanisms,is constructed to boost the representation ability of the network.In stage-2,the output of the stage-1 and its corresponding HR SAR images are translated to optical images by the SORTN,respectively.And then the differences between SR images and HR images are computed in the optical space to obtain feedback information that can reduce the space of possible SR solution.After that,we can use the optimized SRUN to directly produce HR SAR image from Low-Resolution(LR)SAR image in the testing phase.The experimental results show that under the guidance of optical image,our OGSRN can achieve excellent performance in both quantitative assessment metrics and visual quality.
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 Natural Science Foundation of China(Nos.12205044 and 12265003)2024 Jiangxi Province Civil-Military Integration Research Institute‘BeiDou+’Project Subtopic(No.2024JXRH0Y06).
文摘Unmanned aerial vehicle(UAV)-borne gamma-ray spectrum survey plays a crucial role in geological mapping,radioactive mineral exploration,and environmental monitoring.However,raw data are often compromised by flight and instrument background noise,as well as detector resolution limitations,which affect the accuracy of geological interpretations.This study aims to explore the application of the Real-ESRGAN algorithm in the super-resolution reconstruction of UAV-borne gamma-ray spectrum images to enhance spatial resolution and the quality of geological feature visualization.We conducted super-resolution reconstruction experiments with 2×,4×and 6×magnification using the Real-ESRGAN algorithm,comparing the results with three other mainstream algorithms(SRCNN,SRGAN,FSRCNN)to verify the superiority in image quality.The experimental results indicate that Real-ESRGAN achieved a structural similarity index(SSIM)value of 0.950 at 2×magnification,significantly higher than the other algorithms,demonstrating its advantage in detail preservation.Furthermore,Real-ESRGAN effectively reduced ringing and overshoot artifacts,enhancing the clarity of geological structures and mineral deposit sites,thus providing high-quality visual information for geological exploration.
基金Supported by the National Natural Science Foundation of China(U23A20595,52034010,52288101)National Key Research and Development Program of China(2022YFE0203400)+1 种基金Shandong Provincial Natural Science Foundation(ZR2024ZD17)Fundamental Research Funds for the Central Universities(23CX10004A).
文摘Existing imaging techniques cannot simultaneously achieve high resolution and a wide field of view,and manual multi-mineral segmentation in shale lacks precision.To address these limitations,we propose a comprehensive framework based on generative adversarial network(GAN)for characterizing pore structure properties of shale,which incorporates image augmentation,super-resolution reconstruction,and multi-mineral auto-segmentation.Using real 2D and 3D shale images,the framework was assessed through correlation function,entropy,porosity,pore size distribution,and permeability.The application results show that this framework enables the enhancement of 3D low-resolution digital cores by a scale factor of 8,without paired shale images,effectively reconstructing the unresolved fine-scale pores under a low resolution,rather than merely denoising,deblurring,and edge clarification.The trained GAN-based segmentation model effectively improves manual multi-mineral segmentation results,resulting in a strong resemblance to real samples in terms of pore size distribution and permeability.This framework significantly improves the characterization of complex shale microstructures and can be expanded to other heterogeneous porous media,such as carbonate,coal,and tight sandstone reservoirs.
文摘The application of image super-resolution(SR)has brought significant assistance in the medical field,aiding doctors to make more precise diagnoses.However,solely relying on a convolutional neural network(CNN)for image SR may lead to issues such as blurry details and excessive smoothness.To address the limitations,we proposed an algorithm based on the generative adversarial network(GAN)framework.In the generator network,three different sizes of convolutions connected by a residual dense structure were used to extract detailed features,and an attention mechanism combined with dual channel and spatial information was applied to concentrate the computing power on crucial areas.In the discriminator network,using InstanceNorm to normalize tensors sped up the training process while retaining feature information.The experimental results demonstrate that our algorithm achieves higher peak signal-to-noise ratio(PSNR)and structural similarity index measure(SSIM)compared to other methods,resulting in an improved visual quality.
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the National Natural Science Foundation of China(61772149,61866009,61762028,U1701267,61702169)Guangxi Science and Technology Project(2019GXNSFFA245014,ZY20198016,AD18281079,AD18216004)+1 种基金the Natural Science Foundation of Hunan Province(2020JJ3014)Guangxi Colleges and Universities Key Laboratory of Intelligent Processing of Computer Images and Graphics(GIIP202001).
文摘The tradeoff between efficiency and model size of the convolutional neural network(CNN)is an essential issue for applications of CNN-based algorithms to diverse real-world tasks.Although deep learning-based methods have achieved significant improvements in image super-resolution(SR),current CNNbased techniques mainly contain massive parameters and a high computational complexity,limiting their practical applications.In this paper,we present a fast and lightweight framework,named weighted multi-scale residual network(WMRN),for a better tradeoff between SR performance and computational efficiency.With the modified residual structure,depthwise separable convolutions(DS Convs)are employed to improve convolutional operations’efficiency.Furthermore,several weighted multi-scale residual blocks(WMRBs)are stacked to enhance the multi-scale representation capability.In the reconstruction subnetwork,a group of Conv layers are introduced to filter feature maps to reconstruct the final high-quality image.Extensive experiments were conducted to evaluate the proposed model,and the comparative results with several state-of-the-art algorithms demonstrate the effectiveness of WMRN.
文摘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.
基金The authors are highly thankful to the Development Research Center of Guangxi Relatively Sparse-populated Minorities(ID:GXRKJSZ201901)to the Natural Science Foundation of Guangxi Province(No.2018GXNSFAA281164)This research was financially supported by the project of outstanding thousand young teachers’training in higher education institutions of Guangxi,Guangxi Colleges and Universities Key Laboratory Breeding Base of System Control and Information Processing.
文摘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.
基金supported by the National Natural Science Foundation of China(61971165)the Key Research and Development Program of Hubei Province(2020BAB113)。
文摘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.
基金This work was supported in part by the National Science Foundation of China under Grant 61572526.
文摘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.
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A novel channel attention residual network(CAN)for SISR has been proposed to rescale pixel-wise features by explicitly modeling interdependencies between channels and encoding where the visual attention is located.The backbone of CAN is channel attention block(CAB).The proposed CAB combines cosine similarity block(CSB)and back-projection gating block(BG).CSB fully considers global spatial information of each channel and computes the cosine similarity between each channel to obtain finer channel statistics than the first-order statistics.For further exploration of channel attention,we introduce effective back-projection to the gating mechanism and propose BG.Meanwhile,we adopt local and global residual connections in SISR which directly convey most low-frequency information to the final SR outputs and valuable high-frequency components are allocated more computational resources through channel attention mechanism.Extensive experiments show the superiority of the proposed CAN over the state-of-the-art methods on benchmark datasets in both accuracy and visual quality.
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.
基金supported by Balochistan University of Engineering and Technology,Khuzdar,Balochistan,Pakistan.
文摘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.
基金supported by the General Project of Natural Science Foundation of Hebei Province of China(H2019201378)the Foundation of the President of Hebei University(XZJJ201917)the Special Project for Cultivating Scientific and Technological Innovation Ability of University and Middle School Students of Hebei Province(2021H060306).
文摘The diagnosis of COVID-19 requires chest computed tomography(CT).High-resolution CT images can provide more diagnostic information to help doctors better diagnose the disease,so it is of clinical importance to study super-resolution(SR)algorithms applied to CT images to improve the reso-lution of CT images.However,most of the existing SR algorithms are studied based on natural images,which are not suitable for medical images;and most of these algorithms improve the reconstruction quality by increasing the network depth,which is not suitable for machines with limited resources.To alleviate these issues,we propose a residual feature attentional fusion network for lightweight chest CT image super-resolution(RFAFN).Specifically,we design a contextual feature extraction block(CFEB)that can extract CT image features more efficiently and accurately than ordinary residual blocks.In addition,we propose a feature-weighted cascading strategy(FWCS)based on attentional feature fusion blocks(AFFB)to utilize the high-frequency detail information extracted by CFEB as much as possible via selectively fusing adjacent level feature information.Finally,we suggest a global hierarchical feature fusion strategy(GHFFS),which can utilize the hierarchical features more effectively than dense concatenation by progressively aggregating the feature information at various levels.Numerous experiments show that our method performs better than most of the state-of-the-art(SOTA)methods on the COVID-19 chest CT dataset.In detail,the peak signal-to-noise ratio(PSNR)is 0.11 dB and 0.47 dB higher on CTtest1 and CTtest2 at×3 SR compared to the suboptimal method,but the number of parameters and multi-adds are reduced by 22K and 0.43G,respectively.Our method can better recover chest CT image quality with fewer computational resources and effectively assist in COVID-19.
基金supported in part by the National Natural Science Foundation of China under Grant 61806099in part by the Natural Science Foundation of Jiangsu Province of China under Grant BK20180790,in part by the Natural Science Research of Jiangsu Higher Education Institutions of China under Grant 8KJB520033in part by Startup Foundation for Introducing Talent of Nanjing University of Information Science and Technology under Grant 2243141701077.
文摘Image super resolution is an important field of computer research.The current mainstream image super-resolution technology is to use deep learning to mine the deeper features of the image,and then use it for image restoration.However,most of these models mentioned above only trained the images in a specific scale and do not consider the relationships between different scales of images.In order to utilize the information of images at different scales,we design a cascade network structure and cascaded super-resolution convolutional neural networks.This network contains three cascaded FSRCNNs.Due to each sub FSRCNN can process a specific scale image,our network can simultaneously exploit three scale images,and can also use the information of three different scales of images.Experiments on multiple datasets confirmed that the proposed network can achieve better performance for image SR.
