Convolutional neural networks(CNNs) have shown great potential for image super-resolution(SR).However,most existing CNNs only reconstruct images in the spatial domain,resulting in insufficient high-frequency details o...Convolutional neural networks(CNNs) have shown great potential for image super-resolution(SR).However,most existing CNNs only reconstruct images in the spatial domain,resulting in insufficient high-frequency details of reconstructed images.To address this issue,a channel attention based wavelet cascaded network for image super-resolution(CWSR) is proposed.Specifically,a second-order channel attention(SOCA) mechanism is incorporated into the network,and the covariance matrix normalization is utilized to explore interdependencies between channel-wise features.Then,to boost the quality of residual features,the non-local module is adopted to further improve the global information integration ability of the network.Finally,taking the image loss in the spatial and wavelet domains into account,a dual-constrained loss function is proposed to optimize the network.Experimental results illustrate that CWSR outperforms several state-of-the-art methods in terms of both visual quality and quantitative metrics.展开更多
Image super-resolution (SR) is one of the classic computer vision tasks. This paper proposes a super-resolution network based on adaptive frequency component upsampling, named SR-AFU. The network is composed of multip...Image super-resolution (SR) is one of the classic computer vision tasks. This paper proposes a super-resolution network based on adaptive frequency component upsampling, named SR-AFU. The network is composed of multiple cascaded dilated convolution residual blocks (CDCRB) to extract multi-resolution features representing image semantics, and multiple multi-size convolutional upsampling blocks (MCUB) to adaptively upsample different frequency components using CDCRB features. The paper also defines a new loss function based on the discrete wavelet transform, making the reconstructed SR images closer to human perception. Experiments on the benchmark datasets show that SR-AFU has higher peak signal to noise ratio (PSNR), significantly faster training speed and more realistic visual effects compared with the existing methods.展开更多
Structured illumination microscopy(SIM)is a popular and powerful super-resolution(SR)technique in biomedical research.However,the conventional reconstruction algorithm for SIM heavily relies on the accurate prior know...Structured illumination microscopy(SIM)is a popular and powerful super-resolution(SR)technique in biomedical research.However,the conventional reconstruction algorithm for SIM heavily relies on the accurate prior knowledge of illumination patterns and signal-to-noise ratio(SNR)of raw images.To obtain high-quality SR images,several raw images need to be captured under high fluorescence level,which further restricts SIM’s temporal resolution and its applications.Deep learning(DL)is a data-driven technology that has been used to expand the limits of optical microscopy.In this study,we propose a deep neural network based on multi-level wavelet and attention mechanism(MWAM)for SIM.Our results show that the MWAM network can extract high-frequency information contained in SIM raw images and accurately integrate it into the output image,resulting in superior SR images compared to those generated using wide-field images as input data.We also demonstrate that the number of SIM raw images can be reduced to three,with one image in each illumination orientation,to achieve the optimal tradeoff between temporal and spatial resolution.Furthermore,our MWAM network exhibits superior reconstruction ability on low-SNR images compared to conventional SIM algorithms.We have also analyzed the adaptability of this network on other biological samples and successfully applied the pretrained model to other SIM systems.展开更多
Super-resolution(SR)algorithms address the inabilities of poor imaging devices,there by producing high quality images with enhanced resolution.We propose a new SR approach which produces sharp high resolution(HR)image...Super-resolution(SR)algorithms address the inabilities of poor imaging devices,there by producing high quality images with enhanced resolution.We propose a new SR approach which produces sharp high resolution(HR)image using its low resolution(LR)counterparts.The proposed method uses geometric duality for spatially adapting covariance-based interpolation(CBI).To preserve edge information,a multi-stage cascaded joint bilateral filter(MSCJBF)is proposed as an intermediary stage.These edges are incorporated in the high frequency subbands obtained by the stationary wavelet transform(SWT),through nearest neighbor interpolation(NNI)method.Prior to the NNI process,the high frequency subbands undergo two-lobed lanczos interpolation to achieve the desired resolution enhancement.The quantitative and qualitative analysis for various test images prove the superiority of our method.展开更多
In this article algebraic multigrid as preconditioners are designed, with biorthogonal wavelets, as intergrid operators for the Krylov subspace iterative methods. Construction of hierarchy of matrices in algebraic mul...In this article algebraic multigrid as preconditioners are designed, with biorthogonal wavelets, as intergrid operators for the Krylov subspace iterative methods. Construction of hierarchy of matrices in algebraic multigrid context is based on lowpass filter version of Wavelet Transform. The robustness and efficiency of this new approach is tested by applying it to large sparse, unsymmetric and ill-conditioned matrices from Tim Davis collection of sparse matrices. Proposed preconditioners have potential in reducing cputime, operator complexity and storage space of algebraic multigrid V-cycle and meet the desired accuracy of solution compared with that of orthogonal wavelets.展开更多
In this paper, we present the construction of purely algebraic Daubechies wavelet based preconditioners for Krylov subspace iterative methods to solve linear sparse system of equations. Effective preconditioners are d...In this paper, we present the construction of purely algebraic Daubechies wavelet based preconditioners for Krylov subspace iterative methods to solve linear sparse system of equations. Effective preconditioners are designed with DWTPerMod algorithm by knowing size of the matrix and the order of Daubechies wavelet. A notable feature of this algorithm is that it enables wavelet level to be chosen automatically making it more robust than other wavelet based preconditioners and avoids user choosing a level of transform. We demonstrate the efficiency of these preconditioners by applying them to several matrices from Tim Davis collection of sparse matrices for restarted GMRES.展开更多
基金Supported by the National Natural Science Foundation of China(No.61901183)Fundamental Research Funds for the Central Universities(No.ZQN921)+4 种基金Natural Science Foundation of Fujian Province Science and Technology Department(No.2021H6037)Key Project of Quanzhou Science and Technology Plan(No.2021C008R)Natural Science Foundation of Fujian Province(No.2019J01010561)Education and Scientific Research Project for Young and Middle-aged Teachers of Fujian Province 2019(No.JAT191080)Science and Technology Bureau of Quanzhou(No.2017G046)。
文摘Convolutional neural networks(CNNs) have shown great potential for image super-resolution(SR).However,most existing CNNs only reconstruct images in the spatial domain,resulting in insufficient high-frequency details of reconstructed images.To address this issue,a channel attention based wavelet cascaded network for image super-resolution(CWSR) is proposed.Specifically,a second-order channel attention(SOCA) mechanism is incorporated into the network,and the covariance matrix normalization is utilized to explore interdependencies between channel-wise features.Then,to boost the quality of residual features,the non-local module is adopted to further improve the global information integration ability of the network.Finally,taking the image loss in the spatial and wavelet domains into account,a dual-constrained loss function is proposed to optimize the network.Experimental results illustrate that CWSR outperforms several state-of-the-art methods in terms of both visual quality and quantitative metrics.
基金supported by the National Natural Science Foundation of China(Grant Nos.61603197 and 61772284)Natural Science Foundation of Nanjing University of Posts and Telecommunications(NY221071).
文摘Image super-resolution (SR) is one of the classic computer vision tasks. This paper proposes a super-resolution network based on adaptive frequency component upsampling, named SR-AFU. The network is composed of multiple cascaded dilated convolution residual blocks (CDCRB) to extract multi-resolution features representing image semantics, and multiple multi-size convolutional upsampling blocks (MCUB) to adaptively upsample different frequency components using CDCRB features. The paper also defines a new loss function based on the discrete wavelet transform, making the reconstructed SR images closer to human perception. Experiments on the benchmark datasets show that SR-AFU has higher peak signal to noise ratio (PSNR), significantly faster training speed and more realistic visual effects compared with the existing methods.
基金supported by the National Natural Science Foundation of China(Grant Nos.62005307 and 61975228).
文摘Structured illumination microscopy(SIM)is a popular and powerful super-resolution(SR)technique in biomedical research.However,the conventional reconstruction algorithm for SIM heavily relies on the accurate prior knowledge of illumination patterns and signal-to-noise ratio(SNR)of raw images.To obtain high-quality SR images,several raw images need to be captured under high fluorescence level,which further restricts SIM’s temporal resolution and its applications.Deep learning(DL)is a data-driven technology that has been used to expand the limits of optical microscopy.In this study,we propose a deep neural network based on multi-level wavelet and attention mechanism(MWAM)for SIM.Our results show that the MWAM network can extract high-frequency information contained in SIM raw images and accurately integrate it into the output image,resulting in superior SR images compared to those generated using wide-field images as input data.We also demonstrate that the number of SIM raw images can be reduced to three,with one image in each illumination orientation,to achieve the optimal tradeoff between temporal and spatial resolution.Furthermore,our MWAM network exhibits superior reconstruction ability on low-SNR images compared to conventional SIM algorithms.We have also analyzed the adaptability of this network on other biological samples and successfully applied the pretrained model to other SIM systems.
文摘Super-resolution(SR)algorithms address the inabilities of poor imaging devices,there by producing high quality images with enhanced resolution.We propose a new SR approach which produces sharp high resolution(HR)image using its low resolution(LR)counterparts.The proposed method uses geometric duality for spatially adapting covariance-based interpolation(CBI).To preserve edge information,a multi-stage cascaded joint bilateral filter(MSCJBF)is proposed as an intermediary stage.These edges are incorporated in the high frequency subbands obtained by the stationary wavelet transform(SWT),through nearest neighbor interpolation(NNI)method.Prior to the NNI process,the high frequency subbands undergo two-lobed lanczos interpolation to achieve the desired resolution enhancement.The quantitative and qualitative analysis for various test images prove the superiority of our method.
文摘In this article algebraic multigrid as preconditioners are designed, with biorthogonal wavelets, as intergrid operators for the Krylov subspace iterative methods. Construction of hierarchy of matrices in algebraic multigrid context is based on lowpass filter version of Wavelet Transform. The robustness and efficiency of this new approach is tested by applying it to large sparse, unsymmetric and ill-conditioned matrices from Tim Davis collection of sparse matrices. Proposed preconditioners have potential in reducing cputime, operator complexity and storage space of algebraic multigrid V-cycle and meet the desired accuracy of solution compared with that of orthogonal wavelets.
文摘In this paper, we present the construction of purely algebraic Daubechies wavelet based preconditioners for Krylov subspace iterative methods to solve linear sparse system of equations. Effective preconditioners are designed with DWTPerMod algorithm by knowing size of the matrix and the order of Daubechies wavelet. A notable feature of this algorithm is that it enables wavelet level to be chosen automatically making it more robust than other wavelet based preconditioners and avoids user choosing a level of transform. We demonstrate the efficiency of these preconditioners by applying them to several matrices from Tim Davis collection of sparse matrices for restarted GMRES.
