Quality Of Reconstructed Images Research Articles

HoloDiffusion: Sparse Digital Holographic Reconstruction via Diffusion Modeling

In digital holography, reconstructed image quality can be primarily limited due to the inability of a single small aperture sensor to cover the entire field of a hologram. The use of multi-sensor arrays in synthetic aperture digital holographic imaging technology contributes to overcoming the limitations of sensor coverage by expanding the area for detection. However, imaging accuracy is affected by the gap size between sensors and the resolution of sensors, especially when dealing with a limited number of sensors. An image reconstruction method is proposed that combines physical constraint characteristics of the imaging object with a score-based diffusion model, aiming to enhance the imaging accuracy of digital holography technology with extremely sparse sensor arrays. Prior information of the sample is learned by the neural network in the diffusion model to obtain a score function, which alternately constrains the iterative reconstruction process with the underlying physical model. The results demonstrate that the structural similarity and peak signal-to-noise ratio of the reconstructed images using this method are higher than the traditional method, along with a strong generalization ability.

Unsupervised reconstruction with a registered time-unsheared image constraint for compressed ultrafast photography

Compressed ultrafast photography (CUP) is a computational imaging technology capable of capturing transient scenes in picosecond scale with a sequence depth of hundreds of frames. Since the inverse problem of CUP is an ill-posed problem, it is challenging to further improve the reconstruction quality under the condition of high noise level and compression ratio. In addition, there are many articles adding an external charge-coupled device (CCD) camera to the CUP system to form the time-unsheared view because the added constraint can improve the reconstruction quality of images. However, since the images are collected by different cameras, slight affine transformation may have great impacts on the reconstruction quality. Here, we propose an algorithm that combines the time-unsheared image constraint CUP system with unsupervised neural networks. Image registration network is also introduced into the network framework to learn the affine transformation parameters of input images. The proposed algorithm effectively utilizes the implicit image prior in the neural network as well as the extra hardware prior information brought by the time-unsheared view. Combined with image registration network, this joint learning model enables our proposed algorithm to further improve the quality of reconstructed images without training datasets. The simulation and experiment results demonstrate the application prospect of our algorithm in ultrafast event capture.

Research on Human Lung Impedance Tomography Based on Soft Thresholding Image Segmentation and Reduced-Order Tikhonov Regularization

The lung is one of the most vital organs in the human body, and its condition is closely correlated with overall health. Electrical impedance tomography (EIT), as a biomedical imaging technique, often produces low-quality reconstructed images due to its inherent ill-posedness in solving the inverse problem. To address this issue, this paper proposes a soft-threshold region segmentation algorithm with a relaxation factor. This algorithm segments the reconstructed lung images into internal regions, edge regions, and background regions, resulting in clearer boundaries in the reconstructed images. This facilitates the intuitive identification of regions of interest by healthcare professionals. Additionally, this segmentation algorithm is suitably combined with a dimension-reduced Tikhonov regularization algorithm. By utilizing the joint capabilities of these algorithms, the partition points belonging to the background region can be excluded from the sought grayscale vector, thereby improving the ill-posedness of the image reconstruction process and enhancing the quality of image reconstruction. Finally, a 16-electrode human lung EIT simulation model is established for the thoracic region and verified through simulation. Experimental validation is conducted using a human lung tank simulation platform to further demonstrate the effectiveness of the proposed method.

A Multi-Hyperspectral Image Collaborative Mapping Model Based on Adaptive Learning for Fine Classification

Hyperspectral (HS) data, encompassing hundreds of spectral channels for the same area, offer a wealth of spectral information and are increasingly utilized across various fields. However, their limitations in spatial resolution and imaging width pose challenges for precise recognition and fine classification in large scenes. Conversely, multispectral (MS) data excel in providing spatial details for vast landscapes but lack spectral precision. In this article, we proposed an adaptive learning-based mapping model, including an image fusion module, spectral super-resolution network, and adaptive learning network. Spectral super-resolution networks learn the mapping between multispectral and hyperspectral images based on the attention mechanism. The image fusion module leverages spatial and spectral consistency in training data, providing pseudo labels for spectral super-resolution training. And the adaptive learning network incorporates spectral response priors via unsupervised learning, adjusting the output of the super-resolution network to preserve spectral information in reconstructed data. Through the experiment, the model eliminates the need for the manual setting of image prior information and complex parameter selection, and can adjust the network structure and parameters dynamically, eventually enhancing the reconstructed image quality, and enabling the fine classification of large-scale scenes with high spatial resolution. Compared with the recent dictionary learning and deep learning spectral super-resolution methods, our approach exhibits superior performance in terms of both image similarity and classification accuracy.

Hide Digital Images in Encrypted Image Files After Two Stages

This paper introduces a novel encryption technique for concealing digital images within encrypted files through a two-stage process. The methodology incorporates sparse coding and compressive sensing, leveraging a learned dictionary to recover the sparse coding of plain images. Comprising compressive sampling and random projection with a Gaussian measurement matrix, the approach achieves joint compression and encryption. Pseudorandom encryption and chaos-based block scrambling are subsequently applied to produce the final encrypted image. Experimental results using 256 × 256 test photographs from the USC-SIPI dataset demonstrate the superiority of the proposed method in terms of both Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM). The study also conducts key sensitivity analysis, revealing the method's susceptibility to changes in the secret key, and statistical attack analysis, demonstrating its robustness against attacks exploiting statistical information. In conclusion, the proposed encryption technique not only ensures cryptographic strength but also excels in image reconstruction quality, making it a promising solution for secure image transmission and storage

Super-resolution reconstruction method of the optical synthetic aperture image using generative adversarial network

Abstract In order to solve the contradiction between large aperture elements and high-resolution images, in this study, we propose an improved image-resolution method based on generative adversarial network (GAN). First, we analyze the imaging principle of the optical synthetic aperture. Further, we improve a super-resolution GAN; especially, this network uses a multi-scale convolutional cascade to obtain global features of the image, and a multi-scale receptive field block and residual in residual dense block are built to obtain image details. In addition, this study uses the Mish function as the activation function of the discriminator to solve the problems of neuron extreme, gradient explosion, and poor generalization ability of the model. Through simulation, the results show that the proposed method can achieve a peak signal-to-noise ratio (PSNR) of 30 dB compared with traditional image super-resolution reconstruction methods for synthetic aperture image. The method proposed has an improvement of 2 dB in the PSNR and 0.016 in structure similarity index measure compared with the original super-resolution GAN. Therefore, this method can effectively reduce the image distortion and improve the quality of image reconstruction.

Optical fiber bundle differential compressive imaging.

We present a differential compressive imaging method for an optical fiber bundle (OFB), which provides a solution for an ultrathin bend-resistant endoscope with high resolution. This method uses an OFB and a diffuser to generate speckle illumination patterns. Differential operation is additionally applied to the speckle patterns to produce sensing matrices, by which the correlation between the matrices is greatly reduced from 0.875 to 0.0275, which ensures the high quality of image reconstruction. Pixilation artifacts from the fiber core arrangement are also effectively eliminated with this configuration. We demonstrate high-resolution reconstruction of images of 132 × 132 pixels with a compression rate of 12% using 77 fiber cores, the total diameter of which is only about 91 µm. An experimental verification proves that this method is tolerant to a limited degree of fiber bending, which provides a potential approach for robust high-resolution fiber endoscopy.

Fast high quality computational ghost imaging based on saliency variable sampling detection

Fast computational ghost imaging with high quality and ultra-high-definition resolution reconstructed images has important application potential in target tracking, biological imaging and other fields. However, as far as we know, the resolution (pixels) of the reconstructed image is related to the number of measurements. And the limited resolution of reconstructed images at low measurement times hinders the application of computational ghost imaging. Therefore, in this work, a new computational ghost imaging method based on saliency variable sampling detection is proposed to achieve high-quality imaging at low measurement times. This method physically variable samples the salient features and realizes compressed detection of computational ghost imaging based on the salient periodic features of the bucket detection signal. Numerical simulation and experimental results show that the reconstructed image quality of our method is similar to the compressed sensing method at low measurement times. Even at 500 (sampling rate 0.76%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$0.76\\%$$\\end{document}) measurement times, the reconstructed image of the method still has the target features. Moreover, the 2160×4096\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$2160\ imes 4096$$\\end{document} (4K) pixels ultra-high-definition resolution reconstructed images can be obtained at only a sampling rate of 0.11%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$0.11\\%$$\\end{document}. This method has great potential value in real-time detection and tracking, biological imaging and other fields.

Split Bregman quantum noise removal algorithm for 3D reconstruction of neutron computed tomography image

The low intensity of the neutron source for neutron computed tomography (CT) results in a long acquisition time for a single projection, which causes the neutron projection data to contain a large amount of quantum noise. Quantum noise will degrade the quality of neutron CT reconstruction images. Therefore, an efficient quantum noise removal algorithm must be used in CT reconstruction. In this paper, an efficient quantum noise removal algorithm for neutron CT 3D image reconstruction is proposed by analysing classical image processing algorithms and quantum image processing algorithms, which employs the maximum likelihood expectation maximization to reconstruct the image and split Bregman algorithm to solve for the total variation (MLEM-SBTV). Experimental results show that MLEM-SBTV performs well in removing quantum noise and reconstructing the detailed structure of images.

Sparse-view cone-beam computed tomography iterative reconstruction based on new multi-gradient direction total variation.

The accurate reconstruction of cone-beam computed tomography (CBCT) from sparse projections is one of the most important areas for study. The compressed sensing theory has been widely employed in the sparse reconstruction of CBCT. However, the total variation (TV) approach solely uses information from the i-coordinate, j-coordinate, and k-coordinate gradients to reconstruct the CBCT image. It is well recognized that the CBCT image can be reconstructed more accurately with more gradient information from different directions. Thus, this study introduces a novel approach, named the new multi-gradient direction total variation minimization method. The method uses gradient information from the ij-coordinate, ik-coordinate, and jk-coordinate directions to reconstruct CBCT images, which incorporates nine different types of gradient information from nine directions. This study assessed the efficacy of the proposed methodology using under-sampled projections from four different experiments, including two digital phantoms, one patient's head dataset, and one physical phantom dataset. The results indicated that the proposed method achieved the lowest RMSE index and the highest SSIM index. Meanwhile, we compared the voxel intensity curves of the reconstructed images to assess the edge structure preservation. Among the various methods compared, the curves generated by the proposed method exhibited the highest level of consistency with the gold standard image curves. In summary, the proposed method showed significant potential in enhancing the quality and accuracy of CBCT image reconstruction.

Fast System Matrix Generation Based on Single Angle Calibration in Open-Sided Field Free Line Magnetic Particle Imaging.

Open-sided field-free line magnetic particle imaging (OS FFL MPI) is a novel medical imaging system configuration that has received significant attention in recent years. However, the measurement-based system matrix (SM) image reconstruction for OS FFL MPI typically requires multiple angle calibration (MAC), which is time-consuming in practice. To address this issue, we propose a fast 2D SM generation method that requires only a single angle calibration (SAC). The SAC method exploits the rotational invariance of the system function. Based on the measured single angle system function, the system function is rotated to generate system functions at other angles, and then the SM for image reconstruction is constructed. Then, we conducted various simulation experiments and built an OS FFL MPI scanner to evaluate the proposed SAC method. The experiments demonstrating the effectiveness of SAC in reducing calibration workload, requiring fewer scanning numbers while maintaining a similar image reconstruction quality compared to MAC method. Furthermore, the SM generated by SAC produces consistent imaging results with the SM generated by MAC, regardless of the interpolation algorithms, the number of rotation angles, or the signal-to-noise ratios employed in phantom imaging experiments. SAC has been experimentally verified to reduce acquisition time while maintaining accurate and robust reconstruction performance. The significance of SAC lies in its contribution to improving calibration efficiency in OS FFL MPI, potentially facilitating the implementation of MPI in a wider range of applications.

Sparse Bayesian Deep Learning for Cross Domain Medical Image Reconstruction

Cross domain medical image reconstruction aims to address the issue that deep learning models trained solely on one source dataset might not generalize effectively to unseen target datasets from different hospitals. Some recent methods achieve satisfactory reconstruction performance, but often at the expense of extensive parameters and time consumption. To strike a balance between cross domain image reconstruction quality and model computational efficiency, we propose a lightweight sparse Bayesian deep learning method. Notably, we apply a fixed-form variational Bayes (FFVB) approach to quantify pixel-wise uncertainty priors derived from degradation distribution of the source domain. Furthermore, by integrating the uncertainty prior into the posterior sampled through stochastic gradient Langevin dynamics (SGLD), we develop a training strategy that dynamically generates and optimizes the prior distribution on the network weights for each unseen domain. This strategy enhances generalizability and ensures robust reconstruction performance. When evaluated on medical image reconstruction tasks, our proposed approach demonstrates impressive performance across various previously unseen domains.

An Efficient Image Compression Technique using Long Short-Term Memory Networks (LSTM)

The emergence of big data has imposed significant challenges on data storage and transmission. One pressing issue is leveraging deep learning techniques to achieve superior compression ratios and enhance image quality. Recurrent Neural Networks (RNNs) offer a promising avenue for controlling image bit rates iteratively, thereby enhancing compression performance. However, integrating Long Short-Term Memory (LSTM) into RNNs to address long-term dependencies increases model complexity. To expedite training and enhance image reconstruction quality, this study proposes several innovations.Initially, we enhance the activation function within LSTM to more effectively manage information retention and omission, thereby reducing parameter count and expediting training. Additionally, we introduce an image recovery block within the decoder to reconstruct high-resolution images. Finally, to expedite loss convergence, we replace L1 loss with SmoothL1 loss. Experimental outcomes demonstrate the efficacy of our approach, showcasing higher compression ratios

Uncertainty-Aware GAN for Single Image Super Resolution

Generative adversarial network (GAN) has become a popular tool in the perceptual-oriented single image super-resolution (SISR) for its excellent capability to hallucinate details. However, the performance of most GAN-based SISR methods is impeded due to the limited discriminative ability of their discriminators. In specific, these discriminators only focus on the global image reconstruction quality and ignore the more fine-grained reconstruction quality for constraining the generator, as they predict the overall realness of an image instead of the pixel-level realness. Here, we first introduce the uncertainty into the GAN and propose an Uncertainty-aware GAN (UGAN) to regularize SISR solutions, where the challenging pixels with large reconstruction uncertainty and importance (e.g., texture and edge) are prioritized for optimization. The uncertainty-aware adversarial training strategy enables the discriminator to capture the pixel-level SR uncertainty, which constrains the generator to focus on image areas with high reconstruction difficulty, meanwhile, it improves the interpretability of the SR. To balance weights of multiple training losses, we introduce an uncertainty-aware loss weighting strategy to adaptively learn the optimal loss weights. Extensive experiments demonstrate the effectiveness of our approach in extracting the SR uncertainty and the superiority of the UGAN over the state-of-the-arts in terms of the reconstruction accuracy and perceptual quality.

High-Fidelity Diffusion-Based Image Editing

Diffusion models have attained remarkable success in the domains of image generation and editing. It is widely recognized that employing larger inversion and denoising steps in diffusion model leads to improved image reconstruction quality. However, the editing performance of diffusion models tends to be no more satisfactory even with increasing denoising steps. The deficiency in editing could be attributed to the conditional Markovian property of the editing process, where errors accumulate throughout denoising steps. To tackle this challenge, we first propose an innovative framework where a rectifier module is incorporated to modulate diffusion model weights with residual features from the original images, thereby providing compensatory information to bridge the fidelity gap. Furthermore, we introduce a novel learning paradigm aimed at minimizing error propagation during the editing process, which trains the editing procedure in a manner similar to denoising score-matching. Extensive experiments demonstrate that our proposed framework and training strategy achieve high-fidelity reconstruction and editing results across various levels of denoising steps, meanwhile exhibits exceptional performance in terms of both quantitative metric and qualitative assessments. Lastly, we explore our model's generalization though several applications like image-to-image translation and out-of-domain image editing.

High quality underwater computational ghost imaging based on speckle decomposition and fusion of reconstructed images

Ghost imaging (GI) is an imaging method that reconstructs object information via light-intensity correlation measurements. The unconventional imaging mechanism of GI makes it suitable for imaging in scattering medium, for instance, turbid liquid, biological tissues, etc. However, the strong background noise in the reconstructed images is still the bottleneck problems. In this paper, we focus on the improvements of the reconstructions in underwater GI and propose a speckle decomposition and fusion method for suppressing the noise. The approach utilized computational ghost imaging framework and dictionary learning to acquire high- and low-frequency components that are better suited for image feature-based reconstruction. Furthermore, once the suitable threshold has been established, the speckles captured from the reference path are decomposed using the Nonsubsampled Contourlet Transform (NSCT). The acquired high- and low-frequency are then correlated with the overall optical intensity that captured by the bucket detectors. Ultimately, a multi-scale inverse NSCT transformation is employed to produce the final fusion-reconstructed image. The quantitative evaluation of the reconstructed image quality was conducted. In contrast to previous methodologies, the proposed method offers significant enhancements of the underwater GI imaging quality.

Chromatic correction for super multi-view 3D display based on diffraction theory.

The traditional analysis method for super multi-view 3D display based on geometric optics, which approximates the lenticular lenses as a series of pinhole structures, ignored the chromatic aberration. In this paper, the optimization method based on diffraction theory is proposed for super multi-view 3D display, where the wavefronts are evaluated accurately by the forward propagation method, and the chromatic aberration of the synthetic viewpoint image is reduced dramatically by the backward reconstruction optimization method (BROM). The optical experiment is performed to verify the feasibility of the method, which is consistent with numerical simulation results. It is proved that the proposed method simulates the physical propagation process of super multi-view 3D display and improves the reconstructed image quality. In the future, it can be used to achieve the super multi-view 3D light field technology with low crosstalk.

Autoencoder-based image compression for wireless sensor networks

This work presents an image compression technique designed for wireless sensor networks (WSNs), leveraging autoencoders and incorporating an error-bound mechanism. The algorithm strategically reduces redundancies in image data, conserving energy by exploiting spatial and temporal correlations within sampled image data through autoencoder features. Precise control over the distortion level in reconstructed images is achieved via the error-bound mechanism, establishing equilibrium between compression rate and reconstruction error. Evaluation results demonstrate comparable image reconstruction fidelity to existing methods (JPEG, JPEG2000, HDPhoto, and an existing Rate-Distortion Balanced approach). The proposed algorithm achieves superior image reconstruction quality at compression ratio rates exceeding 70%, emphasizing a fundamental approach prioritizing heightened reconstructed image quality while balancing compression ratio, distortion, and energy efficiency. Notably, a substantial 50% reduction in overall energy consumption is realized at a compression rate of 38.6%.

Feature Fusion for Multi-Coil Compressed MR Image Reconstruction.

Magnetic resonance imaging (MRI) occupies a pivotal position within contemporary diagnostic imaging modalities, offering non-invasive and radiation-free scanning. Despite its significance, MRI's principal limitation is the protracted data acquisition time, which hampers broader practical application. Promising deep learning (DL) methods for undersampled magnetic resonance (MR) image reconstruction outperform the traditional approaches in terms of speed and image quality. However, the intricate inter-coil correlations have been insufficiently addressed, leading to an underexploitation of the rich information inherent in multi-coil acquisitions. In this article, we proposed a method called "Multi-coil Feature Fusion Variation Network" (MFFVN), which introduces an encoder to extract the feature from multi-coil MR image directly and explicitly, followed by a feature fusion operation. Coil reshaping enables the 2D network to achieve satisfactory reconstruction results, while avoiding the introduction of a significant number of parameters and preserving inter-coil information. Compared with VN, MFFVN yields an improvement in the average PSNR and SSIM of the test set, registering enhancements of 0.2622dB and 0.0021dB respectively. This uplift can be attributed to the integration of feature extraction and fusion stages into the network's architecture, thereby effectively leveraging and combining the multi-coil information for enhanced image reconstruction quality. The proposed method outperforms the state-of-the-art methods on fastMRI dataset of multi-coil brains under a fourfold acceleration factor without incurring substantial computation overhead.

Radio-astronomical image reconstruction with a conditional denoising diffusion model

Context. Reconstructing sky models from dirty radio images for accurate source extraction, including source localization and flux estimation, is a complex yet critical task, and has important applications in galaxy evolution studies at high redshift, particularly in deep extragalactic fields using for example the Atacama Large Millimetre Array (ALMA). With the development of large-scale projects, such as the Square Kilometre Array (SKA), we anticipate the need for more advanced source-extraction methods. Existing techniques, such as CLEAN and PyBDSF, currently struggle to effectively extract faint sources, highlighting the necessity for the development of more precise and robust methods. Aims. The success of the source-extraction process critically depends on the quality and accuracy of image reconstruction. As the imaging process represents an “information-lossy” operator, the reconstruction is characterized by uncertainty. The current study proposes the application of stochastic neural networks for the direct reconstruction of sky models from “dirty” images. This approach allows us to localize radio sources and to determine their fluxes with corresponding uncertainties, providing a potential advancement in the field of radio-source characterization. Methods. We used a dataset of 10 164 images simulated with the CASA tool based on the ALMA Cycle 5.3 antenna configuration. We applied conditional denoising diffusion probabilistic models (DDPMs) to directly reconstruct sky models from these dirty images, and then processed these models using Photutils to extract the coordinates and fluxes of the sources. To test the robustness of the proposed model, which was trained on a fixed water vapor value, we examined its performance under varying levels of water vapor. Results. We demonstrate that the proposed approach is state of the art in terms of source localisation, achieving over 90% completeness at a signal-to-noise ratio (S/N) of as low as 2. Additionally, the described method offers an inherent measure of prediction reliability thanks to the stochastic nature of the chosen model. In terms of flux estimation, the proposed model surpasses PyBDSF in terms of performance, accurately extracting fluxes for 96% of the sources in the test set, a notable improvement over the 57% achieved by CLEAN+ PyBDSF. Conclusions. Conditional DDPMs are a powerful tool for image-to-image translation, yielding accurate and robust characterization of radio sources, and outperforming existing methodologies. While this study underscores the significant potential of DDPMs for applications in radio astronomy, we also acknowledge certain limitations that accompany their use, and suggest directions for further refinement and research.