Fast Reconstruction Method Research Articles

Comparative analysis of machine learning models for particle flow reconstruction

Abstract. Using the simulation data of different calorimeters, we investigate the use of machine learning and python algorithms for the simulation and reconstruction of particle flow energy in high-energy physics. We train models based on simulated pixel value image instead of common numerical data. We define two models that use different Regressor algorithms. Multi-layer Perceptron (MLP) Regressor offer stable and accurate prediction under less affection situation. Convolutional Neutral Networks (CNN) Regressor provided better and stronger modeling and reconstruction ability; however, it could cause overfitting results in certain situations. Furthermore, we optimize our models with the use of PyTorch. These models can serve as fast method for particle flow reconstruction in future studies and experiments.

Mining Association Rules on Time-sensitive Data

Real-world data is continuously produced andcollected quickly; hence, mining association rules are used tofind relationships between item sets. One of these combinedrule mining techniques is Rare Association Rule Mining(RARM), a method that extracts rare, combined rules with lowsupport but high confidence from the database. Additionally,a large amount of time-sensitive data is created in many fields,and combining valid and outdated data leads to low efficiencyin extracting combined rules. This paper explores a miningmethod that increases rare, combined rules on time-sensitivedata to extract common and rare patterns in the database.The primary approach of the research proposes a new treestructure called ILC-tree, inspired by the LC-tree structurepublished in 2022. Specifically, our approach includes a newtree structure and a fast reconstruction method. The proposedapproach reduces execution time and memory consumptionby approximately 2 times compared to the old tree structure.

Maximum-correntropy-based sequential method for fast neural population activity reconstruction in the cortex from incomplete abnormally-disturbed noisy measurements

This paper continues to explore the membrane potential reconstruction and pattern recognition problem in a neural tissue modeled by Stochastic Dynamic Neural Field (SDNF) equation. Although recent research has suggested an efficient solution based on the state-space approach through nonlinear Bayesian filtering framework, it is becoming extremely difficult to ignore the existence of non-Gaussian uncertainties in the SDNFs as well as the stability problem of neuronal population dynamics to outliers. Motivated by recent events in signal processing and mathematical neuroscience, this paper explores the SDNFs in a presence of non-Gaussian uncertainties, which is the shot noise case, where the corrupted data might appear due to broken sensors. We derive the “distributionally robust” state estimator for the membrane potential reconstruction process that is the Maximum Correntropy Criterion Extended Kalman Filter (MCC-EKF) as well as its fast and numerically robust (to roundoff) implementation method by using the sequential principle of processing the measurement vectors. The numerical experiments are provided to illustrate the performance of the novel estimation methods.

Fast radiance field reconstruction from sparse inputs

Neural Radiance Field (NeRF) has emerged as a powerful method in data-driven 3D reconstruction because of its simplicity and state-of-the-art performance. However, NeRF requires densely captured calibrated images and lengthy training and rendering time to realize high-resolution reconstruction. Thus, we propose a fast radiance field reconstruction method from a sparse set of images with silhouettes. Our approach integrates NeRF with Shape from Silhouette, a traditional 3D reconstruction method that uses silhouette information to fit the shape of an object. To combine NeRF’s implicit representation with Shape from Silhouette’s explicit representation, we propose a novel explicit–implicit radiance field representation consisting of voxel grids with confidence and feature embedding for geometry and a multilayer perceptron network to decode view-dependent color emission for appearance. We propose to make the reconstructed geometry compact by taking advantage of silhouette images, which can avoid the majority of artifacts in sparse input scenarios and speed up training and rendering. We also apply voxel dilating and pruning to refine the geometry prediction. In addition, we impose a total variation regularization on our model to encourage a smooth radiance field. Experiments on the DTU and the NeRF-Synthetic datasets show that our algorithm surpasses the existing baselines in terms of efficiency and accuracy.

Validity of a fast automated 3d spine reconstruction measurements for biplanar radiographs: SOSORT 2024 award winner.

To validate a fast 3D biplanar spinal radiograph reconstruction method with automatic extract curvature parameters using artificial intelligence (AI). Three-hundred eighty paired, posteroanterior and lateral, radiographs from the EOS X-ray system of children with adolescent idiopathic scoliosis were randomly selected from the database. For the AI model development, 304 paired images were used for training; 76 pairs were employed for testing. The validation was evaluated by comparing curvature parameters, including Cobb angles (CA), apical axial vertebral rotation (AVR), kyphotic angle (T1-T12 KA), and lordotic angle (L1-L5 LA), to manual measurements from a rater with 8years of scoliosis experience. The mean absolute differences ± standard deviation (MAD ± SD), the percentage of measurements within the clinically acceptable errors, the standard error of measurement (SEM), and the inter-method intraclass correlation coefficient ICC[2,1] were calculated. The average reconstruction speed of the 76 test images was recorded. Among the 76 test images, 134 and 128 CA were exported automatically and measured manually, respectively. The MAD ± SD for CA, AVR at apex, KA, and LA were 3.3° ± 3.5°, 1.5° ± 1.5°, 3.3° ± 2.6° and 3.5° ± 2.5°, respectively, and 98% of these measurements were within the clinical acceptance errors. The SEMs and the ICC[2,1] for the compared parameters were all less than 0.7° and > 0.94, respectively. The average time to display the 3D spine and report the measurements was 5.2 ± 1.3s. The developed AI algorithm could reconstruct a 3D scoliotic spine within 6s, and the automatic curvature parameters were accurately and reliably extracted from the reconstructed images.

Enhancing online dose distribution reconstruction in radiotherapy through sparse sampled rotating fiber arrays and deep learning

A optical fiber array dosimeter based on radiation-induced luminescence can be used in two-dimensional dose distribution measurements. However, using rotating fiber arrays introduces challenges in terms of online monitoring and variations in detector performance due to the long data acquisition time. This study aims to propose and demonstrate a novel method for online fast reconstruction of two-dimensional dose distributions in radiation therapy using projection data obtained from sparsely sampled rotating fiber arrays. The projection data were processed in both the projection and image domains to achieve restoration and noise reduction by deep learning techniques. The performance of the proposed method was evaluated using simulation data obtained by Monte Carlo toolkit Geant4 and experimental data obtained from a medical accelerator. Results showed that the method can successfully reconstruct dose distribution through sparse sampling and reduce the measurement time to one-sixth of the original. The peak signal-to-noise ratio, root mean square error, and structural similarity index were 23.72, 2.68, and 0.95, respectively. Additionally, the 3%/3 mm gamma pass rate reached 98.4% under specific irradiation conditions with a dose of at least 10% of the maximum dose. The integration of sparse sampling techniques, rotating fiber arrays, and deep learning techniques offers new possibilities for the fast and efficient reconstruction of two-dimensional dose distributions, ensuring high-quality radiotherapy outcomes.

A method for fast reconstruction of closed section workpiece surface using point clouds

Parameterized reconstruction of workpiece surfaces is a critical step for advanced manufacturing applications, such as the solving of machining parameters, and the expression of workpiece in situ measurement. Generally, the point clouds model is easy to obtain and can be seen as the source model of the workpiece, and the B-spline surface is always taken as the ideal target parameterized model. Existing research focuses on reconstructing the single-valued surface, which can be projected onto a spatial plane without overlapping. However, the dual-valued surface, which overlaps at least twice, is also commonly encountered in industry, and has few investigations. Therefore, this paper proposes a fast reconstruction method based on reasonable segmentation and parameter domain mapping. In this approach, first, the dual-valued point clouds model is segmented into multiple single-valued point clouds models according to the sought edges in the optimal attitude. Then, the grid point coordinates of the single-valued point clouds model are calculated using the parametric-domain moving least squares method. Finally, the B-spline surface is generated by interpolating these grid points. The proposed algorithm is applied to single-bending closed-section workpieces such as the turbine blade to illustrate the effectiveness of this method. The contrast results with existing method demonstrate that the proposed approach can reconstruct the workpiece with multi-valued surfaces more quickly and more accurately, which is significant in advanced manufacturing.

Two-and-a-half order score-based model for solving 3D ill-posed inverse problems

Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) are crucial technologies in the field of medical imaging. Score-based models demonstrated effectiveness in addressing different inverse problems encountered in the field of CT and MRI, such as sparse-view CT and fast MRI reconstruction. However, these models face challenges in achieving accurate three dimensional (3D) volumetric reconstruction. The existing score-based models predominantly concentrate on reconstructing two-dimensional (2D) data distributions, resulting in inconsistencies between adjacent slices in the reconstructed 3D volumetric images. To overcome this limitation, we propose a novel two-and-a-half order score-based model (TOSM). During the training phase, our TOSM learns data distributions in 2D space, simplifying the training process compared to working directly on 3D volumes. However, during the reconstruction phase, the TOSM utilizes complementary scores along three directions (sagittal, coronal, and transaxial) to achieve a more precise reconstruction. The development of TOSM is built on robust theoretical principles, ensuring its reliability and efficacy. Through extensive experimentation on large-scale sparse-view CT and fast MRI datasets, our method achieved state-of-the-art (SOTA) results in solving 3D ill-posed inverse problems, averaging a 1.56 dB peak signal-to-noise ratio (PSNR) improvement over existing sparse-view CT reconstruction methods across 29 views and 0.87 dB PSNR improvement over existing fast MRI reconstruction methods with × 2 acceleration. In summary, TOSM significantly addresses the issue of inconsistency in 3D ill-posed problems by modeling the distribution of 3D data rather than 2D distribution which has achieved remarkable results in both CT and MRI reconstruction tasks.

Compressive hyperspectral imaging based on Images Structure Similarity and deep image prior

In this paper, the structural similarity between RGB image and spectral image is studied, and a non-iterative Images Structure Similarity(ISS) method for fast reconstruction of spectral image is proposed. At the same time, the input of the Deep Image Prior (DIP) method is optimized for the first time by using the initial spectral data reconstructed by ISS. It raises the starting value of the iteration. Specifically, we take the RGB image data as the base of the spectral data, and solve the base coefficient by the least square method to quickly estimate the initial hyperspectral image. The Gaussian noise data is replaced by the estimated initial spectral data to constrain the solution space of the network and reduce the number of iterations. Finally, the structural similarity between RGB image and spectral image is used. The RGB three-channel graph is used to filter the iterative results to improve the reconstruction quality. Experimental results show that compared with other hyperspectral imaging methods, the proposed method can improve the quality of reconstruction in both spectral resolution and spatial resolution. In addition, compared with other methods based on Deep Image Prior (DIP), our improvement greatly reduces the reconstruction time and is more suitable for actual snapshot spectral imaging.

Fourier Single-Pixel Imaging Based on Online Modulation Pattern Binarization

Down-sampling Fourier single-pixel imaging is typically achieved by truncating the Fourier spectrum, where exclusively the low-frequency Fourier coefficients are extracted while discarding the high-frequency components. However, the truncation of the Fourier spectrum can lead to an undesired ringing effect in the reconstructed result. Moreover, the original Fourier single-pixel imaging necessitated grayscale Fourier basis patterns for illumination. This requirement limits imaging speed because digital micromirror devices (DMDs) generate grayscale patterns at a lower refresh rate. In order to solve the above problem, a fast and high-quality Fourier single-pixel imaging reconstruction method is proposed in the paper. In the method, the threshold binarization of the Fourier base pattern is performed online to improve the DMD refresh rate, and the reconstruction quality of Fourier single-pixel imaging at a low-sampling rate is improved by generating an adversarial network. This method enables fast reconstruction of target images with higher quality despite low-sampling rates. Compared with conventional Fourier single-pixel imaging, numerical simulation and experimentation demonstrate the effectiveness of the proposed method. Notably, this method is particularly significant for fast Fourier single-pixel imaging applications.

Fast laser field reconstruction method based on a Gerchberg–Saxton algorithm with mode decomposition

Knowledge of the electric field of femtosecond, high intensity laser pulses is of paramount importance to study the interaction of this class of lasers with matter. A hybrid method to reconstruct the laser field from fluence measurements in the transverse plane at multiple positions along the propagation axis is presented, combining a Hermite–Gauss mode decomposition (MD) and elements of the Gerchberg–Saxton algorithm (GSA). The proposed GSA-MD takes into account the pointing instabilities of high intensity laser systems by tuning the centers of the HG modes. Furthermore, it quickly builds a field description by progressively increasing the number of modes and thus the accuracy of the field reconstruction. The results of field reconstruction using the GSA-MD are shown to be in excellent agreement with experimental measurements from two different high peak power laser facilities.

Dictionary Fields: Learning a Neural Basis Decomposition

We present Dictionary Fields, a novel neural representation which decomposes a signal into a product of factors, each represented by a classical or neural field representation, operating on transformed input coordinates. More specifically, we factorize a signal into a coefficient field and a basis field, and exploit periodic coordinate transformations to apply the same basis functions across multiple locations and scales. Our experiments show that Dictionary Fields lead to improvements in approximation quality, compactness, and training time when compared to previous fast reconstruction methods. Experimentally, our representation achieves better image approximation quality on 2D image regression tasks, higher geometric quality when reconstructing 3D signed distance fields, and higher compactness for radiance field reconstruction tasks. Furthermore, Dictionary Fields enable generalization to unseen images/3D scenes by sharing bases across signals during training which greatly benefits use cases such as image regression from partial observations and few-shot radiance field reconstruction.

Multi-grid representation with field regularization for self-supervised surface reconstruction from point clouds

Surface reconstruction from point clouds plays a crucial role in computer vision. The current state-of-the-art methods solve this problem by learning signed distance functions (SDFs) with ground truth distance supervisions, which are difficult to obtain. Moreover, most recent works represent each shape with a single or several latent codes, which fail to provide detailed guidance to reconstruct the local geometry. To address these issues, we propose MGSDF, a novel method for high-fidelity and fast surface reconstruction from raw point clouds. Specifically, we design a scalable representation with learnable hierarchical feature grids to capture multi-level geometric details. We introduce a self-supervised learning scheme that optimizes the SDF directly from the raw point cloud by pulling the space onto the surface. In addition, we propose a field regularization constraint on the predicted distance values and gradients on the zero-level set of SDFs for robust optimization. Our experimental results demonstrate significant improvements over the state-of-the-art in surface reconstruction from clean, noisy and varying density point clouds under widely used benchmarks.

A Simple Switching-Event Dependent High-Frequency Sampling Method for Power Conversion System

Precise current and voltage sensing are challenging for digital control in high-frequency power conversion systems. Given that the power electronics circuitry is triggered repetitively by power device switching events, a switching-time dependent sampling method is proposed to realize an equivalent high-frequency signal sampling with a low-speed Analog Digital Converter (ADC) and digital controller. Two sampling modes are developed in the proposed methods in terms of sampling rates lower and higher than the digital controller clock frequency, respectively. A fast and simple signal reconstruction method is designed to ensure the feasibility in a low-cost processor. A series-resonant dual-active-bridge (SR-DAB) is taken as an example for the theoretical analysis and experimental verification. The resonant current and Miller plateau voltage in the topology are sampled to verify the potential of the proposed method for online parameter recognition of DC-DC converters and device behavior monitoring of power devices.

Fast reconstruction method for defect profiles of ferromagnetic materials based on metal magnetic memory technique

In this paper, a fast reconstruction method for surface defect profiles of ferromagnetic materials is proposed based on the metal magnetic memory technology. An improved magnetic charge model that can adapt to rectangular and V-shaped defect profiles and a new particle swarm optimization algorithm based on a chaotic initial distribution, sigmoid inertia weight coefficient, and sine cosine acceleration coefficients are established as the forward model and iterative means of the method, respectively. The proposed method is verified with theoretical and experimental data, and the influence of noise is considered. The reconstruction method has good accuracy, repeatability, and robustness.

Double total variation (DTV) regularization and Improved adaptive moment estimation (IADAM) optimization method for fast MR image reconstruction

Background and ObjectiveCompressed sensing has been extensively studied as an advanced technique for fast MR image reconstruction. Current reconstruction algorithms often use total variation as the regularization term. Traditional total variation can easily lead to a staircase effect because it only pays attention to the variational information of the horizontal and vertical subbands. MethodsIn this paper, we propose a novel algorithm to reduce the staircase effect by increasing the variational information of the two diagonal subbands, which named Double Total Variation (DTV). We optimize the conjugate gradient algorithm by Improved Adaptive Moment Estimation (IADAM) as the solution algorithm. ResultsMR images of three body parts (head, knee and ankle) were used for simulations under different acceleration factor conditions. The conjugate gradient and fast conjugate gradient series algorithms were selected for comparison experiments. The results showed that the improved adaptive moment estimation conjugate gradient combined with DTV achieves the best reconstruction performance, therefore proved the superiority of DTV. After that, 64 different MR images of the three body parts were further simulated and the results demonstrated the general superiority from the proposed algorithm. ConclusionsThe results of this study support that the proposed method may facilitate the development of the research field of image reconstruction algorithms and provide ideas for other algorithmic improvements.

Fast reconstruction method of three-dimension model based on dual RGB-D cameras for peanut plant

BackgroundPlant shape and structure are important factors in peanut breeding research. Constructing a three-dimension (3D) model can provide an effective digital tool for comprehensive and quantitative analysis of peanut plant structure. Fast and accurate are always the goals of the plant 3D model reconstruction research.ResultsWe proposed a 3D reconstruction method based on dual RGB-D cameras for the peanut plant 3D model quickly and accurately. The two Kinect v2 were mirror symmetry placed on both sides of the peanut plant, and the point cloud data obtained were filtered twice to remove noise interference. After rotation and translation based on the corresponding geometric relationship, the point cloud acquired by the two Kinect v2 was converted to the same coordinate system and spliced into the 3D structure of the peanut plant. The experiment was conducted at various growth stages based on twenty potted peanuts. The plant traits’ height, width, length, and volume were calculated through the reconstructed 3D models, and manual measurement was also carried out during the experiment processing. The accuracy of the 3D model was evaluated through a synthetic coefficient, which was generated by calculating the average accuracy of the four traits. The test result showed that the average accuracy of the reconstructed peanut plant 3D model by this method is 93.42%. A comparative experiment with the iterative closest point (ICP) algorithm, a widely used 3D modeling algorithm, was additionally implemented to test the rapidity of this method. The test result shows that the proposed method is 2.54 times faster with approximated accuracy compared to the ICP method.ConclusionsThe reconstruction method for the 3D model of the peanut plant described in this paper is capable of rapidly and accurately establishing a 3D model of the peanut plant while also meeting the modeling requirements for other species' breeding processes. This study offers a potential tool to further explore the 3D model for improving traits and agronomic qualities of plants.

Fast Mesh Reconstruction from Single View Based on GCN and Topology Modification

3D reconstruction based on single view aims to reconstruct the entire 3D shape of an object from one perspective. When existing methods reconstruct the mesh surface of complex objects, the surface details are difficult to predict and the reconstruction visual effect is poor because the mesh representation is not easily integrated into the deep learning framework; the 3D topology is easily limited by predefined templates and inflexible, and unnecessary mesh self-intersections and connections will be generated when reconstructing complex topology, thus destroying the surface details; the training of the reconstruction network is limited by the large amount of information attached to the mesh vertices, and the training time of the reconstructed network is too long. In this paper, we propose a method for fast mesh reconstruction from single view based on Graph Convolutional Network (GCN) and topology modification. We use GCN to ensure the generation of high-quality mesh surfaces and use topology modification to improve the flexibility of the topology. Meanwhile, a feature fusion method is proposed to make full use of the features of each stage of the image hierarchically. We use 3D open dataset ShapeNet to train our network and add a new weight parameter to speed up the training process. Extensive experiments demonstrate that our method can not only reconstruct object meshes on complex topological surfaces, but also has better qualitative and quantitative results.

Inversion of the Gravity Gradiometry Data by ResUnet Network: An Application in Nordkapp Basin, Barents Sea

The study and assessment of the subsurface density distribution are vital for mining and oil & gas exploration. This can be achieved by the three-dimensional (3D) inversion of the observed gravity and gravity gradiometry (GG) data. Due to the ill-posedness of the geophysical inverse problem, the nonuniqueness and instability of solutions represent the main difficulties in inversion. In recent years, convolutional neural networks, especially U-net technology, have found wide applications in image processing, recognition, and reconstruction. This paper proposes using this method for fast reconstruction of the subsurface density models based on the ResUnet technology. The developed new method was examined on two 3D synthetic gravity and gravity gradiometry datasets inversion. The results show that the ResUnet network can reconstruct the density anomaly with sharp boundaries and is robust to the noise, making the solution stable.

Deep parallel MRI reconstruction based on a complex-valued loss function

To propose a new method for fast MRI reconstruction based on deep learning in parallel MRI data using a new loss function defined as the summation of the mean squared errors of the magnitude and phase. The multicoil image data were combined into single-coil image data to eliminate the correlation between noises and used as a label in the training process. Considering the importance of the phase information in some applications, where the phase information was lost when combining multicoil data using sum of square method, a new loss function was introduced, defined as the weighted sum of the mean squared error (MSE) of the magnitude and phase. The single weight in the loss function was used to balance the importance of the magnitude and phase in different applications. To validate the proposed method, real brain and knee data in FastMRI dataset were used for training and testing. We also compared this proposed method with two other methods that used MSE or mean absolute error (MAE) as a loss function. The experimental results showed that the proposed method was capable of accurate reconstruction of multicoil MR images with significantly reduced artifacts compared with the other two methods. Quantitative analysis showed that the propose method increased the peak signal-to-noise ratio (PSNR) of the reconstructed images by about 1 dB. The proposed deep MRI reconstruction method using a new loss function to fit the noise in parallel MRI data can accelerate MRI reconstruction and significantly improve the quality of the reconstructed images.