Reconstruction Framework Research Articles

Unsupervised Bidirectional Contrastive Reconstruction and Adaptive Fine-Grained Channel Attention Networks for image dehazing

Recently, Unsupervised algorithms has achieved remarkable performance in image dehazing. However, the CycleGAN framework can lead to confusion in generator learning due to inconsistent data distributions, and the DisentGAN framework lacks effective constraints on generated images, resulting in the loss of image content details and color distortion. Moreover, Squeeze and Excitation channel attention employs only fully connected layers to capture global information, lacking interaction with local information, resulting in inaccurate feature weight allocation for image dehazing. To solve the above problems, in this paper, we propose an Unsupervised Bidirectional Contrastive Reconstruction and Adaptive Fine-Grained Channel Attention Networks (UBRFC-Net). Specifically, an Unsupervised Bidirectional Contrastive Reconstruction Framework (BCRF) is proposed, aiming to establish bidirectional contrastive reconstruction constraints, not only to avoid the generator learning confusion in CycleGAN but also to enhance the constraint capability for clear images and the reconstruction ability of the unsupervised dehazing network. Furthermore, an Adaptive Fine-Grained Channel Attention (FCA) is developed to utilize the correlation matrix to capture the correlation between global and local information at various granularities promotes interaction between them, achieving more efficient feature weight assignment. Experimental results on challenging benchmark datasets demonstrate the superiority of our UBRFC-Net over state-of-the-art unsupervised image dehazing methods. This study successfully introduces an enhanced unsupervised image dehazing approach, addressing limitations of existing methods and achieving superior dehazing results. The source code is available at https://github.com/Lose-Code/UBRFC-Net.

A novel framework for three-dimensional electrical impedance tomography reconstruction of maize ear via feature reconfiguration and residual networks.

Electrical impedance tomography (EIT) provides an indirect measure of the physiological state and growth of the maize ear by reconstructing the distribution of electrical impedance. However, the two-dimensional (2D) EIT within the electrode plane finds it challenging to comprehensively represent the spatial distribution of conductivity of the intact maize ear, including the husk, kernels, and cob. Therefore, an effective method for 3D conductivity reconstruction is necessary. In practical applications, fluctuations in the contact impedance of the maize ear occur, particularly with the increase in the number of grids and computational workload during the reconstruction of 3D spatial conductivity. These fluctuations may accentuate the ill-conditioning and nonlinearity of the EIT. To address these challenges, we introduce RFNetEIT, a novel computational framework specifically tailored for the absolute imaging of the three-dimensional electrical impedance of maize ear. This strategy transforms the reconstruction of 3D electrical conductivity into a regression process. Initially, a feature map is extracted from measured boundary voltage via a data reconstruction module, thereby enhancing the correlation among different dimensions. Subsequently, a nonlinear mapping model of the 3D spatial distribution of the boundary voltage and conductivity is established, utilizing the residual network. The performance of the proposed framework is assessed through numerical simulation experiments, acrylic model experiments, and maize ear experiments. Our experimental results indicate that our method yields superior reconstruction performance in terms of root-mean-square error (RMSE), correlation coefficient (CC), structural similarity index (SSIM), and inverse problem-solving time (IPST). Furthermore, the reconstruction experiments on maize ears demonstrate that the method can effectively reconstruct the 3D conductivity distribution.

Breaking the limitations with sparse inputs by variational frameworks (BLIss) in terahertz super-resolution 3D reconstruction

Data acquisition, image processing, and image quality are the long-lasting issues for terahertz (THz) 3D reconstructed imaging. Existing methods are primarily designed for 2D scenarios, given the challenges associated with obtaining super-resolution (SR) data and the absence of an efficient SR 3D reconstruction framework in conventional computed tomography (CT). Here, we demonstrate BLIss, a new approach for THz SR 3D reconstruction with sparse 2D data input. BLIss seamlessly integrates conventional CT techniques and variational framework with the core of the adapted Euler-Elastica-based model. The quantitative 3D image evaluation metrics, including the standard deviation of Gaussian, mean curvatures, and the multi-scale structural similarity index measure (MS-SSIM), validate the superior smoothness and fidelity achieved with our variational framework approach compared with conventional THz CT modal. Beyond its contributions to advancing THz SR 3D reconstruction, BLIss demonstrates potential applicability in other imaging modalities, such as X-ray and MRI. This suggests extensive impacts on the broader field of imaging applications.

Improving the Machine Learning Performance for Image Recognition Using a New Set of Mountain Fourier Moments

The orthogonal moments are giving relevant results of these last years within the framework of object detection, pattern recognition and image reconstruction. This article is based on orthogonal functions called "Orthogonal Mountain functions (OMFs)" and we introduce a new set of moments called the multichannel Mountain Fourier moments (MMFMs), their performance is in reconstruction, noise invariants, rotation, scale and translation for image color. To validate these proposed techniques, we made several experimental tests to analyse images. We compare the results obtained from invariant moments and other current orthogonal invariant moments; the experiments show the power of the proposed moments.

ANALYSIS OF THE CURRENT PROBLEMS OF PASSENGER AIR TRANSPORT DEVELOPMENT IN UKRAINE IN WARTIME CONDITIONS

The subject of the study is the impact of the full-scale military invasion and aggression of the Russian Federation on passenger air transportation in Ukraine. Passenger air transportation in Ukraine has been seriously challenged by the full-scale military invasion of Ukraine by the Russian Federation, accompanied by changes in infrastructure and passenger demand. The research’s relevance lies in determining strategic ways of solving problems caused by the state of war. The aggression of the Russian Federation against Ukraine led to significant disturbances in the field of passenger air transportation. The destruction of infrastructure, changes in passenger demand, and challenges for the aviation industry create a need for a systemic analysis and determination of ways out of this complex situation. The research aims to deeply analyse modern problems and determine the prospects for developing passenger air transportation in wartime conditions and post-war reconstruction. The authors aim to develop practical recommendations for optimising the sector and maintaining its sustainability. Objectives of the study include examining the consequences of military aggression on aviation infrastructure and analysing changes in the structure of demand; identifying the challenges that arise for air carriers and other industry participants in martial law; exploring adaptation strategies for passenger aviation and determining ways out of the crisis; assessing the necessity and effectiveness of measures to restore and support passenger air transport. To achieve the goal, the authors used a comprehensive approach that includes assessing the state of the infrastructure and applying quantitative research methods. As a result, the authors determined the impact of military aggression on aviation infrastructure, analysed changes in passenger demand, and identified challenges for the aviation industry. The study reveals the possibilities of adaptation and strategies for exiting the crisis. Based on the analysis, the authors conclude the need for urgent measures to restore and support passenger air transportation within the framework of post-war reconstruction. Recommendations include strategies for infrastructure modernisation, financial support for airlines, and the creation of conditions for international cooperation. The active role of the state in solving these issues is also vital to achieving sustainable development of the aviation sector. Keywords: aviation sector, passenger air transportation, martial law, aviation infrastructure modernisation strategies.

An Improved OMP Algorithm for Enhancing the Anti-Interference Performance of Array Antennas.

The demand for precise positioning in noisy environments has propelled the development of research on array antenna radar systems. Although the orthogonal matching pursuit (OMP) algorithm demonstrates superior performance in signal reconstruction, its application efficacy in noisy settings faces challenges. Consequently, this paper introduces an innovative OMP algorithm, DTM_OMP_ICA (a dual-threshold mask OMP algorithm based on independent component analysis), which optimizes the OMP signal reconstruction framework by utilizing two different observation bases in conjunction with independent component analysis (ICA). By implementing a mean mask strategy, it effectively denoises signals received by array antennas in noisy environments. Simulation results reveal that compared to traditional OMP algorithms, the DTM_OMP_ICA algorithm shows significant advantages in noise suppression capability and algorithm stability. Under optimal conditions, this algorithm achieves a noise suppression rate of up to 96.8%, with its stability also reaching as high as 99%. Furthermore, DTM_OMP_ICA surpasses traditional denoising algorithms in practical denoising applications, proving its effectiveness in reconstructing array antenna signals in noisy settings. This presents an efficient method for accurately reconstructing array antenna signals against a noisy backdrop.

The promises and pitfalls of disaster aid platforms: a case study of Lebanon’s 3RF

PurposeUsing critical disaster studies and state theory, we assess the disaster aid platform named Lebanon Reconstruction, Reform and Recovery Framework (3RF) that was put in place by international donors in the aftermath of the Beirut Port Blast in August 2020, in order to examine the effectiveness of its inclusive decision-making architecture, as well as its institutional building and legislative reform efforts.Design/methodology/approachThe paper uses the case study approaach and relies on two original data sets compiled by authors, using desk reviews of academic literature and secondary data, in addition to 24 semi-structured expert interviews and participant observation for two years.FindingsThe aid platform appears innovative, participatory and effectively functioning toward recovery and reform. However, in practice, the government dismisses CSOs, undermines reforms and dodges state building, whereas the 3RF is structured in incoherent ways and operates according to conflicting logics, generating inertia and pitfalls that hinder effective participatory governance, prevent institutional building, and delay the making of projects.Research limitations/implicationsThe research contributes to critical scholarship as it addresses an important research gap concerning disaster aid platforms’ institutional design and governance that are under-studied in critical disaster studies and political studies. It also highlights the need for critical disaster studies to engage with state theory and vice-versa.Practical implicationsThe research contributes to evaluations of disaster recovery processes and outcomes. It highlights the limits of disaster aid platforms’ claims for participatory decision-making, institutional-building and reforms.Originality/valueThe paper amplifies critical disaster studies, through the reflexive analysis of a case-study of an aid platform.

Evolutionary probability density reconstruction of stochastic dynamic responses based on physics-aided deep learning

Probability density evolution is the vital probabilistic information for stochastic dynamic system. However, it may face big challenges when using numerical methods to solve the generalized probability density evolution equation (GDEE) of complicated real-world system under complex excitations. Recently, physics-informed deep learning has gained popularity in solving partial differential equations due to the superior approximation and generalization capabilities, which opens a promising intelligent way to solve the GDEE. In this work, a mesh-free learning model, i.e., Phy-EPDNN, is proposed for evolutionary probability density (EPD) reconstruction, where a normalized GDEE is derived and embedded in the developed network as the prior physical knowledge. The computational domain can be customized by users on demand, in which the GDEE is not required to be solved in the whole computational domain as that in numerical methods. There is no need of boundary and initial conditions for the proposed model. A data augmentation method is also proposed to obtain sufficient collection data for supervised learning. Three specially selected analytical models and two practical scenarios verify the potential applicability of the proposed general framework for EPD reconstruction. Parametric analysis is performed to discuss the influence of the major network parameters on reconstruction performance.

Plug-and-Play latent feature editing for orientation-adaptive quantitative susceptibility mapping neural networks

Quantitative susceptibility mapping (QSM) is a post-processing technique for deriving tissue magnetic susceptibility distribution from MRI phase measurements. Deep learning (DL) algorithms hold great potential for solving the ill-posed QSM reconstruction problem. However, a significant challenge facing current DL-QSM approaches is their limited adaptability to magnetic dipole field orientation variations during training and testing. In this work, we propose a novel Orientation-Adaptive Latent Feature Editing (OA-LFE) module to learn the encoding of acquisition orientation vectors and seamlessly integrate them into the latent features of deep networks. Importantly, it can be directly Plug-and-Play (PnP) into various existing DL-QSM architectures, enabling reconstructions of QSM from arbitrary magnetic dipole orientations. Its effectiveness is demonstrated by combining the OA-LFE module into our previously proposed phase-to-susceptibility single-step instant QSM (iQSM) network, which was initially tailored for pure-axial acquisitions. The proposed OA-LFE-empowered iQSM, which we refer to as iQSM+, is trained in a simulated-supervised manner on a specially-designed simulation brain dataset. Comprehensive experiments are conducted on simulated and in vivo human brain datasets, encompassing subjects ranging from healthy individuals to those with pathological conditions. These experiments involve various MRI platforms (3T and 7T) and aim to compare our proposed iQSM+ against several established QSM reconstruction frameworks, including the original iQSM. The iQSM+ yields QSM images with significantly improved accuracies and mitigates artifacts, surpassing other state-of-the-art DL-QSM algorithms. The PnP OA-LFE module’s versatility was further demonstrated by its successful application to xQSM, a distinct DL-QSM network for dipole inversion. In conclusion, this work introduces a new DL paradigm, allowing researchers to develop innovative QSM methods without requiring a complete overhaul of their existing architectures.

LMD: Faster Image Reconstruction with Latent Masking Diffusion

As a class of fruitful approaches, diffusion probabilistic models (DPMs) have shown excellent advantages in high-resolution image reconstruction. On the other hand, masked autoencoders (MAEs), as popular self-supervised vision learners, have demonstrated simpler and more effective image reconstruction and transfer capabilities on downstream tasks. However, they all require extremely high training costs, either due to inherent high temporal-dependence (i.e., excessively long diffusion steps) or due to artificially low spatial-dependence (i.e., human-formulated high mask ratio, such as 0.75). To the end, this paper presents LMD, a faster image reconstruction framework with Latent Masking Diffusion. First, we propose to project and reconstruct images in latent space through a pre-trained variational autoencoder, which is theoretically more efficient than in the pixel-based space. Then, we combine the advantages of MAEs and DPMs to design a progressive masking diffusion model, which gradually increases the masking proportion by three different schedulers and reconstructs the latent features from simple to difficult, without sequentially performing denoising diffusion as in DPMs or using fixed high masking ratio as in MAEs, so as to alleviate the high training time-consumption predicament. Our approach allows for learning high-capacity models and accelerate their training (by 3x or more) and barely reduces the original accuracy. Inference speed in downstream tasks also significantly outperforms the previous approaches.

NeuSurf: On-Surface Priors for Neural Surface Reconstruction from Sparse Input Views

Recently, neural implicit functions have demonstrated remarkable results in the field of multi-view reconstruction. However, most existing methods are tailored for dense views and exhibit unsatisfactory performance when dealing with sparse views. Several latest methods have been proposed for generalizing implicit reconstruction to address the sparse view reconstruction task, but they still suffer from high training costs and are merely valid under carefully selected perspectives. In this paper, we propose a novel sparse view reconstruction framework that leverages on-surface priors to achieve highly faithful surface reconstruction. Specifically, we design several constraints on global geometry alignment and local geometry refinement for jointly optimizing coarse shapes and fine details. To achieve this, we train a neural network to learn a global implicit field from the on-surface points obtained from SfM and then leverage it as a coarse geometric constraint. To exploit local geometric consistency, we project on-surface points onto seen and unseen views, treating the consistent loss of projected features as a fine geometric constraint. The experimental results with DTU and BlendedMVS datasets in two prevalent sparse settings demonstrate significant improvements over the state-of-the-art methods.

Self-Supervised 3D Human Mesh Recovery from a Single Image with Uncertainty-Aware Learning

Despite achieving impressive improvement in accuracy, most existing monocular 3D human mesh reconstruction methods require large-scale 2D/3D ground-truths for supervision, which limits their applications on unlabeled in-the-wild data that is ubiquitous. To alleviate the reliance on 2D/3D ground-truths, we present a self-supervised 3D human pose and shape reconstruction framework that relies only on self-consistency between intermediate representations of images and projected 2D predictions. Specifically, we extract 2D joints and depth maps from monocular images as proxy inputs, which provides complementary clues to infer accurate 3D human meshes. Furthermore, to reduce the impacts from noisy and ambiguous inputs while better concentrate on the high-quality information, we design an uncertainty-aware module to automatically learn the reliability of the inputs at body-joint level based on the consistency between 2D joints and depth map. Experiments on benchmark datasets show that our approach outperforms other state-of-the-art methods at similar supervision levels.

Full-Body Motion Reconstruction with Sparse Sensing from Graph Perspective

Estimating 3D full-body pose from sparse sensor data is a pivotal technique employed for the reconstruction of realistic human motions in Augmented Reality and Virtual Reality. However, translating sparse sensor signals into comprehensive human motion remains a challenge since the sparsely distributed sensors in common VR systems fail to capture the motion of full human body. In this paper, we use well-designed Body Pose Graph (BPG) to represent the human body and translate the challenge into a prediction problem of graph missing nodes. Then, we propose a novel full-body motion reconstruction framework based on BPG. To establish BPG, nodes are initially endowed with features extracted from sparse sensor signals. Features from identifiable joint nodes across diverse sensors are amalgamated and processed from both temporal and spatial perspectives. Temporal dynamics are captured using the Temporal Pyramid Structure, while spatial relations in joint movements inform the spatial attributes. The resultant features serve as the foundational elements of the BPG nodes. To further refine the BPG, node features are updated through a graph neural network that incorporates edge reflecting varying joint relations. Our method's effectiveness is evidenced by the attained state-of-the-art performance, particularly in lower body motion, outperforming other baseline methods. Additionally, an ablation study validates the efficacy of each module in our proposed framework.

Abstract 6236: Systems biology modeling identifies SMARCD3 as a master regulator facilitating everolimus resistance in ER+ breast cancer

Abstract Breast cancer is the most common malignancy in women and estrogen receptor positive (ER+) breast cancers represent nearly 75% of all breast tumors. Everolimus, an mTORC1 inhibitor, in combination with exemestane has been approved for patients with metastatic ER+ breast cancer. However, many patients eventually develop resistance to everolimus and leads to poor survival outcomes. Characterizing everolimus-resistant cells can reveal targetable molecular phenotypes that can eventually lead to new therapeutic targets. In this study, we elucidate systems-level phenotypic distinctions between everolimus sensitive and refractory cells. We generated several isogenic ER+ breast cancer cell lines resistant or sensitive to everolimus. We then leveraged transcriptomic profiles from sensitive and resistant cells before or after everolimus treatment to decipher the underlying mechanisms essential to the resistant state. Using linear mixed effect models, we identified several meta-phenotypes that were distinct between sensitive and resistant cell states. These included growth-factor signaling, cell cycle, metabolism, stemness, and apoptosis meta-phenotypes. Our analyses also identified strong activation of growth-factor receptors including IGF1R/INSR and ESR1 in the resistant cells, which were maintained despite everolimus treatment. Next, we adopted a transcriptional regulatory network reconstruction framework to identify the master regulators responsible for the activation of resistance meta-phenotypes. We identified SMARCD3 as the key master regulator controlling expression of genes across diverse resistance meta-phenotypes, including growth-factor signaling. Further, using transcriptomic profiles from a neoadjuvant trial of 23 post-menopausal ER+ breast cancers treated with everolimus, we found that SMARCD3 expression was elevated in resistant tumors. To confirm the role of SMARCD3 in everolimus resistance, we repressed transcription of the SMARCD3 gene using CRISPR interference to re-sensitize resistant cells to everolimus treatment. In conclusion, we used context-specific cell transcriptomic profiles and integrative systems-biology approaches to elucidate mechanisms of resistance in response to everolimus treatment in ER+ breast cancer. Our findings suggest SMARCD3 upregulation promotes resistance to everolimus treatment and may serve as a novel therapeutic target in ER+ breast cancer. Citation Format: Eric F. Medina, Patrick A. Cosgrove, Eleni Farmaki, Vince K. Grolmusz, Feng Chi, Jason I. Griffiths, Andrea H. Bild, Aritro Nath. Systems biology modeling identifies SMARCD3 as a master regulator facilitating everolimus resistance in ER+ breast cancer [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 6236.

Highly robust reconstruction framework for three-dimensional optical imaging based on physical model constrained neural networks

Objective. The reconstruction of three-dimensional optical imaging that can quantitatively acquire the target distribution from surface measurements is a serious ill-posed problem. Traditional regularization-based reconstruction can solve such ill-posed problem to a certain extent, but its accuracy is highly dependent on a prior information, resulting in a less stable and adaptable method. Data-driven deep learning-based reconstruction avoids the errors of light propagation models and the reliance on experience and a prior by learning the mapping relationship between the surface light distribution and the target directly from the dataset. However, the acquisition of the training dataset and the training of the network itself are time consuming, and the high dependence of the network performance on the training dataset results in a low generalization ability. The objective of this work is to develop a highly robust reconstruction framework to solve the existing problems. Approach. This paper proposes a physical model constrained neural networks-based reconstruction framework. In the framework, the neural networks are to generate a target distribution from surface measurements, while the physical model is used to calculate the surface light distribution based on this target distribution. The mean square error between the calculated surface light distribution and the surface measurements is then used as a loss function to optimize the neural network. To further reduce the dependence on a priori information, a movable region is randomly selected and then traverses the entire solution interval. We reconstruct the target distribution in this movable region and the results are used as the basis for its next movement. Main Results. The performance of the proposed framework is evaluated with a series of simulations and in vivo experiment, including accuracy robustness of different target distributions, noise immunity, depth robustness, and spatial resolution. The results collectively demonstrate that the framework can reconstruct targets with a high accuracy, stability and versatility. Significance. The proposed framework has high accuracy and robustness, as well as good generalizability. Compared with traditional regularization-based reconstruction methods, it eliminates the need to manually delineate feasible regions and adjust regularization parameters. Compared with emerging deep learning assisted methods, it does not require any training dataset, thus saving a lot of time and resources and solving the problem of poor generalization and robustness of deep learning methods. Thus, the framework opens up a new perspective for the reconstruction of three-dimension optical imaging.

Increasing the scan-efficiency of pulmonary imaging at 0.55 T using iterative concomitant field and motion-corrected reconstruction.

To develop an iterative concomitant field and motion corrected (iCoMoCo) reconstruction for isotropic high-resolution UTE pulmonary imaging at 0.55 T. A free-breathing golden-angle stack-of-spirals UTE sequence was used to acquire data for 8 min with prototype and commercial 0.55 T MRI scanners. The data was binned into 12 respiratory phases based on superior-inferior navigator readouts. The previously published iterative motion corrected (iMoCo) reconstruction was extended to include concomitant field correction directly in the cost function. The reconstruction was implemented within the Gadgetron framework for inline reconstruction. Data were retrospectively reconstructed to simulate scan times of 2, 4, 6, and 8 min. Image quality was assessed using apparent SNR and image sharpness. The technique was evaluated in healthy volunteers and patients with known lung pathology including coronavirus disease 2019 infection, chronic granulomatous disease, lymphangioleiomyomatosis, and lung nodules. The technique provided diagnostic-quality images, and image quality was maintained with a slight loss in SNR for simulated scan times down to 4 min. Parenchymal apparent SNR was 4.33 ± 0.57, 5.96 ± 0.65, 7.36 ± 0.64, and 7.87 ± 0.65 using iCoMoCo with scan times of 2, 4, 6, and 8 min, respectively. Image sharpness at the diaphragm was comparable between iCoMoCo and reference images. Concomitant field corrections visibly improved the sharpness of anatomical structures away from the isocenter. Inline image reconstruction and artifact correction were achieved in <5 min. The proposed iCoMoCo pulmonary imaging technique can generate diagnostic quality images with 1.75 mm isotropic resolution in less than 5 min using a 6-min acquisition, on a 0.55 T scanner.

Model-based iterative reconstruction for direct imaging with point spread function encoded echo planar MRI

BackgroundEcho planar imaging (EPI) is a fast measurement technique commonly used in magnetic resonance imaging (MRI), but is highly sensitive to measurement non-idealities in reconstruction. Point spread function (PSF)-encoded EPI is a multi-shot strategy which alleviates distortion, but acquisition of encodings suitable for direct distortion-free imaging prolongs scan time. In this work, a model-based iterative reconstruction (MBIR) framework is introduced for direct imaging with PSF-EPI to improve image quality and acceleration potential. MethodsAn MBIR platform was developed for accelerated PSF-EPI. The reconstruction utilizes a subspace representation, is regularized to promote local low-rankedness (LLR), and uses variable splitting for efficient iteration. Comparisons were made against standard reconstructions from prospectively accelerated PSF-EPI data and with retrospective subsampling. Exploring aggressive partial Fourier acceleration of the PSF-encoding dimension, additional comparisons were made against an extension of Homodyne to direct PSF-EPI in numerical experiments. A neuroradiologists' assessment was completed comparing images reconstructed with MBIR from retrospectively truncated data directly against images obtained with standard reconstructions from non-truncated datasets. ResultsImage quality results were consistently superior for MBIR relative to standard and Homodyne reconstructions. As the MBIR signal model and reconstruction allow for arbitrary sampling of the PSF space, random sampling of the PSF-encoding dimension was also demonstrated, with quantitative assessments indicating best performance achieved through nonuniform PSF sampling combined with partial Fourier. With retrospective subsampling, MBIR reconstructs high-quality images from sub-minute scan datasets. MBIR was shown to be superior in a neuroradiologists' assessment with respect to three of five performance criteria, with equivalence for the remaining two. ConclusionsA novel image reconstruction framework is introduced for direct imaging with PSF-EPI, enabling arbitrary PSF space sampling and reconstruction of diagnostic-quality images from highly accelerated PSF-encoded EPI data.

The One-Point-One-Line geometry for robust and efficient line segment correspondence

Three-dimensional (3D) lines are common elements in artificial scenes and serve as basic, yet essential features for structural 3D reconstruction. The crucial step of 3D line reconstruction, namely two-view line segment matching, still faces challenges in terms of both accuracy and efficiency improvements. Therefore, robust and efficient constraints are needed to establish valid line candidates. This paper introduces a novel geometry constraint called “one-point-one-line geometry” (OPOL) to enhance the precision of line matching and reduce computational complexity. OPOL offers two remarkable advantages: (1) It takes point orientations as the constraint, which is not only invariant to projective transformations, but also alleviates computational requirements. (2) It needs only one point match to construct the geometry constraint, thus both the grouping and validation are greatly reduced. Additionally, we incorporate the line sweep strategy into OPOL, leveraging depth and space constraints derived from existing 3D points to further enhance efficiency. Extensive experiments conducted on large-coverage and high-resolution images (as large as 10336 × 7788 pixels) demonstrated that OPOL matched lines within a second for an image pair. Both quantitative and qualitative results also demonstrated the superior accuracy and efficiency performance of OPOL. We integrated OPOL into multiple view line reconstruction frameworks, and the promising experimental results reveal the performance of OPOL for robust line reconstruction. The OPOL code is publicly available at https://github.com/JoeAlexxxxx/OPOL.

A hierarchical multi-UAV cooperative framework for infrastructure inspection and reconstruction

Unmanned aerial vehicles (UAVs) are emerging as a powerful tool for inspections and repair works in large-scale and unstructured 3D infrastructures, but current approaches take a long time to cover the entire area. Planning using UAVs for inspections and repair works puts forward a requirement of improving time efficiency in large-scale and cluster environments. This paper presents a hierarchical multi-UAV cooperative framework for infrastructure inspection and reconstruction to balance the workload and reduce the overall task completion time. The proposed framework consists of two stages, the exploration stage and the exploitation stage, resolving the task in a sequential manner. At the exploration stage, the density map is developed to update global and local information for dynamic load-balanced area partition based on reconstructability and relative positions of UAVs, and the Voronoi-based planner is used to enable the UAVs to reach their best region. After obtaining the global map, viewpoints are generated and divided while taking into account the battery capacity of each UAV. Finally, a shortest path planning method is used to minimize the total traveling cost of these viewpoints for obtaining a high-quality reconstruction. Several experiments are conducted in both a simulated and real environment to show the time efficiency, robustness, and effectiveness of the proposed method. Furthermore, the whole system is implemented in real applications.

3D-MRI super-resolution reconstruction using multi-modality based on multi-resolution CNN

Background and ObjectiveHigh-resolution (HR) MR images provide rich structural detail to assist physicians in clinical diagnosis and treatment plan. However, it is arduous to acquire HR MRI due to equipment limitations, scanning time or patient comfort. Instead, HR MRI could be obtained through a number of computer assisted post-processing methods that have proven to be effective and reliable. This paper aims to develop a convolutional neural network (CNN) based super-resolution reconstruction framework for low-resolution (LR) T2w images. MethodIn this paper, we propose a novel multi-modal HR MRI generation framework based on deep learning techniques. Specifically, we construct a CNN based on multi-resolution analysis to learn an end-to-end mapping between LR T2w and HR T2w, where HR T1w is fed into the network to offer detailed a priori information to help generate HR T2w. Furthermore, a low-frequency filtering module is introduced to filter out the interference from HR-T1w during high-frequency information extraction. Based on the idea of multi-resolution analysis, detailed features extracted from HR T1w and LR T2w are fused at two scales in the network and then HR T2w is reconstructed by upsampling and dense connectivity module. ResultsExtensive quantitative and qualitative evaluations demonstrate that the proposed method enhances the recovered HR T2w details and outperforms other state-of-the-art methods. In addition, the experimental results also suggest that our network has a lightweight structure and favorable generalization performance. ConclusionThe results show that the proposed method is capable of reconstructing HR T2w with higher accuracy. Meanwhile, the super-resolution reconstruction results on other dataset illustrate the excellent generalization ability of the method.