Multi-contrast magnetic resonance imaging (MRI) has important value in clinical applications because it can reflect comprehensive tissue characterization from anatomy and function to metabolism. Previous studies utilize abundant details in high-resolution (HR) reference (Ref) images to guide the super-resolution (SR) of low-resolution (LR) images, termed multi-contrast MRI SR. Yet, their clinical applications are hindered by: 1) discrepancies in MRI equipment and acquisition protocols across hospitals (which lead to gaps in data distribution), and 2) lack of paired LR and HR images in certain modalities for supervised training. Herein, we rethink multi-contrast MRI from a clinical perspective, and propose an implicit sampling and generation (ISG) network plus an unsupervised fine-tuning (FT) framework. Briefly, the ISG network possesses a powerful representation capability, enabling arbitrary-scale LR inputs and SR outputs. The fine-tuning framework, as a test-time training technique, allows models to be adapted to testing data. Experiments are conducted on two clinical datasets containing amide proton transfer weighted (APTw) images from tumor patients and fluid-attenuated inversion recovery (FLAIR) images from a 5T scanner, respectively. For tumor patients, our ISG+FT proves $4{\times }$ SR capacity in APTw metabolic images, receiving good recognition from radiologists. In both quantitative and qualitative evaluations, ISG+FT outperforms state-of-the-art baselines. The ablation and robustness study further demonstrate the rationality of ISG+FT. Overall, our proposed method shows considerable promise in clinical scenarios.

The 3D perception of satellites, including both their shape and pose, is a key foundation for robotic on-orbit servicing. However, the demanding space environment-such as intense and dim illumination-presents significant challenges. Previous non-cooperative methods focus on specific geometric features like solar panel brackets or docking rings, overlooking the satellite's overall shape and increasing the risk of collisions during grasping. Additionally, satellites are often weakly textured, limiting the accuracy of 3D perception. To address these issues, we propose, for the first time, a 3D perceptionbased visual servo system of non-cooperative satellites. This system combines reconstruction and tracking to enhance shape perception and pose estimation accuracy in orbital conditions. Specifically, we employ an alternating iterative strategy to simultaneously reconstruct and track the satellite and introduce a novel constraint to fuse different cues under extreme conditions. Further, we develop a simulation environment platform, a dualarm microgravity grasping system, and an online monitoring module to enhance system capabilities for on-orbit servicing. Synthetic and real-world datasets from the simulation environment are also created for experimental validation. Results show that each module of our system achieves state-of-the-art performance.

Graph Neural Networks (GNNs) are effective and popular techniques for representation learning of graph data, significantly relying on message passing mechanism. Most GNNs utilize graph convolution with low-pass filtering to update the representation in a coupled way, ignoring the potential interference between attribute and topology. To solve this challenging issue, this study proposes a Flexible Graph Representation Learning (FGRL) method, which adheres to a decoupling and then fusion framework. Specifically, the FGRL utilizes a two-way representation learning scheme to improve the flexibility of message passing by disentangling information in the attribute space and topology space. Beyond low-pass filtering, high-pass filtering information is crucial for node-specific characteristic preservation and also extracted simultaneously. The FGRL mitigates interference between attribute and topological representations by enhancing complementarity with cross-frequency diversity exploration. A more comprehensive and flexible graph embedding representation could be obtained by adaptively fusing attribute, low-pass, and high-pass information. Experimental results demonstrate that the proposed FGRL achieves superior performance in node classification tasks, verifying its discriminative ability in graph representation learning.

With the development of computation methods and the requirement of data processing, it is often required to execute electromagnetic (EM) simulations in a lot of different complex formation models simultaneously. For this purpose, in this article, we advance a contraction high-order Born approximation (CHBA) of scattered EM fields from arbitrary perturbation in conductivity based on the 3-D finite volume method (FVM) of coupled potentials. We manage to apply the CHBA to efficiently and precisely simulate the logging while drilling (LWD) ultra-deep resistivity measurement in multiple perturbation models based on arbitrarily given anisotropic reference models. First, from the energy conservation of the EM fields, we derive the rigorous contraction operator about the modified scattered EM fields through the variable transformations. After that, the modified scattered EM fields are expanded into an unconditionally convergent series. All terms of the series can be obtained by solving the Helmholtz equation with recursively right-hand terms. Then, we apply the relative residuals of the modified scattered EM fields to determine the truncation order of the series and acquire the reliable CHBA solution. The Helmholtz equation is discretized by the 3-D FVM and solved by the parallel direct sparse solver (PARDISO). We thus obtain the EM fields of multiple sources in the multiple perturbation models simultaneously. Finally, the numerical results validate the algorithm and compare the EM responses in multiple perturbation models.

OBJECTIVE: Ankle joint moments are critical in gait analysis, with accurate assessments typically necessitating complex inverse dynamics modeling. Pressure insoles are widely used wearable devices that have shown feasibility in estimating joint angles. However, achieving cost-effective, high-precision estimation of ankle joint moment remains challenging. This study combines genetic algorithm (GA) with deep forest regression (DFR) to optimize the number and layout of plantar pressure sensors, and estimate ankle joint moment based on plantar pressure. METHODS: 26 healthy young participants were recruited to collect motion trajectories, ground reaction forces, and plantar pressure data while walking at fast, medium, and slow speeds. Ten gait cycles per speed per participant were analyzed for ankle joint moments using inverse dynamics, constituting the dataset. An optimization algorithm was constructed by combining GA with DFR, using the fitness function as the objective for sensor number and layout optimization. The leave-one-out cross-validation was employed to evaluate the precision of the model. RESULTS: The highest fitness was achieved with an optimized layout using 9 sensors. The Pearson Correlation Coefficients for the sagittal, coronal, and transverse plane moments were 0.967 ± 0.014, 0.918 ± 0.027, and 0.894 ± 0.073. The optimized layout showed no significant difference in estimation accuracy across various walking speeds (P > 0.05). CONCLUSION: The proposed GA-DFR algorithm is capable of estimating ankle joint moment accurately and optimizing the number and layout of sensors. SIGNIFICANCE: The algorithm and optimized sensor layout enables the accurate and rapid estimation of ankle joint moment from plantar pressure insoles with trade-off approach.

Abstract To help the new media presentation and brand building of Dongguan City memory, a virtual reality modeling model based on multi‐perspective and deep learning is proposed. First, in order to address the issue of imbalanced input and output information in depth map prediction tasks, as well as poor accuracy of predicted depth map boundaries, a depth map prediction model based on multiple perspectives and deep learning is built. Then, a single perspective modeling framework is proposed to address the scarcity of perspectives in practical situations, and a dynamic fusion model is built for single‐view virtual reality scenes based on multi‐view generation networks. The results indicated that the mean square error, average relative error, and average logarithmic error were minimized at 0.52, 0.138, and 0.068, respectively. The multi‐threshold accuracy index demonstrated peak values at 0.772, 0.8821, and 0.947, respectively. The grid simplification algorithm exhibited the shortest running times at 1.57, 2.52, 3.91, and 6.53 s, respectively. Moreover, the single‐view modeling frame displayed the smallest angle distance at 0.1449, while the overlap degree of the point cloud scene reached the highest levels at 77.47, 79.49, 83.5, and 84.47, respectively. To sum up, the model has a good application effect in virtual reality modeling and positively affects virtual reality technology development.

Wireless short-hop communication is a crucial solution for information transmission between logging while drilling and measurement while drilling. It is important for closed-loop control in geosteering drilling. Compared with wired transmission, wireless short-hop communication offers a cost-effective and stable alternative. It furthermore reduces drilling risks and improves efficiency. Current research primarily concentrates on magnetic dipole antennas, where resistivity stands as the only continuous variable under investigation, and consideration of other parameters may be limited. It lacks complex models and fails to account for factors such as borehole mud and antenna slots. This paper utilizes the Finite Element Method to examine the transmitting and receiving characteristics of electric dipole and magnetic dipole antennas and investigate the effects of transmission conditions and instrument structure on the signal. Experimental validation in a water tank confirmed the reliability and practicality of the numerical simulation results. It suggests that using a coil number between 150 and 200 turns with a frequency of 5 to 8 kHz for both antenna structures in oil-based mud can achieve transmission distances of over 15 m. The antenna slot has minimal impact on the signal. Design considerations should prioritize overall structural stability and mechanical strength. These findings contribute valuable insights to the design and optimization of the instrument.

Chemical Exchange Saturation Transfer Magn-etic Resonance Imaging (CEST-MRI) is a promising approach for detecting tissue metabolic changes. However, due to the constraints of scan time and contrast-noise-ratio, CEST-MRI always exhibits low spatial resolution, hindering the clinical applications especially for detection of small lesions. Many super-resolution (SR) methods have shown good performance in medical images. However, when applied to CEST-MRI, these methods have two shortcomings that may limit their performance. Firstly, CEST-MRI has an additional frequency dimension, but the information along this dimension is not fully utilized. The second is that these SR methods mainly focus on improving the quality of the CEST-weighted images, while the accuracy of the quantitative maps is the most concerned aspect for CEST-MRI. To address these shortcomings, we propose a Cross-space Optimization-based Mutual learning nETwork (COMET) for SR of CEST-MRI. COMET incorporates novel spatio-frequency extraction modules and a mutual learning module to leverage and combine information from both spatial and frequency spaces, thereby enhancing the SR performance. Furthermore, we propose a novel CEST-based normalization loss to address the normalization-induced distribution problem and preserve the sharpness of quantitative maps, enabling more accurate CEST-MRI quantification. COMET is evaluated on an ischemia rat brain dataset and a human brain dataset. The results demonstrate COMET achieves 8-fold SR, providing accurate quantitative maps. Moreover, COMET outperforms all other state-of-the-art SR methods. Additionally, COMET exhibits its potential in prospective study.

Hand-eye calibration estimates the pose of a camera relative to a robot, which is a fundamental problem for visually guided robots, especially for dynamic object grasping. Most methods use 2D fiducial markers with distinctive visual features and require pre-calibration for accurate calibration, which can not work online. In this paper, we propose a novel hand-eye calibration method based on the natural 3D object, which can work online and automatically even if the object is textureless or weakly textured. We first propose a Pose Refinement Network (PR-Net) to improve the accuracy of 3D object tracking. Then we build a 3D convergence point constraint based on the multi-view information with the accurate object pose to adjust the object position. Finally, we optimize the hand-eye pose by the closed-loop constraint with the optimized object position, solving the problem that is easy to fall into a local minimum. The experiments show that the average error of our hand-eye calibration method is 1.20 degrees and 23.18 mm. The results achieve state-of-the-art by using the working object to realize the online hand-eye calibration.

Template-based 3D object tracking still lacks a high-precision benchmark of real scenes due to the difficulty of annotating the accurate 3D poses of real moving video objects without using markers. In this paper, we present a multi-view approach to estimate the accurate 3D poses of real moving objects, and then use binocular data to construct a new benchmark for monocular textureless 3D object tracking. The proposed method requires no markers, and the cameras only need to be synchronous, relatively fixed as cross-view and calibrated. Based on our object-centered model, we jointly optimize the object pose by minimizing shape reprojection constraints in all views, which greatly improves the accuracy compared with the single-view approach, and is even more accurate than the depth-based method. Our new benchmark dataset contains 20 textureless objects, 22 scenes, 404 video sequences and 126K images captured in real scenes. The annotation error is guaranteed to be less than 2mm, according to both theoretical analysis and validation experiments. We reevaluate the state-of-the-art 3D object tracking methods with our dataset, reporting their performance ranking in real scenes. Our BCOT benchmark and code can be found at https://ar3dv.github.io/BCOT-Benchmark/.

The accurate large-scale measurement of peach crowns is vital in horticultural science and the optimization of orchard management. Nowadays, numerous crown parameters (e.g., crown area, height, and volume) can be obtained via the analysis of point clouds or photographs. Current laser-based sensors provide the required reliable and accurate information; however, they are costly and time-consuming. Therefore, a simpler approach for crown measurement is required. For this purpose, this study presents a pipeline for the monitoring and clustering of 259 peach tree crowns based on unmanned aerial vehicle (UAV) images of a peach orchard in Southeast China. Considering the limitation that the original aerial image dataset contains little information, a data augmentation process is adopted, and an efficient deep learning architecture based on conditional generative adversarial networks (cGANs) was designed to extract the crown area. Then, the shape of the crown area was clustered using an edge detection process and a$k$-means algorithm. Finally, an ellipsoid volume method (EVM) was applied to estimate the crown volume. Five indicators—namely,$Q_{\mathrm {seg}}$,$S_{\mathrm {r}}$, Precision, Recall, and F-measure—were employed to evaluate the crown extraction effects, and the average results for testing samples were 0.832, 0.847, 0.851, 0.828, and 0.846, respectively. Compared with other approaches—namely, fully convolutional network (FCN), U-Net, SegNet21, the excess green index (ExG), and the color index of vegetation extraction (CIVE)—the proposed cGAN model performs better, achieving an accuracy improvement of 5%–25%. For the estimation of crown volume, using measurements from a light detection and ranging (LIDAR) scanner as a reference, the correlation coefficient and relative-root-mean-square error (R-RMSE) were found to be 0.836% and 14.93%, respectively. Overall, the results demonstrate that the proposed method is feasible for measuring peach tree crowns. The wide application of such technology would facilitate applied research in plant phenotyping and precision horticulture.

Reliability plays a central role in deep sub-micron and nanometre IC fabrication technology and has recently been reported to be one of the key issues affecting the inference phase of neural networks. State-of-the-art machine learning (ML) accelerators exploit massively computing parallelism observed in neural networks to achieve high energy efficiency. The topology of ML engines' computing fabric, which constitutes large arrays of processing elements (PEs), has been increasing dramatically to incorporate the huge size and heterogeneity of the rapid evolving ML algorithm. However, it is commonly observed that activations of zero value lead to reduced PE utilization. In this work, we present a novel and low-cost approach to enhance the reliability of generic ML accelerators by Qpportunistically exploring the chances of runtime Redundancy provided by neighbouring PEs, named as OR-ML. In contrast to conventional redundancy techniques, the proposed technique introduces no additional computing resources, therefore significantly reduces the implementation overhead and achieves obvious level of protection. The design prototype is evaluated using emulated fault injection on FPGA, executing mainstream neural networks for objectionclassification and detection.

Memory bandwidth utilization has become the key performance bottleneck for state-of-the-art variants of neural network kernels. Current structures such as depth-wise, point-wise and atrous convolutions have already introduced diverse and discontinuous memory access patterns, which impact efficient activation supply due to more frequent cache misses and consequently high-penalty DRAM pre-charging. To handle this, GPU achieves efficient parallelization with sophisticated optimization of CUDA program to reduce memory footprints, which demands high engineering efforts. In this work, we in contrast propose a programmable direct memory access engine for convolutional neural networks (CNN-DMA) supporting a fast supply of activation for independent and scalable computing units. The CNN-DMA favours a predictable activation streaming approach which completely avoids penalties by bus contention, cache misses and less carefully designed low-level programs. Furthermore, we enhance the baseline DMA with the capability of out-of-order data supply to filter out unique sliding-windows to boost the performance of the computing infrastructure. Experiments on state-of-the-art neural networks show that CNN-DMA achieves optimal DRAM access efficiency for point-wise convolution layers, while reduces 30% to 70% rounds of computation with sliding-window filtering.