To leverage the complementary advantages of SAR’s all-weather and all-day imaging capability and optical imagery’s intuitive visualization, SAR-to-optical image translation (S2OIT) has emerged as a promising solution to mitigate the interpretability challenges posed by SAR’s speckle noise and geometric distortions. However, the scale of high-quality registered SAR-optical data is limited, where incorporating priors is a viable solution. What’s more, the digging out of optical prior is insufficient among the existing methods, leading to inadequate synthesis of optical-like texture in translated optical images. To address these challenges, we propose DOGAN, a DINO-based optical-prior-driven GAN framework that integrates ample optical priors extracted from a pretrained DINO model into the S2OIT process. Specifically, to fully exploit the tremendous optical prior preserved in pretrained DINO and extract multiscale optical prior, a DINO-based Optical-prior Extraction (DOE) module is proposed. Furthermore, to elevate the domain adaptability of optical prior, a lightweight Stacked Optical-Aware (SOA) adapter is proposed to fine-tune DINO for remote sensing data with minimal trainable parameters. To instill the extracted affluent optical prior into the S2OIT pipeline stably, the SAR-optical Multi-scale Domain Alignment (SO-MDA) module is proposed, which employs L1 and Multi-kernel Maximum Mean Discrepancy (MK-MMD) losses to align intermediate optical and S2O features. Extensive experiments on SAR2Opt and SEN1-2 datasets demonstrate that DOGAN achieves state-of-the-art performance in both translation fidelity and structural realism. To the best of our knowledge, this is the first work to leverage DINO-based optical priors for the S2OIT task.

Due to various restrictions, some Internet of Things (IoT) sensing layers can only deploy a small number of sensor nodes for spatiotemporal low-resolution environmental information sensing, making the urgent issue of how to recover the spatiotemporal high-resolution sensing data (SHD). Existing methods mainly focus on the reconstruction problem of random data loss in densely deployed nodes, while continuous data loss in spatiotemporal low-resolution sensing data (SLD) can severely degrade their reconstruction performance. In this work, an acrlong SLRTC is proposed to avoid the impact of continuous data loss and further enhance the spatiotemporal correlation. The SLD is arranged in a third-order tensor, where horizontal and vertical directions are node location indexes, and tubal direction is the time index. To avoid continuous data loss and enhance the spatial correlation of data, each frontal slice of the tensor is divided into a group of overlapping patches and then concatenated into a third-order spatial structure tensor. To further ensure the stricter low-rank prior, the spatial structure tensors are divided into two groups and linearly mapped to a third-order tensor with Hankel structure to exploit the spatiotemporal correlation among the data, and then the two Hankel tensors are concatenated into a three-order tensor for exploiting inter-Hankel tensor temporal correlation. Experimental results on real and simulated IoT data show that the proposed method can reconstruct SHD with high accuracy and the acrlong NMAE is lower than 0.0172 and 0.0124, respectively, when only 12% of the data is observed.

Cross-view geo-localization seeks to match geographic locations using images from varied sources, including drones and satellites. Interpreting images captured by drones poses significant challenges due to the varying positions and scales resulting from the camera’s aerial perspective. Traditional approaches have primarily focused on harnessing contextual cues, which may lead to overfitting. Therefore, it is crucial to find an optimal balance between leveraging contextual details and identifying relevant features. To address this, we introduce a novel method for cross-view geo-localization that employs counterfactual causal reasoning (CCR). This method aims to refine the model’s focus, ensuring a balanced emphasis on both the intricate details of the target structure and its broader contextual environment. Our method incorporates an Adaptive Dimension Interaction Block (ADIB), which effectively discerns feature interactions across multiple dimensions, enhanced by counterfactual causal reasoning to improve recognition of target structures and their contexts. In tasks of image-based drone-view target localization and drone navigation, our method achieves superior performance on the University-1652 and SUES-200 benchmark datasets. The code and model files will be made available athttps://github.com/Cyberpunk1998/CCR.

Hyperspectral image classification (HSIC) has been a popular task in recent years. Even benefiting from the rapid development of deep neural networks (DNNs), there are still remaining intrinsic problems, including inadequate utilization of spatial-spectral information and insufficient labeled samples. The recent emergency of diffusion models (DMs) came to the fore because of their impressive refined image generation performance. DMs have been proven to not only can capture the underlying information of data through training the decoder of DMs, but also have more stable training than GANs while retaining even better performance. To better perceive and utilize spectral-spatial information while alleviating insufficient labeled samples simultaneously, we introduce the DM into HSIC from a data generation perspective. Specifically, we propose a stage-wise DM framework (SWDiff), dividing the HSIC task into three stages, including: pretrain the diffusion decoder with the hyperspectral image (HSI); generate new HSI cubes through the well-trained decoder to extra supply the original HSI set; and utilize the supplied dataset to train varied classifiers to obtain a better classification performance. Suitable pretraining could enable the decoder to acquire spatial-spectral information of the HSIs sufficiently via modeling spectral-spatial relationships across samples, leading to better utilization of spectral and spatial information of HSIs. Furthermore, the DM could provide the inference stage with spatial-spectral prior knowledge to ensure the feasibility and plausibility of the dataset complement, which could alleviate the insufficient labeled samples problem. Eventually, the classification stage will benefit from the first two stages.

As acquired seismic data is usually incomplete and noisy, simultaneous reconstruction and denoising is an extremely important step for the accurate interpretation of seismic data and subsequent processing. We propose a hybrid low-rank and sparsity constraint method with Hankel structure preservation to improve the performance of simultaneous reconstruction and denoising. The proposed method combines the advantages of high efficiency pertaining to sparsity-promoting transforms and the strong data adaptability of rank reduction methods. Meanwhile, a structure-preserving matrix is constructed to preserve the predefined Hankel structure of the twofold Hankel matrix to further improve the accuracy and efficiency of simultaneous reconstruction and denoising. Moreover, weighted nuclear norm minimization (WNNM) is introduced to adaptively assign weights to different singular values. Experimental results in both synthetic and field seismic data compared with other state-of-the-art methods demonstrate the superior performance of the proposed method.

Recently, there has been growing interest in hyperspectral images (HSIs) classification tasks, with both Graph Neural Networks (GNN) and Convolutional Neural Networks (CNN) proving to be effective means of analysis. GNN can better capture the spatial structure of HSIs in large target irregular regions through superpixel segmentation, while CNN can refine classification tasks by processing pixel-level features in small target regular regions. However, neither GNN nor CNN models alone can simultaneously consider superpixel-level and pixel-level features to cover both large and small target regions. To fully utilize the strengths of GNN and CNN, we propose a novel model called the Graph-Polarized Fusion Network (GPF). The GPF consists of two branches: the Fusion Graph Neural Network (FGNN) classifier in the GNN branch conducts feature learning on large, irregular target regions using both Graph Convolutional Network (GCN) and Graph Attention Network (GAT) as feature extraction operators. The features are integrated using three aggregators, namely Min, Max, and Weighted Add, followed by updating the nodes through 2D convolutional layers. The Polarized Neural Network (PNN) classifier of the CNN branch primarily works on small, target regular regions using Polarized Self-Attention (PSA) to conduct high-resolution processing on the two dimensions of space and channel without increasing time loss. Additionally, GPF employs residual connections to extract features from long distances and multi-angles. It also uses weighted fusion to integrate the superpixel-level and pixel-level features obtained from the two branches. Rigorous experiments on five real datasets demonstrate that GPF can fully mine the latent features of HSIs, achieving competitive results compared with other state-of-the-art methods.

The emergence of the heterogeneous Internet of Things (IoT) has realized the demand for multi-attribute data collection in response to the increasing demand for information in diverse applications. Sparse sampling has been used to reduce network energy consumption in order to extend the life of energy-constrained networks. Real-time multi-attribute data aggregation under the sparse sensing framework has become a research focus. Therefore, we proposed a sparse-sampling-based IoT data aggregation approach to reduce network energy consumption and enable real-time multi-attribute reconstruction. For data collection, a sparse sampling data collection approach is proposed that can successfully collect and transmit the multi-attribute data to the sink even while certain IoT sensor nodes are in the sleep mode. For data reconstruction, a real-time multi-attribute data reconstruction method based on subspace is proposed. The proposed method arranges multi-attribute data in a tensor form in order to further utilize the correlation of multi-attribute data. Subspaces representing the spatial distributions of the multi-attribute data can be obtained from the previously reconstructed data. Incorporating total variation constraint, the proposed method reconstructs the current time slot multi-attribute data with high precision in real time. The experimental results demonstrate the effectiveness of the proposed method in real-time multi-attribute data reconstruction.

Environmental monitoring is an important application of wireless sensor networks (WSNs). However, due to the limited number of sensors, the global distribution of the sensed physical environmental parameter with a high resolution in the monitoring area cannot be accurately obtained. In this paper, a structured matrix completion based method is proposed to obtain the global distribution of selected environmental parameter with partial sensors. By arranging the data into an enhanced matrix exhibiting Hankel structure, the inherent correlation among data in the monitoring area can be further exploited to improve the accuracy of data estimation. Furthermore, an efficient algorithm based on alternating direction method of multipliers is described to solve the resulting problem. Experimental results demonstrate that the proposed method can estimate the global distribution of the environmental parameter and achieves better estimation accuracy compared with the existing methods.

The seismic energy is the most correlative along the structural direction, and thus, many traditional filtering methods can be optimally performed in a flattened gather. We introduce in detail a flattening operator for creating the flattened dimension, where a denoising operator can be applied subsequently. The flattening operator is created by deriving a plane-wave trace continuation relation following the plane-wave equation. We demonstrate that the plane-wave trace continuation can well preserve the strong amplitude variation existing in the seismic data. In order to obtain a reliable slope estimation in the presence of noise, a robust slope estimation approach is introduced to substitute the traditional method. The flattening operator can be combined with many state-of-the-art filtering methods to obtain superior performance. Both synthetic and field seismic data are used to demonstrate the potential of the proposed framework in realistic applications.

Due to data loss and sparse sampling methods utilized in WSNs to reduce energy consumption, reconstructing the raw sensed data from partial data is an indispensable operation. In this paper, a real-time data recovery method is proposed using the spatiotemporal correlation among WSN data. Specifically, by introducing the historical data, joint low-rank constraint and temporal stability are utilized to further exploit the data spatiotemporal correlation. Furthermore, an algorithm based on the alternating direction method of multipliers is described to solve the resultant optimization problem efficiently. The simulation results show that the proposed method outperforms the state-of-the-art methods for different types of signal in the network.

Group sparse representation has shown great potential in image restoration, which can be considered as a low-rank matrix approximation problem. The nuclear norm minimization method, as a convex relaxation of the rank minimization, shrinks all the singular values simultaneously. Recent advances have suggested the truncated nuclear norm minimization method to better approximate the rank of the matrix. In this paper, we connect group sparse representation with truncated nuclear norm minimization with the application to image restoration. Then, an implementation of fast convergence via the alternating direction method of multipliers is developed to solve the proposed problem. Moreover, an effective dictionary for each group is learned from the recovery image itself rather than a dataset with a large number of natural images. Experimental results demonstrate that the proposed GSR-TNNM method achieves a good convergence performance and is able to improve image quality significantly compared with the state-of-the-art methods.

An effective way to reduce the energy consumption of energy constrained wireless sensor networks is reducing the number of collected data, which causes the recovery problem. In this paper, we propose a novel data recovery method based on low-rank tensors for the heterogeneous wireless sensor networks with various sensor types. The proposed method represents the collected high-dimensional data as low-rank tensors to effectively exploit the spatiotemporal correlation that exists in the various data. Furthermore, an algorithm based on the alternating direction method of multipliers is developed to solve the resultant optimization problem efficiently. Experimental results demonstrate that the proposed method significantly outperforms the sparsity constraint method and matrix completion method for each type of signals.

High-dimensional MR imaging often requires long data acquisition time, thereby limiting its practical applications. This paper presents a low-rank tensor based method for accelerated high-dimensional MR imaging using sparse sampling. This method represents high-dimensional images as low-rank tensors (or partially separable functions) and uses this mathematical structure for sparse sampling of the data space and for image reconstruction from highly undersampled data. More specifically, the proposed method acquires two datasets with complementary sampling patterns, one for subspace estimation and the other for image reconstruction; image reconstruction from highly undersampled data is accomplished by fitting the measured data with a sparsity constraint on the core tensor and a group sparsity constraint on the spatial coefficients jointly using the alternating direction method of multipliers. The usefulness of the proposed method is demonstrated in MRI applications; it may also have applications beyond MRI.