Deblurring in remote sensing images is a challenging task due to the long-range imaging capabilities of remote sensing sensors, which often results in image blur. Factors contributing to image blur include atmospheric disturbances during long-range imaging or the orbital motion of remote sensing platforms. The existing methods remove blur in remote sensing images using the traditional attention mechanism, which focuses on a limited number of features. However, they often overlook the features among neighboring positions in blurry areas, and these areas contain more relevant features. Leveraging these features can effectively assist in restoring the complex object textures of remote sensing blurry images. To achieve this, we propose a novel implicit neural attention mechanism for assembling more relevant features implied by surrounding coordinates. Specifically, we use the features and their corresponding coordinates to learn the enhanced feature representation with more relevant features, and this representation can be used to derive the deblurred images. Extensive experiments demonstrate that our proposed method, INA-RSDeblur, outperforms the state-of-the-art deblurring methods in remote sensing blurry images.

Existing CNN-based and Transformer-based methods have demonstrated remarkable performance in low-level visual tasks, including image deblurring. These methods generally capture spatial features only in a single way, such as by stacking blocks of CNNs and Transformers, resulting in inadequate utilization of spatial context. To address this issue, we propose a new feature aggregation scheme for image deblurring, named Omni-Deblurring. The core of our omni-deblurring is the omni-range context block, which enables explicitly aggregating the local-range, regional-range, and global-range features in a compact manner. With this design, it can bring a wider receptive field for modeling the contextual features. Extensive experiments on synthetic and real-world blurry datasets demonstrate the effectiveness of our proposed method in both quantitative and qualitative evaluations. Furthermore, the quality of our deblurring model is evaluated in the task of object detection, and the mean Average Precision (mAP) metric increases by 10% across all classes compared with other deblurring models. Code is available athttps://github.com/yaowli468/Omni-Deblurring.

Natural fractures play a crucial role in the storage and seepage of oil shale. However, identifying fractures using conventional logging techniques presents challenges due to complex response characteristics and severe data imbalance. Here, we propose a highly accurate integrated ensemble learning method, called BSI-extreme gradient boosting (XGBoost), for identifying the natural fracture development, which combines several steps including isolation forests (iForests), synthetic minority oversampling techniques (SMOTEs), and XGBoost, and incorporates rock brittleness as a controlling factor in the model construction process. The proposed model effectively addresses several challenges encountered in fracture identification, including complex logging response characteristics, low precision and recall of fractured labels, and excessive sensitivity of ensemble learning to noise. To do so, the relationship between fracture density and brittle mineral content is analyzed through core analysis and X-ray diffraction (XRD). Then, conventional logging and rock brittleness are used as features for training the model. Herein, by screening the outliers of iForest, SMOTE oversampling, and feature selection, optimal hyperparameters of the model are obtained through the grid search method. The results demonstrated that using BSI-XGBoost, the testing set achieved an accuracy of 92.45%. Comparatively, this accuracy is 4.86% higher than the original XGBoost model and 3.73% higher than the B-XGBoost model, which incorporated brittleness curves but did not include oversampling and outlier removal. Collectively, this workflow provided an effective method for intelligent identification of fractures in oil shale with high accuracy based on easily accessible conventional logging curves.

Under low-light conditions, perceptual fusion techniques, such as image fusion, can mitigate the inherent limitations of source images, thereby enhancing the safety performance of automated driving. However, these methods typically perform fusion and detection tasks separately, making it difficult to improve detection precision, as the fused images often lack the rich target information necessary for effective low-light traffic detection. In this paper, an end-to-end unified interactive network is proposed, which eliminates the problem of structural inconsistency between fusion and detection tasks by constructing interaction relationships. In this work, a dual-branch coupled feature extraction module is proposed. Different from other dual-branch methods, this module couples weak features from different modalities to enhance features. In addition, an interactive fusion module is proposed to achieve mutual enhancement between fusion and detection tasks while adaptively weighting the fusion of infrared and visible features. Extensive experimental results on traffic scene datasets, such as LLVIP and FMB, demonstrate that the proposed unified network not only achieves excellent fusion results but also significantly improves traffic object detection precision in low-light environments.

Transformer-based methods have achieved excellent performance in single image super-resolution (SISR) due to their ability to model long-range dependency. However, most existing methods require huge computational resources, making it difficult to apply on mobile devices with limited computing and storage resources. In this paper, we propose a lightweight CNN and spatial-channel Transformer hybrid network (CSCTHN), which adopts spatial and channel self-attention alternately and leverages the local extraction capability of CNN. CSCTHN’s basic unit CNN and Transformer hybrid module (CTHM) comprises three key components: dual-branch interactive spatial self-attention block (DISSAB) for capturing spatial context with lower computational cost, channel self-attention block (CSAB) for capturing channel information and local feature enhancement block (LFEB) that utilizes CNN to extract local information. Extensive experiments demonstrate that CSCTHN is superior to the state-of-the-art methods in terms of reconstruction performance and model complexity (e.g.,31.33dB@Manga109 ×4 with only 706K parameters).

Earth’s surface is covered by thin-cloud throughout the year, which greatly limits the application of remote sensing (RS) images obtained at a high cost. Currently, deep-learning technology has received widespread attention in the field of thin-cloud removal from RS images. The parameter training process of the deep network in this letter is divided into two stages according to the frequency domain feature of training samples. In the first stage, the loss between the thin-cloud removal image and the corresponding clear image is minimized by the full-frequency domain training. In the second stage, the parameters of the first stage are frozen, and the high-frequency features of the thin-cloud image are integrated into the Decoder module for network training. Furthermore, the corresponding attention module of the dual-tree wavelet is designed. For better training in the second stage, the high-frequency loss function based on three-level wavelet transform is designed. Compared with the highest average values of peak signal to noise ratio (PSNR) and structural similarity (SSIM) of traditional methods, FDT-Net achieves an improvement by up to 33.4108% and 7.5184%, respectively. In quantitative experiments, compared with the highest average values of PSNR and SSIM among deep-learning methods, FDT-Net has an improvement by 2.1505% and 0.9123%, respectively. Therefore, the proposed deep-learning network FDT-Net can significantly extend the temporal and spatial range of RS image application under thin-cloud weather conditions. The code of model is available at https://github.com/chonghaozhan/FDT-Net.

Different from the ground image with uniform haze, the haze in remote sensing (RS) image has the characteristics of irregular shape and uneven concentration in hazy weather. It brings a great challenge to the application of RS image data in advanced image processing tasks. A novel dehazing network for non-uniform hazy remote sensing image, named as KFA-Net, is proposed to solve the aforementioned issues. The designed asymmetric size feature cascade (ASFC), k-means pixel attention (KPA) and FFT channel attention (FCA) in KFA-Net all show excellent effects. Compared with symmetrically linked typical Unet, ASFC can more easily extract shallow features for feature reconstruction. Furthermore, different from the commonly used pixel attention that compresses feature maps directly, KPA introduces k-means clustering algorithm in machine learning into the attention mechanism, which facilitates network training to focus on the thick hazy region. Compared to typical squeeze-and-excitation block, FCA uses the low-frequency region feature of spectrogram to obtain the attention weight coefficient in the frequency domain, making network training pay more attention to the feature of image low-frequency region. Extensive comparison experiments verify that the proposed KFA-Net has the great superiority. PSNR/SSIM of KFA-Net are 31.0952% and 6.6401% higher than DCP with the highest citation in traditional dehazing methods, respectively. PSNR/SSIM of KFA-Net are 2.2049% and 0.4966% higher than the recently proposed 4KDehazing with the best performance among all comparison dehazing methods, respectively. The KFA-Net proposed in this research can greatly enhance the temporal and spatial scope of RS image application in hazy weather conditions.

Low-rank tensor completion methods have been advanced recently for modeling sparsely observed data with a multimode structure. However, low-rank priors may fail to interpret the model factors of general tensor objects. The most common method to address this drawback is to use regularizations together with the low-rank priors. However, due to the complex nature and diverse characteristics of real-world multiway data, the use of a single or a few regularizations remains far from efficient, and there are limited systematic experimental reports on the advantages of these regularizations for tensor completion. To fill these gaps, we propose a modified CP tensor factorization framework that fuses the l2norm constraint, sparseness (l1norm), manifold, and smooth information simultaneously. The factorization problem is addressed through a combination of Nesterov's optimal gradient descent method and block coordinate descent. Here, we construct a smooth approximation to the l1norm and TV norm regularizations, and then, the tensor factor is updated using the projected gradient method, where the step size is determined by the Lipschitz constant. Extensive experiments on simulation data, visual data completion, intelligent transportation systems, and GPS data of user involvement are conducted, and the efficiency of our method is confirmed by the results. Moreover, the obtained results reveal the characteristics of these commonly used regularizations for tensor completion in a certain sense and give experimental guidance concerning how to use them.

Low‐resolution (LR) document images may cause difficulties in reading or low recognition rates in computer vision. Thus, it is necessary to improve the resolution of an LR document image via some algorithms. In this study, a novel document image super‐resolution (SR) method using structural similarity and Markov random field (MRF) is proposed. First, the non‐local algorithm is utilised to find similar patches. Instead of using the Euclidian distance, a modified chi‐square distance is proposed to measure the patch similarity because the bimodality characteristic of the document images can be better described by this modified chi‐square distance. Finally, the structural similarity of similar patches is served as a constraint for the MRF‐based SR method, which is proper to describe the neighbouring relationship between patches. The SR reconstruction for LR images of printed and handwritten documents are carried out by the proposed algorithm. Experimental results show that the reconstructed SR images obtain higher peak signal‐to‐noise ratio and structural similarity values than those of several state‐of‐the‐art SR methods and visually pleasant SR images can be produced as well.

This letter proposes a novel single image super-resolution (SR) method based on the low-rank matrix recovery (LRMR) and neighbor embedding (NE). LRMR is used to explore the underlying structures of subspaces spanned by similar patches. Specifically, the training patches are first divided into groups. Then the LRMR technique is utilized to learn the latent structure of each group. The NE algorithm is performed on the learnt low-rank components of HR and LR patches to produce SR results. Experimental results suggest that our approach can reconstruct high quality images both quantitatively and perceptually.

This paper presents a novel method for single-image superresolution (SR) reconstruction using the low-rank matrix recovery and nonlinear mappings. First, the low-rank matrix recovery is utilized to learn the underlying structures of subspaces spanned by the grouped patch features. Second, the low-rank components of low-resolution (LR) and high-resolution (HR) patch features are mapped onto high-dimensional spaces by nonlinear mappings respectively. Then the mapped high-dimensional vectors are projected onto a unified space, where the two manifolds constructed by LR and HR patches respectively have similar local geometry and the SR reconstruction is performed via neighboring embedding. The experimental results validate the effectiveness of our method and suggest that the proposed method outperforms other SR algorithms qualitatively and quantitatively.