Search

Abstract Image restoration with impulse noise is an important task in image processing. Taking into account the statistical distribution of impulse noise, the ℓ1‐norm data fidelity and total variation (ℓ1TV) model has been widely used in this area. However, the ℓ1TV model usually performs worse when the noise level is high. To overcome this drawback, several nonconvex models have been proposed. In this paper, an efficient iterative algorithm is proposed to solve nonconvex models arising in impulse noise. Compared to existing algorithms, the proposed algorithm is a completely explicit algorithm in which every subproblem has a closed‐form solution. The key idea is to transform the original nonconvex models into an equivalent constrained minimization problem with two separable objective functions, where one is differentiable but nonconvex. As a consequence, the proximal linearized alternating direction method of multipliers is employed to solve it. Extensive numerical experiments are presented to demonstrate the efficiency and effectiveness of the proposed algorithm.

Super-resolution (SR) aims to recover a high-resolution image from a single or multiple low-resolution images, compensating for the limitations of satellite sensor imaging. Deep convolutional neural networks have made great achievement in remote sensing image SR. In this article, we propose a novel gradient prior dilated convolutional network (GPDCN) for remote sensing image SR, which obtains contextual spatial connections and alleviates structural distortions. The GPDCN comprises a multiscale feature extraction network and a feature reconstruction network. The former employs a double-path dilated residual block with dilation convolution to increase a receptive field, a global self-attention module to detect long-range reliance among image patches, and a gradient propagation network to extract high-level gradient information. The latter uses the mixed high-order attention module to reconstruct the feature by collecting the high-order characteristics of multiple frequency bands. Experiments with the Massachusetts_Roads and 3K VEHICLE_SR datasets demonstrate that the GPDCN outperforms recent techniques concerning both quantitative and qualitative measures.

PurposeDuring neoadjuvant chemotherapy (NACT), breast tumor morphological and vascular characteristics are usually changed. This study aimed to evaluate the tumor shrinkage pattern and response to NACT by preoperative multiparametric magnetic resonance imaging (MRI), including dynamic contrast-enhanced MRI (DCE-MRI), diffuse weighted imaging (DWI) and T2 weighted imaging (T2WI).MethodIn this retrospective analysis, female patients with unilateral unifocal primary breast cancer were included for predicting tumor pathologic/clinical response to NACT (n=216, development set, n=151 and validation set, n=65) and for discriminating the tumor concentric shrinkage (CS) pattern from the others (n=193; development set, n=135 and validation set, n=58). Radiomic features (n=102) of first-order statistical, morphological and textural features were calculated on tumors from the multiparametric MRI. Single- and multiparametric image-based features were assessed separately and were further combined to feed into a random forest-based predictive model. The predictive model was trained in the testing set and assessed on the testing dataset with an area under the curve (AUC). Molecular subtype information and radiomic features were fused to enhance the predictive performance.ResultsThe DCE-MRI-based model showed higher performance (AUCs of 0.919, 0.830 and 0.825 for tumor pathologic response, clinical response and tumor shrinkage patterns, respectively) than either the T2WI or the ADC image-based model. An increased prediction performance was achieved by a model with multiparametric MRI radiomic feature fusion.ConclusionsAll these results demonstrated that multiparametric MRI features and their information fusion could be of important clinical value for the preoperative prediction of treatment response and shrinkage pattern.

Researchers have resorted to model quantization to compress and accelerate graph neural networks (GNNs). Nevertheless, several challenges remain: (1) quantization functions overlook outliers in the distribution, leading to increased quantization errors; (2) the reliance on full-precision teacher models results in higher computational and memory overhead. To address these issues, this study introduces a novel framework called quantized graph neural networks for image classification (QGNN-IC), which incorporates a novel quantization function, Pauta quantization (PQ), and two innovative self-distillation methods, attention quantization distillation (AQD) and stochastic quantization distillation (SQD). Specifically, PQ utilizes the statistical characteristics of distribution to effectively eliminate outliers, thereby promoting fine-grained quantization and reducing quantization errors. AQD enhances the semantic information extraction capability by learning from beneficial channels via attention. SQD enhances the quantization robustness through stochastic quantization. AQD and SQD significantly improve the performance of the quantized model with minimal overhead. Extensive experiments show that QGNN-IC not only surpasses existing state-of-the-art quantization methods but also demonstrates robust generalizability.

Internal Solitary Waves (ISWs) play a pivotal role in transporting energy and matter within the ocean and also pose substantial risks to ocean engineering, navigation, and underwater communication systems. Consequently, measures need to be adopted to alleviate their negative effects and minimize linked risks. An effective method entails extracting ISW positions from Synthetic Aperture Radar (SAR) data for precise trajectory prediction and efficient avoidance strategies. However, manual extraction of ISWs from SAR data is time-consuming and prone to inaccuracies. Hence, it is imperative to develop a high-precision, rapid, and automated ISW-extraction algorithm. In this paper, we introduce Middle Transformer U2-net (MTU2-net), an innovative model that integrates a distinctive loss function and Transformer to improve the accuracy of ISWs’ extraction. The novel loss function enhances the model’s capacity to extract bow waves, whereas the Transformer ensures coherence in ISW’s patterns. By conducting experiments involving 762 image scenes, incorporating ISWs, from the South China Sea, we established a standardized dataset. The Mean Intersection over Union (MIoU) achieved on this dataset was 71.57%, surpassing the performance of other compared methods. The experimental outcomes showcase the remarkable performance of our proposed model in precisely extracting bow wave attributes from SAR data.

The restoration of images corrupted by blurring and structured noise has attracted growing attention in the domains of image processing and computer vision. However, many works only focus on the restoration of the images degraded by blurring and additive structured noise or multiplicative structured noise separately. It is still a challenge and an open problem to restore degraded images with blurring and multiplicative structured noise, simultaneously. In this paper, based on the total variation (TV), the statistical property of the Gamma noise and the maximum a posteriori (MAP) estimator, we obtain a convex variational model to recover blurred images with multiplicative structured noise. Especially, to get this convex model, we reformulate the prior assumption of the images degradation model by division instead of multiplication. For solving this convex model, an effective alternating direction method of multipliers (ADMM) is employed. Numerical experiments are presented to illustrate the effectiveness and efficiency of the proposed model.