Search

In July 2021, numerous audio recordings dating back to 2006 through 2012 were leaked. In them, Real Madrid's President Florentino Pérez was heard insulting some of the most beloved legends of Real Madrid fans, including celebrity Cristiano Ronaldo. Despite his lack of manners, the seriousness of the president's insults, and the lack of a formal apology, the images of Pérez and Real Madrid barely suffered because of this incident. This scholarly commentary examines the variables of culture and country as well as the specific characteristics of the soccer industry and fandom that explain the lack of public accountability when a top executive of a soccer organization commits verbal excesses in form and substance, as in the Pérez case. [ABSTRACT FROM AUTHOR]

Cross-resolution person re-identification (CR-ReID) is a highly practical task that primarily addresses the image misalignment issue due to image resolution variations, which are caused by differences in the distances between cameras and camera performance variations. The existing cutting-edge approaches attempted to use super-resolution (SR) techniques to recover lost details in low-resolution (LR) images. However, the existing SR techniques focus on improving low-level semantic information metrics. Evaluation techniques for high-level semantic recognition tasks are not well suited for low-level image quality metrics. We propose a new framework called image feature restoration using a swin transformer (IFRSW), which uses the feature difference between LR and high-resolution (HR) images as the supervisory signal to constrain the SR module. We further improved the swin transformer by introducing a new multiresolution feature fusion strategy, enhancing its ability to extract features from multiresolution images. Additionally, we introduce a pooling technique called "softpooling" to preserve more information during the feature downsampling process. Our method exhibits a noteworthy 4.2% in rank 1 accuracy improvement on a challenging real LR dataset CAVIR, surpassing the current optimal approach. Our method achieves superior performance to the existing state-of-the-art (SOTA) methods. [ABSTRACT FROM AUTHOR]

Chronic kidney disease (CKD) is a life-threatening condition which is hard to identify early, as there are no symptoms. It is possible to prevent or minimize the evolution of this chronic condition before it reaches an end stage, where dialysis or surgical intervention is the only way to save the patient’s life. Early detection and adequate therapy can increase the risk of this occurring. The majority of supervised techniques employ labeled datasets to build in-domain predictions of CKD. However, the results are typically poor when a classifier is used to categorize an image of CKD in a different domain after it has been trained on labeled images for that domain. However, a machine learning technique known as “cross-domain few-shot learning” involves training a model to generalize information from one domain to another using only a small number of samples from the target domain. So, a novel hybrid classifier with few shot learning is proposed to improve the cross-domain CKD prediction performance. The kidney’s CT images were collected and preprocessed using ENSNet annotation, autoencoder denoising, green fire blue filter and image restoration. The pre-data were provided for the segmentation process using supervised InfNet segmentation, which segments an exact region of CKD. The segmented regions were fed to an input of the classification process. A few shot learning-based hybrid classifiers were developed to predict CKD in the cross-domain. In a few shot learning, more samples were collected for the training phase, and fewer samples were used for the classifier’s testing. Based on the few shot learning, the proposed CKD model was tested and diagnosed with the input samples at appropriate conditions. The designed proposed model offers 97.9% accuracy, 96.4% precision, 96.4% recall and 98.6% negative predictive value. In addition, observed values of the proposed model were contrasted with some other approaches for validating the process. The proposed few-shot learning-based hybrid classifier is an effective choice for more precise cross-domain CKD prediction at low processing time. [ABSTRACT FROM AUTHOR]

In this paper, we propose a modified Fletcher–Reeves conjugate gradient method. The new search direction is calculated in such a way that it is close to a three term PRP conjugate gradient method. In particular, we introduce a parameter that adjusts the weight applied to the standard FR method, ensuring that our CG method satisfies the sufficient descent property. Global convergence is established under the strong Wolfe line search. The method is tested on a set of unconstrained optimization problems and the results demonstrate the new method's competency against existing methods. Furthermore, the new method is implemented to solve an image restoration problem of removing impulse noise from a digital image. [ABSTRACT FROM AUTHOR]

All-in-one image restoration aims to recover various degraded images using a unified model. To adaptively reconstruct high-quality images, recent prevalent CNN and Transformer based models incorporate learnable prompts to dynamically acquire degradation-specific knowledge for different degraded images, achieving state-of-the-art restoration performance. However, existing methods exhibit limitations, including high computational burden and inadequate modeling of long-range dependencies. To address these issues, we propose a reasoning and action prompt-driven Mamba-based image restoration model, namely RamIR. Specifically, RamIR employs the Mamba block for long-range dependencies modeling with linear computational complexity relative to the feature map size. Inspired by Chain-of-Thought (CoT) prompting, we integrate Reasoning and Action (ReAct) prompts within the Mamba block. Hence, we utilize the capability of pretrained vision language (PVL) models to generate textual reasoning prompts describing the type and severity of degradations. Simultaneously, another output from PVL acts as action prompt representing the clean image caption. These prompts, employed in a CoT manner, enhance the network's sensitivity to degradation and elicit targeted recovery actions tailored to different reasoning prompts. Additionally, we explore the seamless interaction between Mamba blocks and prompts, introducing a novel prompt-driven module (PDM) to facilitate prompt utilization. Extensive experimental results demonstrate the superior performance of RamIR, highlighting its advantages in terms of input scaling efficiency over existing benchmark models for all-in-one image restoration. [ABSTRACT FROM AUTHOR]

Adverse weather conditions, such as haze and raindrop, consistently degrade the quality of remote sensing images and affect subsequent vision-based applications. Recent years have witnessed advancements in convolutional neural networks (CNNs) and Transformers in the field of remote sensing image restoration. However, these methods either suffer from limited receptive fields or incur quadratic computational overhead, leading to an imbalance between performance and model efficiency. In this paper, we propose an effective vision state space model (called Weamba) for remote sensing image restoration by modeling long-range pixel dependencies with linear complexity. Specifically, we develop a local-enhanced state space module to better aggregate rich local and global information, both of which are complementary and beneficial for high-quality image reconstruction. Furthermore, we design a multi-router scanning strategy for spatially varying feature extraction, alleviating the issue of redundant information caused by repeated scanning directions in existing methods. Extensive experiments on multiple benchmarks show that the proposed Weamba performs favorably against state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Group sparse residual constraint model with nonlocal priors (GSRC-NLP) has made great success in image restoration and produce state-of-the-art performance, realized through reducing the group sparsity residual. In the GSRC-NLP model, L 1 norm is used to reduce the group sparsity residual. However, the L 1 norm penalty has been known to lead to the over-shrinkage of the large sparse coefficients. In this paper, we utilize the adaptive correction procedure to reduce excessive penalties on large coefficient values while improving group sparsity. The proposed corrected group sparse residual constraint model (CGSRC) can improve the sparsity of the group sparsity residual, which lead to better performance in image restoration. We apply the iterative shrinkage/thresholding and the alternating direction method of multipliers to solve the proposed models. In addition, we study the properties of the proposed CGSRC model including the existence and uniqueness of the solution as well as the convergence of the proposed algorithms. Experimental results on image denoising and image inpainting show that the proposed models outperform several state-of-the-art image denoising and image inpainting methods in terms of both objective and perceptual quality metrics. [ABSTRACT FROM AUTHOR]

Image anomaly detection plays an important role in various fields, such as industrial defect detection and medical image analysis. Although the use of image restoration has led to significant progress in image anomaly detection, challenges persist in insufficient image feature extraction and inadequate integration of low-level and high-level features. In this study, a framework that combines reconstruction methods with knowledge distillation is designed. To address the challenge of insufficient image convolution feature extraction, a multi-branch feature extraction module is introduced, extracting both local and global features using convolution and self-attention modules, respectively. Additionally, to overcome the inadequate integration of low-level and high-level features in the skip connection part, a straightforward skip connection is designed to fuse semantic information from high-level features with finer details from low-level features through element-wise multiplication. Extensive experiments on industrial image datasets, such as Mvtec AD and BTAD, validate the effectiveness of the proposed method in improving anomaly detection localization performance. The Mvtec AD dataset yielded impressive results, with image-level and pixel-level ROC_AUC achieving average accuracy values of 99.16% and 98.09%, respectively. Similarly, on the BTAD dataset, our method exhibited remarkable performance, achieving average accuracy values of 93% and 96% for image-level and pixel-level ROC_AUC, respectively. These notable improvements across both datasets underscore the effectiveness of our proposed method. [ABSTRACT FROM AUTHOR]

Image restoration (IR) involves the retrieval of missing or damaged image information and represents a significant challenge in the field of visual reconstruction. Currently, U-Net based Diffusion Models (DMs) display favorable results when utilized for IR tasks. However, the DM based on U-Net demonstrates shortcomings in capturing the global context for IR. To address this issue, we propose a Novel Image Restoration Approach Based on U-shaped Transformer and DMs (DIRformer). DIRformer enhances the modeling capacity for long-range dependencies within DMs. In particular, DIRformer replaces the traditional U-Net downsampling with Patch merging, dedicated to improving detail preservation, and replaces upsampling with Dual up-sample, strategically designed to alleviate checkerboard artifacts. Besides, as a lightweight and versatile transformer-based solution for IR, DIRformer incorporates time and degradation mapping into the transformer design, all while preserving the fundamental U-shaped structural framework. We assess the efficacy of DIRformer in a multi-tasking IR setting across four datasets. The experimental performance illustrates that DIRformer achieves competitive performance on distortion metrics, including PSNR and SSIM. Remarkably, our proposed approach is almost 25 \(\times\) smaller and 2 \(\times\) faster than the existing methods while achieving comparable high performance. [ABSTRACT FROM AUTHOR]

The restoration of images affected by adverse weather conditions is hindered by two main challenges. The first is the restoration of fine details in severely degraded regions. The second is the interference between different types of degradation data during the model training process, which consequently reduces the restoration performance of the model on individual tasks. In this work, we propose a Transformer-based All-in-one image restoration model, called PDFormer, to alleviate the aforementioned issues. Initially, we designed an effective transformer network to capture the global contextual information in the image and utilize this information to restore the locally severely degraded regions better. Additionally, to alleviate the interference between different types of degraded data, we introduced two specialized modules: the Prompt-Guided Feature Refinement Module (RGRM) and the Degradation Mask Supervised Attention Module (MSAM). The former employs a set of learnable prompt parameters to generate prompt information, which interacts with the degraded feature through cross-attention, enhancing the discriminative ability of different degraded features in the latent space. The latter, under the supervision of the degraded mask prior, assists the model in differentiating between different degradation types and locating the regions and sizes of the degradations. The designs above permit greater flexibility in handling specific degradation scenarios, enabling the adaptive removal of different degradation artifacts to restore fine details in images. Performance evaluation on both synthetic and real data has demonstrated that our method surpasses existing approaches, achieving state-of-the-art (SOTA) performance. [ABSTRACT FROM AUTHOR]

In this paper, we explore an algorithm for low-light image enhancement based on Retinex modules. A low light enhancement network based on Ghost-Block and unique image decomposition is proposed, termed as GDNet. This addresses the problem of color distortion that exists in current enhancement algorithms. Firstly, a special module called Ghost-Block is proposed which can effectively reduce the redundant features in the network. Secondly, we design a unique decomposition network based on the Ghost-Block. It decomposes low-light image into texture map, color map, and illumination map, representing the texture structure, color, and illumination distribution in the original image, respectively. Taking into account the influence of different illumination scenarios on color information in the subsequent adjustment process, we develop a coupled color and illumination adjustment network. This treats color and illumination adjustment in low-light enhancement as a joint optimization problem rather than separate sub-tasks, aiming to achieve a natural color distribution with balanced illumination in the enhanced image. Finally, considering potential loss of texture detail information during the light adjustment process, we design a texture adjustment network to further restore the texture structure in natural lighting scenes. Extensive experiments demonstrate that our algorithm outperforms state-of-the-art methods in terms of light adjustment and color fidelity. Moreover, our proposed algorithm exhibits a high degree of similarity with Ground Truth in experiments using normal lighting images as a test set. The source code will be released at . [ABSTRACT FROM AUTHOR]

Stimulated emission depletion (STED) microscopy is a super‐resolution technique that surpasses the diffraction limit and has contributed to the study of dynamic processes in living cells. However, high laser intensities induce fluorophore photobleaching and sample phototoxicity, limiting the number of fluorescence images obtainable from a living cell. Herein, these challenges are addressed by using ultra‐low irradiation intensities and a neural network for image restoration, enabling extensive imaging of single living cells. The endoplasmic reticulum (ER) is chosen as the target structure due to its dynamic nature over short and long timescales. The reduced irradiation intensity combined with denoising permits continuous ER dynamics observation in living cells for up to 7 h with a temporal resolution of seconds. This allows for quantitative analysis of ER structural features over short (seconds) and long (hours) timescales within the same cell, and enabled fast 3D live‐cell STED microscopy. Overall, the combination of ultralow irradiation with image restoration enables comprehensive analysis of organelle dynamics over extended periods in living cells. [ABSTRACT FROM AUTHOR]

In ancient historical ceramics, for various reasons, some problems such as dirt and damage inevitably occur, and necessary repair work must be carried out. Throughout ceramics restoration work, the selection and use of materials are very important. Thus, it is necessary to explore the use of modern intelligent algorithms to assist the selection and application of restoration materials during the whole restoration process, in order to improve the effectiveness of ancient ceramics restoration. In this study, convolutional neural network (CNNs) technology and a machine learning (ML) algorithm were applied to images of ceramics for the defect identification and repair of ancient ceramics, aided by additive manufacturing (AM). The simulation results show that the recall of this algorithm for AM ancient ceramics image recognition was improved by 19.68%. In order to enhance the restoration effects on ancient ceramics, it is necessary to enhance their restoration by expanding the use of digital technology, with the intent to maintain the advantages of traditional handicrafts. Therefore, we should review experiences in the restoration of ancient ceramics, introduce digital technology according to specific needs, and enhance the advanced nature of restoration work. [ABSTRACT FROM AUTHOR]

Accurate and efficient measurement of deposited droplets' volume is vital to achieve zero-defect manufacturing in inkjet printed organic light-emitting diode (OLED), but it remains a challenge due to droplets' featurelessness. In our work, coherence scanning interferometry (CSI) is utilized to measure the volume. However, the CSI redundant sampling and image degradation led by the sample's transparency decrease the efficiency and accuracy. Based on the prior degradation and strong representation for context, a novel method, volume measurement via fringe distribution module (VMFD), is proposed to directly measure the volume by single interferogram without redundant sampling. Firstly, the 3D point spread function (PSF) for CSI imaging is modeling to relate the degradation and image. Secondly, the Zernike to PSF (ZTP) module is proposed to efficiently compute the aberrations to PSF. Then, a physics aberration restoration network (PARN) is designed to remove the degradation via the channel Transformer and U-net architecture. The long term context is learned by PARN and beneficial to restoration. The restored fringes are used to measure the droplet's volume by constrained regression network (CRN) module. Finally, the performances on public datasets and the volume measurement experiments show the promising deblurring, measurement precision and efficiency. [ABSTRACT FROM AUTHOR]

In the field of remote sensing, the acquired images are often severely degraded due to adverse weather conditions, such as haze and raindrops, posing significant challenges for subsequent visual tasks. Although CNN and Transformer have been widely applied to address these issues, they struggle to balance the relationship between global scene recovery, local detail preservation, and computational efficiency, leading to an imbalance between model performance and efficiency. To this end, we propose a lightweight and efficient visual state space model for remote sensing image restoration. Specifically, we propose the Efficient Vision Mamba Block as the core component of the model, incorporating the State Space Model to leverage its linear complexity for modeling long-range dependencies. Furthermore, we design a multi-router scanning strategy to perform global modeling of remote sensing images, capturing large spatial features from different routes and directions. Compared with existing methods that employ fixed-direction scanning, our approach avoids information redundancy caused by repeated scanning, making the model better adaptable to the complex and changeable weather conditions. Extensive experiments validate the superiority of our proposed model, outperforming state-of-the-art methods on both the StateHaze1k and UAV-Rain1k datasets. [ABSTRACT FROM AUTHOR]

Image inpainting is the recent hot research direction in the domain of artificial intelligence due to its significance in image restoration. Even though the traditional image inpainting approaches have shown promising outcomes, they are prone to ambiguous artifacts, particularly in high semantic and boundary areas. To resolve these challenges, we propose an efficient image inpainting model termed Gradient Semantics Generation Network-based Two-stage Image Inpainting Generator (GSGN-TSIIG) for comprehensive image restoration. Firstly, we design GSGN a comprehensive gradient learning framework by employing a convolutional autoencoder as a backbone for accurately determining gradient semantics in the hole region of the corrupted images. Secondly, we develop TSIIG an image inpainting network that leverages the significance of structural and textural generators for repairing the missing pixels and generating better image inpainting outcomes. Furthermore, our model leverages image data collected from diverse sources, including the Places-2_MIT dataset, CelebA dataset, Paris Streetview dataset, and ImageNet dataset for comprehensive performance assessment. Experimental results, including essential measures and quantitative analyses, demonstrate the efficacy of our approach by achieving a PSNR of 35.2 dB and a mean error of 0.01. Notably, comparative evaluations underscore the superior performance of our proposed model over existing approaches, establishing its potential for robust image restoration applications. [ABSTRACT FROM AUTHOR]

Copyright of Iranian Journal of Numerical Analysis & Optimization is the property of Ferdowsi University of Mashhad Press and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Borehole imaging technology is a critical means for the meticulous measurement of rock mass structures. However, the inherent issue of probe eccentricity significantly compromises the quality of borehole images obtained during testing. This paper proposes a method based on grayscale feature analysis for reverse positioning of imaging probes and image restoration. An analysis of the response characteristics of probe eccentricity was conducted, leading to the development of a grayscale feature model and a method for reverse positioning analysis. By calculating the error matrix using the probe's spatial trajectory, this method corrects and restores grayscale errors caused by probe eccentricity in images. Quantitative analysis was conducted on the azimuthal errors in borehole images caused by probe eccentricity, establishing a method for correcting image perspective errors based on probe spatial-positioning calibration. Results indicate significant enhancement in the effectiveness and measurement accuracy of borehole images. [ABSTRACT FROM AUTHOR]

In the rapidly advancing realm of mobile technology, under-display camera (UDC) systems have emerged as a promising solution for achieving seamless full-screen displays. Despite their innovative potential, UDC systems face significant challenges, including low light transmittance and pronounced diffraction effects that degrade image quality. This study aims to address these issues by examining degradation phenomena through optical simulation and employing a deep neural network model incorporating hybrid frequency–spatial domain learning. To effectively train the model, we generated a substantial synthetic dataset that virtually simulates the unique image degradation characteristics of UDC systems, utilizing the angular spectrum method for optical simulation. This approach enabled the creation of a diverse and comprehensive dataset of virtual degraded images by accurately replicating the degradation process from pristine images. The augmented virtual data were combined with actual degraded images as training data, compensating for the limitations of real data availability. Through our proposed methods, we achieved a marked improvement in image quality, with the average structural similarity index measure (SSIM) value increasing from 0.8047 to 0.9608 and the peak signal-to-noise ratio (PSNR) improving from 26.383 dB to 36.046 dB on an experimentally degraded image dataset. These results highlight the potential of our integrated optics and AI-based methodology in addressing image restoration challenges within UDC systems and advancing the quality of display technology in smartphones. [ABSTRACT FROM AUTHOR]

Mongolian patterns are easily damaged by various factors in the process of inheritance and preservation, and the traditional manual restoration methods are time-consuming, laborious, and costly. With the development of deep learning technology and the rapid growth of the image restoration field, the existing image restoration methods are mostly aimed at natural scene images. They do not apply to Mongolian patterns with complex line texture structures and high saturation-rich colors. In order to solve this problem, this paper proposes a Mongolian pattern restoration model with a multi-stage network. In the first stage, a pyramid context encoder network is introduced to learn the contextual features of the image for global restoration; in the second stage, a local restoration network is constructed by combining the RIC convolutional layer and the MPD down-sampling module; and in the third stage, the global refinement restoration is carried out by using the U-Net network that incorporates the attention mechanism. The experimental results show that this paper's method achieves remarkable results in the Mongolian pattern repair task, using four evaluation metrics such as Peak Signal-to-Noise Ratio (PSNR), Structural Similarity (SSIM), LPIPS, and L1 Loss to compare with the existing method. The results show that this paper's method performs well in the Mongolian pattern repair task. Also, the performance of the model on public datasets verifies its wide applicability. The method in this paper provides an efficient solution for the digital restoration of Mongolian motifs and has important application prospects. [ABSTRACT FROM AUTHOR]

In the field of remote sensing, cloud cover severely reduces the quality of satellite observations of the earth. Due to the complete absence of information in cloud-covered regions, cloud removal with a single optical image is an ill-posed problem. Since the synthetic aperture radar (SAR) can effectively penetrate clouds, fusing SAR and optical remote sensing images will effectively alleviate this problem. However, existing SAR-based optical cloud removal methods fail to effectively leverage the global information provided by the SAR image, resulting in limited performance gains. In this paper, we introduce a novel cloud removal method named the Multi-Level SAR-Guided Contextual Attention Network (MSGCA-Net). MSGCA-Net is designed with a multi-level architecture that integrates a SAR-Guided Contextual Attention (SGCA) module to fuse the dependable global contextual information from SAR images with the local features of optical images effectively. In the module of SGCA, the SAR image provides reliable global contextual information and genuine structure of cloud-covered regions, while the optical image provides the local feature information. The proposed model can efficiently extract and fuse global and local contextual information in SAR and optical images. We trained and evaluated the performance of the model on both simulated and real-world datasets. Both qualitative and quantitative experimental evaluation demonstrated that the proposed method can yield high quality cloud-free images and outperform state-of-the-art cloud removal methods. [ABSTRACT FROM AUTHOR]

Hyperspectral Imaging (HSI) excels in material identification and capturing spectral details and is widely utilized in various fields, including remote sensing and environmental monitoring. However, in real-world applications, HSI is often affected by Stray Light Interference (SLI), which severely degrades both its spatial and spectral quality, thereby reducing overall image accuracy and usability. Existing hardware solutions are often expensive and add complexity to the system, and despite these efforts, they cannot fully eliminate SLI. Traditional algorithmic methods, on the other hand, struggle to capture the intricate spatial–spectral dependencies needed for effective restoration, particularly in complex noise scenarios. Deep learning methods present a promising alternative because of their flexibility in handling complex data and strong restoration capabilities. To tackle this challenge, we propose MambaHR, a novel State Space Model (SSM) for HSI restoration under SLI. MambaHR incorporates state space modules and channel attention mechanisms, effectively capturing and integrating global and local spatial–spectral dependencies while preserving critical spectral details. Additionally, we constructed a synthetic hyperspectral dataset with SLI by simulating light spots of varying intensities and shapes across spectral channels, thereby realistically replicating the interference observed in real-world conditions. Experimental results demonstrate that MambaHR significantly outperforms existing methods across multiple benchmark HSI datasets, exhibiting superior performance in preserving spectral accuracy and enhancing spatial resolution. This method holds great potential for improving HSI processing applications in fields such as remote sensing and environmental monitoring. [ABSTRACT FROM AUTHOR]