Search

There is an important need for methods to process myocardial perfusion imaging (MPI) single-photon emission computed tomography (SPECT) images acquired at lower-radiation dose and/or acquisition time such that the processed images improve observer performance on the clinical task of detecting perfusion defects compared to low-dose images. To address this need, we build upon concepts from model-observer theory and our understanding of the human visual system to propose a detection task-specific deep-learning-based approach for denoising MPI SPECT images (DEMIST). The approach, while performing denoising, is designed to preserve features that influence observer performance on detection tasks. We objectively evaluated DEMIST on the task of detecting perfusion defects using a retrospective study with anonymized clinical data in patients who underwent MPI studies across two scanners (N = 338). The evaluation was performed at low-dose levels of 6.25%, 12.5%, and 25% and using an anthropomorphic channelized Hotelling observer. Performance was quantified using area under the receiver operating characteristics curve (AUC). Images denoised with DEMIST yielded significantly higher AUC compared to corresponding low-dose images and images denoised with a commonly used task-agnostic deep learning-based denoising method. Similar results were observed with stratified analysis based on patient sex and defect type. Additionally, DEMIST improved visual fidelity of the low-dose images as quantified using root mean squared error and structural similarity index metric. A mathematical analysis revealed that DEMIST preserved features that assist in detection tasks while improving the noise properties, resulting in improved observer performance. The results provide strong evidence for further clinical evaluation of DEMIST to denoise low-count images in MPI SPECT.

Image restoration aims to recover high‐quality clean images from degraded low‐quality ones. Deep learning‐based approaches have been a focal point in the field of image restoration. However, most methods focus solely on a single type of degradation and may not extend well to real‐world scenarios with unknown degradation. For this purpose, the present study introduces an all‐in‐one image restoration approach by designing a multi‐scale feature fusion UNet structure (MdfUNet). In summary, the proposed method exhibits two significant advantages. For starters, it implicitly fuses degradation information across multiple scales, enabling the network to extract rich hierarchical features and enhancing its generalization ability towards unknown degradations. Secondly, MdfUnet possesses strong image reconstruction capabilities. It utilizes a simple non‐linear feature optimizer to enhance skip connections, providing rich feature representations for the image reconstruction process, and ultimately generating high‐quality restored images. Extensive experimental results show the proposed method outperforms multiple baselines on deraining, dehazing, and denoising datasets. [ABSTRACT FROM AUTHOR]

Given the challenges posed by noise and varying target scales in SAR images, conventional convolutional neural networks often underperform in SAR image detection. To address this, this paper introduces a novel approach. Firstly, a Res-Clo network is proposed for denoising SAR images as a preprocessing step to enhance detection accuracy. Subsequently, an improved network, DML-YOLOv8, is devised based on the YOLOv8 network. The enhancements in the proposed algorithm include several key modifications. Firstly, within the feature extraction layers, a designed MFB module is integrated to effectively broaden the network's receptive field. Next, deformable convolutions are introduced in the feature fusion layers to bolster the network's capability for multi-scale detection. Additionally, a novel loss function, RT-IOU, is designed in feature detection to enhance network inference speed. Finally, a specialized STD small target detection layer is designed to improve detection accuracy for small targets. In practical experiments, it has been shown that the detection method proposed in this paper effectively improves the detection performance of noisy SAR images, and also achieves satisfactory results in multi-scale detection. [ABSTRACT FROM AUTHOR]

Many current image denoising works focus on Gaussian noise removal. However, in many real-life applications, the noise in an image can follow non-Gaussian distributions, such as compressed speckle noise, salt-and-pepper impulse noise (SPIN), and random-valued impulse noise (RVIN). In such scenarios, image denoising models with mean squared error loss will fail to obtain the best noise estimation results. Thus, we propose a non-Gaussian denoising convolutional neural network (DTNet) with truncation loss, which can address compressed speckle noise, SPIN, and RVIN with the same denoising framework. The model is composed of Res2Net blocks with the ability to extract multiscale information. Experiments show that our proposed DTNet method can effectively remove compressed speckle noise and impulse noise, including SPIN and RVIN. In particular, DTNet can recover the original images from images with 90% SPIN or images with 70% RVIN. [ABSTRACT FROM AUTHOR]

Event cameras, characterized by their low power consumption, expansive dynamic range, and high temporal resolution, have attracted great attentions in various computer vision tasks. Compared to frame-based cameras, event cameras exemplify a marked paradigmatic transition in data formation and output. However, the quality of event streams is compromised by background activity and hot pixels, leading to increased computational overheads and sub-optimal outcomes in subsequent applications, notably in recognition, video reconstruction, and target detection tasks. In this paper, a two-step denoising algorithm (referred as GMCM) is proposed to counteract these challenges. The GMCM algorithm comprises two steps: Gaussian denoising preprocessing and motion denoising. The former incorporates Gaussian temporal distribution and adaptive thresholding mechanisms to discern the inclusion of motion-related information within the event streams. Experimental results demonstrate that Gaussian denoising preprocessing can not only adeptly discern whether the event data stream contains motion information but also enhance computational efficiency. Conclusively, the GMCM algorithm achieves state-of-the-art performance, yielding SNR scores of 37.22 and 26.79 on the DVSCLEAN dataset at the noise ratios of 50% and 100%, respectively. [ABSTRACT FROM AUTHOR]

Images of titanium alloy welds detected by time-of-flight diffraction (TOFD) have problems, including large noise signals and many interference streaks around the defects, all of which seriously limit the accuracy and effectiveness of defect recognition. Existing image denoising methods lack the knowledge of the noise characteristics of TOFD images of titanium alloy weld and the preprocessing experience of technicians in the field. In addition, it is difficult to select the parameters of the preprocessing methods, and they are easily influenced by the level of technical personnel, resulting in low efficiency and poor consistency in preprocessing. To address these problems, we proposed a denoising method based on the combination of wavelet band features and deep-learning theory for TOFD images of titanium alloy weld. First, based on the wavelet preprocessing method and the experience of nondestructive testing (NDT) technicians, we constructed an image pair dataset consisting of the original TOFD images of titanium alloy weld and the desired target images to realize the accumulation of engineers' preprocessing knowledge. Second, we constructed a multiband wavelet feature fusion U-net image denoising model (WU-net) and designed a loss function under three constraints of image consistency, image texture information consistency, and structural similarity. This model was able to learn to achieve end-to-end adaptive denoising for TOFD images of titanium alloy weld. Third, we illustrated and validated the effectiveness of TOFD image preprocessing for titanium alloy weld. The results showed that the proposed method effectively eliminated TOFD image noise and improved the accuracy of defect recognition. [ABSTRACT FROM AUTHOR]

Variational regularization, renowned for its sound theoretical foundations and impressive performance, is widely used in image restoration. The traditional regularization models typically use a predefined regularizer to promote smoothness in the solution. However, these models do not explicitly take into account any external information that should be preserved in the restoration. In this paper, we introduce a novel guided regularization model to enhance the efficacy of traditional regularization. Our model incorporates an external guidance regularizer, utilizing a guidance image to bolster the quality of restoration. By integrating this external information into the regularization process, the model is better equipped to preserve specific features or attributes indicated by the guidance image, leading to more accurate and aesthetically pleasing restored images. Furthermore, we demonstrate the convexity of the model and prove the existence and uniqueness of the solution. The alternating direction method of multipliers (ADMM) algorithm is employed to numerically solve the proposed model. In the experimental evaluation, the proposed model is applied to image denoising and deblurring tasks. The experiments successfully validate the proposed model and algorithm. Compared with several state-of-the-art models, the proposed model demonstrates the best performance in terms of peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM). • A novel guided regularization model is proposed, which aims to incorporate additional guidance into regularization process. • We demonstrate the convexity of the model and prove the existence and uniqueness of the solution. • The proposed guided regularization model is applied to image denoising and deblurring tasks, yielding satisfactory results. [ABSTRACT FROM AUTHOR]

In response to the problem of denoising in image fusion, the author proposes a hybrid image fusion and denoising algorithm based on multi-scale transformation (MLT) and signal sparse representation (SRS). A hybrid model is constructed for shear transformation, and the coefficients after MLT decomposition are thresholded. Sliding window technology and translation invariance are used to form sparse representation for image fusion, and SRS algorithm is used to remove noise from the source image. The experimental results show that the algorithm reduces the contrast and spectral information distortion of the fused image, displays high-quality visual fusion effects, maintains high PSNR values under different noise levels, can provide a more complete description of the features in the image, accurately judge the focus area, maintain the structural correlation of the image, and strengthen the description of fusion edges and details in the fused image. It has been proven that the methods of multi-scale transformation and sparse signal representation can fuse and denoise images. [ABSTRACT FROM AUTHOR]

Low-dose computed tomography (LDCT) reduces radiation damage to patients, however, it adds noise and artifacts to the reconstructed images, which deteriorates the quality of CT images. To address the problem of easy edge blurring in the denoising process of LDCT images, this paper proposes a fourth-order partial differential diffusion model with adaptive Laplacian kernel that can protect edge and detail information. The model incorporates the guided filter with edge preserving as a fidelity term in the energy function. Then, using gradient magnitude and the local variance to construct edge and detail detectors in the diffusion function, which can protect the edge and detail information of the LDCT images during the diffusion process. Finally, using the adaptive Laplacian kernel replaces the conventional Laplacian kernel, which has stronger edge preserving. The experimental results show that the proposed model achieves excellent performance in edge preserving and noise suppression in actual thoracic phantom and AAPM clinical LDCT images. In terms of both visual effects and quantitative indexes, the proposed model has good processing performance compared with other excellent algorithms. [ABSTRACT FROM AUTHOR]

In this paper, we introduce a novel method for noise reduction called the High-Dimensional Model Representation (HDMR) Median Filter. HDMR, functioning as a divide and conquer algorithm, dynamically adapts its filtering parameters based on local image characteristics. This adaptation aims to preserve image quality while efficiently eliminating noise. The HDMR Median Filter excels in retaining fine details, preserving edges, and safeguarding essential image features. To assess the performance of the proposed algorithm, we conducted comparisons with results from recent studies. These comparisons were based on two commonly used metrics: Structural Similarity (SSIM) and Peak Signal-to-Noise Ratio (PSNR) The obtained results demonstrate that the noise reduction algorithm obtained with HDMR performs better than the most recent studies in the literature. [ABSTRACT FROM AUTHOR]

The nondestructive testing capability of steel surface defects has a significant impact on quality of industrial production. However, the single-stage detection network YOLOv5s model for steel surface defect detection is of insufficient feature extraction ability and susceptibility to noise interference in extracting surface defect images. Accordingly, a steel surface defect detection system based on YOLOv5s-SE-CA model and bi-dimensional empirical mode decomposition (BEMD) image enhancement is proposed. Firstly, the BEMD is used for image threshold denoising to improve the quality of surface defect images and achieve preprocessing of the dataset. Secondly, the squeeze and excitation network (SENet) attention mechanism is introduced into the backbone network of YOLOv5s model to adaptively adjust weights of each feature channel. Meanwhile, the coordinate attention (CA) attention mechanism is integrated to improve network model’s ability to focus on surface defects. Therefore, the YOLOv5s-SE-CA model is designed to enhance detection capability of steel surface defects. Experimental verification was carried out using the NEU-DET noisy dataset with specific evaluation indicators of image enhancement detection system. Results showed the proposed system has superior performance when compared to traditional models trained on noisy and denoising datasets and achieved more accurate detection of surface defects in steel. [ABSTRACT FROM AUTHOR]

Noise in medical images can degrade the quality of the image and make it difficult to interpret. Denoising algorithms have been commonly used to remove noise from images, and recent advances in optimization methods have led to more effective denoising algorithms. Several algorithms have been proposed in recent times with different performance scales. But recently, deep learning-based models have been much better performing than other models. There have been recent advances in optimized denoising algorithms for medical images. This paper proposes a memory-efficient model based on deep learning which uses a convolutional autoencoder with batch normalization merged with activation layers, called in-place ABN (activated batch normalization). It is concluded that optimized denoising algorithms are effective at removing noise from medical images while preserving image quality. [ABSTRACT FROM AUTHOR]

Coherent anti‐Stokes Raman scattering (CARS) microscopy is a powerful label‐free imaging technique that leverages biomolecular vibrations and is widely used in different fields. However, its intrinsic non‐resonant background (NRB) can distort Raman signals and compromise spectral fidelity. Conventional data analysis methods for CARS encounter a bottleneck in achieving high accuracy. Furthermore, CARS requires balancing imaging speed against image quality. In recent years, endeavors in deep learning have effectively overcome these obstacles, advancing the development of CARS. This review highlights the research that applies deep learning to mitigate NRB, classify CARS data for disease identification, and denoise images. Each approach is delineated in terms of network architecture, training data, and loss functions. Finally, the challenges in this field is discussed and using the latest deep learning advancement is suggested to enhance the reliability and efficiency of CARS microscopy. [ABSTRACT FROM AUTHOR]

Image denoising aims to remove noise from images and improve the quality of images. However, most image denoising methods heavily rely on pairwise training strategies and strict prior knowledge about image structure or noise distribution. While these methods exhibit significant results when handling known types of noise, their generalization performance diminishes when confronted with images containing unknown noise distributions. To address this issue, a two‐stage approach is introduced for enhancing the generalizability of image denoising. The proposed method does not rely on a large amount of paired data or prior knowledge of the noise type and level. Instead, it constructs a denoising pipeline with improved generalizability through an MLP‐based denoiser and generative diffusion prior. Specifically, in the first stage, an initial denoised image is predicted with a structure resembling that of the underlying clean image by introducing an MLP‐based U‐shaped denoising network aided by an implicit structural prior. In the second stage, the generalizability and quality of the denoiser are further enhanced by conditioning the result obtained from the previous stage on the pretrained denoising diffusion null‐space model. Extensive experimentation on multiple datasets demonstrates that this method exhibits better denoising performance and generalizability than other image denoising methods. [ABSTRACT FROM AUTHOR]

This paper proposes an improved three-term conjugate gradient algorithm designed to solve nonlinear equations with convex constraints. The key features of the proposed algorithm are as follows: (i) It only requires that nonlinear equations have continuous and monotone properties; (ii) The designed search direction inherently ensures sufficient descent and trust-region properties, eliminating the need for line search formulas; (iii) Global convergence is established without the necessity of the Lipschitz continuity condition. Benchmark problem numerical results illustrate the proposed algorithm's effectiveness and competitiveness relative to other three-term algorithms. Additionally, the algorithm is extended to effectively address the image denoising problem. [ABSTRACT FROM AUTHOR]

Deep convolutional neural networks (CNNs) have demonstrated significant potential in enhancing image denoising performance. However, most denoising methods fuse different levels of features through long and short skip connections, easily generating a lot of redundant information, thereby weakening the complementarity of different levels of features, resulting in the loss of image details. In this paper, we propose a multi-scale detail–noise complementary learning (MDNCL) network for additive white Gaussian noise removal and real-world noise removal. The MDNCL network comprises two branches, namely the Detail Feature Learning Branch (DLB) and the Noise Learning Branch (NLB). Specifically, a loss function is applied to guide the complementary learning of image detail features and noisy mappings in these two branches. This learning approach effectively balances noise reduction and detail restoration, especially when dealing with high ratios of noise. To enhance the complementarity of features between different network layers and avoid redundant information, we designed a Feature Subtraction Unit (FSU) to capture the differences in features across the DLB network layers. Our extensive experimental evaluations demonstrate that the MDNCL approach achieves impressive denoising performance and outperforms other popular denoising methods. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. 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.)

In order to achieve image denoising in high-noise environment, this paper proposes an image denoising algorithm based on improved wavelet thresholding algorithm.The algorithm first improves the problem of fixed threshold.Secondly, an improved wavelet threshold function is proposed for the traditional hard and soft threshold function.Finally, the combination of improved threshold function and threshold can improve the accuracy of wavelet threshold judgment, and realize the effective separation of image and noise. Experimental results show that the proposed algorithm can not only effectively remove image noise in noisy environment, but also obtain higher(Peak signal-to-noise ratio, PSNR) and smaller (Mean Squared Error, MSE). [ABSTRACT FROM AUTHOR]

Aiming at the characteristics that the signal noise ratio (SNR) gradually decreases from the near to far range of the swath, an adaptive phase filtering algorithm based on Goldstein filtering and combined with multiple quality-guided graphs was proposed. Firstly, the components used to determine the filtering parameters were obtained through residue density, pseudo-coherence coefficient and pseudo-SNR, the three quality-guided graphs. Then, the filter parameters were calculated by weighting the three components. Finally, the size of filtering window was determined according to the account of residues, and the interferometric phase noise was removed in frequency domain. Simulated data, TSX/TDX data and airborne interferometric imaging radar altimeter data were used to verify the performance of the new algorithm. Compared with the results of Goldstein filtering and its improved algorithms, the results showed that the proposed algorithm can effectively filter out phase noise while maintaining the edge characteristics of interferometric fringe. The section of filtering result can well match with the section of simulated pure interfeometric phase. Moreover, the algorithm proposed in this paper can effectively remove the noise in the interferogram of TSX/TDX sea ice data, and the residues' filtering rate was above 86%, which can effectively remove the phase residues of the sea ice surface while maintaining the characteristics of the sea ice edge. Experimental results showed that the new algorithm provides an effective phase noise filtering method for imaging radar altimeter data processing. [ABSTRACT FROM AUTHOR]

The quality of images captured digitally or transmitted over networks is distorted by noise during the process. The current methods of image restoration can be ineffective in dealing with intricate noise patterns or may be slow or imprecise. This paper fills this gap by presenting a new second-order continuous-time dynamical system for denoising of images in image restoration. The approach used in this work poses the problem as a convex quadratic program that can, thus, be solved for optimality. The existence and uniqueness of a global solution are theoretically demonstrated, and the condition for the global strong convergence of the system's trajectory is provided. The method presented in this paper is shown to be useful in a number of experiments on image restoration. As for the performance, it is higher than that of other known algorithms, with an average SNR equal to 34.78 and a Structural Similarity Index Measure (SSIM) of 0.959 for the reconstructed images. Such improvements demonstrate the effectiveness of the second-order dynamical system approach in actual image restoration applications. [ABSTRACT FROM AUTHOR]

Medical image denoising has numerous real-world applications. Despite their widespread use, existing medical image denoising methods fail to address complex noise patterns and typically generate artifacts in numerous cases. This paper proposes a novel medical image denoising method that learns denoising using an end-to-end learning strategy. Furthermore, the proposed model introduces a novel deep–wider residual block to capture long-distance pixel dependencies for medical image denoising. Additionally, this study proposes leveraging multi-head attention-guided image reconstruction to effectively denoise medical images. Experimental results illustrate that the proposed method outperforms existing qualitative and quantitative evaluation methods for numerous medical image modalities. The proposed method can outperform state-of-the-art models for various medical image modalities. It illustrates a significant performance gain over its counterparts, with a cumulative PSNR score of 8.79 dB. The proposed method can also denoise noisy real-world medical images and improve clinical application performance such as abnormality detection. [ABSTRACT FROM AUTHOR]

Synthetic Aperture Radar (SAR) imagery presents significant advantages for observing ocean surface winds owing to its high spatial resolution and low sensitivity to extreme weather conditions. Nevertheless, signal noise poses a challenge, hindering precise wind retrieval from SAR imagery. Moreover, traditional geophysical model functions (GMFs) often falter, particularly in accurately estimating high wind speeds, notably during extreme weather phenomena like tropical cyclones (TCs). To address these limitations, this study proposes a novel hybrid model, CMOD-Diffusion, which integrates the strengths of GMFs with data-driven deep learning methods, thereby achieving enhanced accuracy and robustness in wind retrieval. Based on the coarse estimation of wind speed by the traditional GMF CMOD5.N, we introduce the recently developed data-driven method Denoising Diffusion Probabilistic Model (DDPM). It transforms an image from one domain to another domain by gradually adding Gaussian noise, thus achieving denoising and image synthesis. By introducing the DDPM, the noise from the observed normalized radar cross-section (NRCS) and the residual of the GMF methods can be largely compensated. Specifically, for wind speeds within the low-to-medium range, a DDPM is employed before proceeding to another CMOD iteration to recalibrate the observed NRCS. Conversely, a posterior-placed DDPM is applied after CMOD to reconstruct high-wind-speed regions or TC-affected areas, with the prior information from regions characterized by low wind speeds and recalibrated NRCS values. The efficacy of the proposed model is evaluated by using Sentinel-1 SAR imagery in vertical–vertical (VV) polarization, collocated with data from the European Centre for Medium-Range Weather Forecasts (ECMWF). Experimental results based on validation sets demonstrate significant improvements over CMOD5.N, particularly in low-to-medium wind speed regions, with the Structural Similarity Index (SSIM) increasing from 0.76 to 0.98 and the Root Mean Square Error (RMSE) decreasing from 1.98 to 0.63. Across the entire wind field, including regions with high wind speeds, the validation data obtained through the proposed method exhibit an RMSE of 2.39 m/s, with a correlation coefficient of 0.979. [ABSTRACT FROM AUTHOR]

Given the propagation characteristics of sound waves and the complexity of the underwater environment, denoising forward-looking sonar image data presents a formidable challenge. Existing studies often add noise to sonar images and then explore methods for its removal. This approach neglects the inherent complex noise in sonar images, resulting in inaccurate evaluations of traditional denoising methods and poor learning of noise characteristics by deep learning models. To address the lack of high-quality data for FLS denoising model training, we propose a simulation algorithm for forward-looking sonar data based on RGBD data. By utilizing rendering techniques and noise simulation algorithms, high-quality noise-free and noisy sonar data can be rapidly generated from existing RGBD data. Based on these data, we optimize the loss function and training process of the FLS denoising model, achieving significant improvements in noise removal and feature preservation compared to other methods. Finally, this paper performs both qualitative and quantitative analyses of the algorithm's performance using real and simulated sonar data. Compared to the latest FLS denoising models based on traditional methods and deep learning techniques, our method demonstrates significant advantages in denoising capability. All inference results for the Marine Debris Dataset (MDD) have been made open source, facilitating subsequent research and comparison. [ABSTRACT FROM AUTHOR]

Space-based atmospheric backscatter lidars provide critical information about the vertical distribution of clouds and aerosols, thereby improving our understanding of the climate system. They are additionally useful for detecting hazards to aviation and human health, such as volcanic plumes and man-made pollution events. The Cloud-Aerosol Lidar with Orthogonal Polarization (CALIOP, 2006–2023), Cloud-Aerosol Transport System (CATS, 2015–2017), and Advanced Topographic Laser Altimeter System (ATLAS 2018–present) are three such lidars that operated within the past 20 years. The signal-to-noise ratio (SNR) for these lidars is significantly lower in daytime data compared with nighttime data due to the solar background signal increasing the detector response noise. Averaging horizontally across profiles has been the standard way to increase SNR, but this comes at the expense of resolution. Modern, deep learning-based denoising algorithms can be applied to improve the SNR without coarsening resolution. This paper describes how one such model architecture, Dense Dense U-Net (DDUNet), was trained to denoise CATS 1064 nm raw signal data (photon counts) using artificially noised nighttime data. Simulated CATS daytime 1064 nm data were then created to assess the model's performance. The denoised simulated data increased the daytime SNR by a factor of 2.5 (on average) and decreased minimum detectable backscatter (MDB) to ~ 7.3 × 10 − 4 km−1sr−1, which is lower than the CALIOP 1064 nm night MDB value of 8.6 × 10 − 4 km−1sr−1. Layer detection was performed on simulated 2 km horizontal resolution denoised and 60 km averaged data. Despite the finer resolution input, the denoised layers had more true positives, fewer false positives, and an overall Jaccard Index of 0.54 versus 0.44 when compared to the layers detected on averaged data. Layer detection was also performed on a full month of denoised daytime CATS data (Aug. 2015) to detect layers for comparison with CATS standard Level 2 (L2) product layers. The detection on the denoised data yielded 2.33 times more, higher-quality bins within detected layers at 2.7–33 times finer resolution than the CATS L2 products. [ABSTRACT FROM AUTHOR]

Model-based hyperspectral image (HSI) denoising methods have attracted continuous attention in the past decades, due to their effectiveness and interpretability. In this work, we aim at advancing model-based HSI denoising, through sophisticated investigation for both the fidelity and regularization terms, or correspondingly noise and prior, by virtue of several recently developed techniques. Specifically, we formulate a novel unified probabilistic model for the HSI denoising task, within which the noise is assumed as pixel-wise non-independent and identically distributed (non-i.i.d) Gaussian predicted by a pre-trained neural network, and the prior for the HSI image is designed by incorporating the deep image prior (DIP) with total variation (TV) and spatio-spectral TV. To solve the resulted maximum a posteriori (MAP) estimation problem, we design a Monte Carlo Expectation–Maximization (MCEM) algorithm, in which the stochastic gradient Langevin dynamics (SGLD) method is used for computing the E-step, and the alternative direction method of multipliers (ADMM) is adopted for solving the optimization in the M-step. Experiments on both synthetic and real noisy HSI datasets have been conducted to verify the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

Inexpensive cameras, different acquisition devices and mobile phones have resulted in the production of digital images in all spheres of life. There is common of these images for extracting useful information in many fields to perform image analysis and interpretation. One of the problems being faced in the use of this information is the presence of random valued impulse noise. Impulse noise removal is a crucial step in computer vision. Many articles have been published to remove or suppress impulse noise from grayscale digital images using different approaches. Edges and details are, however, often lost during the restoration of digital images. In this research, a two-stage approach for edge detection, preservation, and impulse noise removal is proposed. An effective statistics rank ordered absolute difference (ROAD) is used in the first stage to detect noisy pixels. Trimmed global mean (TGM) with adaptive window is employed later for the filtering process. With the combination of these processes in the proposed method, a higher quality image is restored and thus becomes more suitable for extracting the desired information. Comparison with many state-of-the-art methodologies indicates that the proposed method is effective in the detection of corrupted pixels and the restoration of images. [ABSTRACT FROM AUTHOR]

A lot of current work based on convolutional neural networks (CNNs) has fetched good visual results on AWGN (additive white Gaussian noise) removal. However, ordinary neural networks are unable to recover detailed information for complex tasks, and the application of a single Gaussian denoising model is greatly limited. To improve the practicality of the denoising algorithm, we trained a DCNN (deep convolutional neural network) to perform multiple denoising tasks, including Gaussian denoising and blind Gaussian denoising. The proposed CNN denoising model with a residual structure and apply feature attention to exploit channel dependency. The network structure mainly consists of sparse block (SB), feature fusion block (FFB), feature compression block (FCB), information interaction block (IIB) and reconstruction block (RB). The SB with sparse mechanism obtains global and local features by alternating between dilated convolution and common convolution. The FFB collects and fuses global and local features to provide additional information for the latter network. The FCB refines the extracted information and compresses the network. The IIB is used for feature integration and dimensionality reduction. Finally, the RB is used to reconstruct the denoised image. A channel attention mechanism is added to the network, and a trade-off is made between the denoising effect and the complexity of the network. A large number of experiments are conducted on five datasets, and the results showed that the proposed method achieves highly competitive performance in both objective evaluation indicators and subjective visual effects. [ABSTRACT FROM AUTHOR]

In this paper, a novel parabolic system involving nonlinear and nonhomogeneous partial differential operator with variable growth structure is introduced for investigating the image denoising and restoration. More precisely, our model is based on regularizing the classical models involving variable exponent operators by considering a nonlinear operator with double phase flux. We begin by investigating theoretically the solvability to the parabolic system under consideration. Under the setting of Musielak-Orlicz spaces, we build a suitable functional framework to study the proposed system. Therefore, we develop the Faedo-Galerkin approach to demonstrate the existence and uniqueness of a weak solution to our model. To illustrate our theoretical results in the context of image noise removal, we present various numerical implementations on some grayscale images. To enrich these simulations, we test the robustness efficiency of the proposed model in the so-called Magnetic Resonance Images (MRI). The obtained numerical results claim that our model is more efficient and robust against noise, in comparison (visually and quantitatively) to some existing state-of-the-art methods. • A novel nonlinear parabolic system is introduced. • The theoretical results are applied to the image denoising and restoration. • Various numerical implementations on some grayscale images are carried out. [ABSTRACT FROM AUTHOR]

Image alignment represents a crucial and essential subject in computer vision applications for image analysis. Getting spatial transformation to align a moving image with a reference image is the aim of image alignment. Deep learning techniques, which have been more and more popular recently, provide good outcomes when applied to alignment challenges in addition to many other computer vision problems. In this work, a supervised DL technique has been used in order to estimate the spatial transformation parameter. The spatial transformation model is based on the stiff technique. To convert moving images to a fixed image, rigid transformation parameters are estimated using a supervised convolutional neural network (CNN). The primary contribution of the presented research is to use a model to handle input images with quality degradation to carry out supervised rigid image alignment with the regression model of the CNNs. In the study, many parameters have been examined in an attempt to ascertain the impact of noise in each image and the parameters that yield the optimal outcomes for the problem. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. 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.)

Copyright of Journal of Chongqing University of Posts & Telecommunications (Natural Science Edition) is the property of Chongqing University of Posts & Telecommunications 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.)

In this paper, we propose a minimization-based image denoising model for the removal of mixed stripe and Gaussian noise. The objective function includes the prior information from both the stripe noise and image. Specifically, we adopted a unidirectional regularization term and a nonconvex group sparsity term for the stripe noise component, while we utilized a nonconvex fractional order total variation (FTV) regularization for the image component. The priors for stripes enable adequate extraction of periodic or non-periodic stripes from an image in the presence of high levels of Gaussian noise. Moreover, the nonconvex FTV facilitates image restoration with less staircase artifacts and well-preserved edges and textures. To solve the nonconvex problem, we employed an iteratively reweighted ℓ1 algorithm, and then the alternating direction method of multipliers was adopted for solving subproblems. This led to an efficient iterative algorithm, and its global convergence was proven. Numerical results show that the proposed model provides better denoising performance than existing models with respect to visual features and image quality evaluations. [ABSTRACT FROM AUTHOR]

The rising popularity of employing deep learning networks for image denoising can be observed over the past decade. Typically, their exceptional performance is rooted in their ability to learn the mapping from noisy images to clear ones through extensive training on image datasets. However, variations in noise types and intensity between test and training images significantly impact their performance. Hence, due to its weak generalization capability in practical applications, it becomes imperative to train multiple denoising models for different types of noise and varying degrees of noise interference. To address this challenge, we introduce an effective masked Transformer network by incorporating the random mask module into the network. Specifically, a random mask module is integrated into the Transformer to randomly discard certain features, thereby augmenting the network's generalization capabilities. Furthermore, the random mask module is also applied during the input processing stage to reduce reliance on the whole original image information. Additionally, the sampling operations are added to the network. Based on this, the image size is reduced to half of the original size through downsampling layer, significantly improving the execution efficiency. Experimental results manifest that the proposed masked Transformer network surpasses state-of-the-art methods like SwinIR and Restormer concerning denoising effectiveness and execution efficiency across both synthetic and real-world noisy images. [ABSTRACT FROM AUTHOR]

The zero-shot image classification is a stimulating problem that attains the human recognition level depending upon the tiny quantity of trained images. Image classification was an essential phenomenon in the computer vision process. Therefore, the major problem was solving the classification process, and generally, the processing of entire data for the extraction process was complicated. To solve this problem, a proposed novel technique was Buffalo-based Graph Neural Zero-short Learning (BbGZSL) that aimed to classify the image types as natural and computer-generated. In the first stage, the denoised process was performed to eliminate the data noise and convert the colour image into a grey scale image. Then, a feature extraction process was performed to extract the required features based on the buffalo fitness features of the proposed model. Furthermore, the extracted features were stored using the learning memory. Finally, perform the unseen image testing and matching process for classifying the image. In addition, the proposed BbGZSL mechanism was implemented in the Python tool with several performance assessments. The proposed model gained 97.06% accuracy, f-score and Recall, as well as 97.07% precision for the tested unseen image dataset. [ABSTRACT FROM AUTHOR]

One of the significant challenges with traditional single-task learning-based anomaly detection using noisy hyperspectral images (HSIs) is the loss of anomaly targets during denoising, especially when the noise and anomaly targets are similar. This issue significantly affects the detection accuracy. To address this problem, this paper proposes a multitask learning (MTL)-based method for detecting anomalies in noisy HSIs. Firstly, a preliminary detection approach based on the JointNet model, which decomposes the noisy HSI into a pure background and a noise–anomaly target mixing component, is introduced. This approach integrates the minimum noise fraction rotation (MNF) algorithm into an autoencoder (AE), effectively isolating the noise while retaining critical features for anomaly detection. Building upon this, the JointNet model is further optimized to ensure that the noise information is shared between the denoising and anomaly detection subtasks, preserving the integrity of the training data during the anomaly detection process and resolving the issue of losing anomaly targets during denoising. A novel loss function is designed to enable the joint learning of both subtasks under the multitask learning model. In addition, a noise score evaluation metric is introduced to calculate the probability of a pixel being an anomaly target, allowing for a clear distinction between noise and anomaly targets, thus providing the final anomaly detection results. The effectiveness of the proposed model and method is validated via testing on the HYDICE and San Diego datasets. The denoising metric results of the PSNR, SSIM, and SAM are 41.79, 0.91, and 4.350 and 42.83, 0.93, and 3.558 on the HYDICE and San Diego datasets, respectively. The anomaly detection ACU is 0.943 and 0.959, respectively. The proposed method outperforms the other algorithms, demonstrating that the reconstructed images using this method exhibited lower noise levels and more complete image information, and the JointNet model outperforms the mainstream HSI anomaly detection algorithms in both the quantitative evaluation and visual effect, showcasing its improved detection capabilities. [ABSTRACT FROM AUTHOR]

During underwater image processing, image quality is affected by the absorption and scattering of light in water, thus causing problems such as blurring and noise. As a result, poor image quality is unavoidable. To achieve overall satisfying research results, underwater image denoising is vital. This paper presents an underwater image denoising method, named HHDNet, designed to address noise issues arising from environmental interference and technical limitations during underwater robot photography. The method leverages a dual-branch network architecture to handle both high and low frequencies, incorporating a hybrid attention module specifically designed for the removal of high-frequency abrupt noise in underwater images. Input images are decomposed into high-frequency and low-frequency components using a Gaussian kernel. For the high-frequency part, a Global Context Extractor (GCE) module with a hybrid attention mechanism focuses on removing high-frequency abrupt signals by capturing local details and global dependencies simultaneously. For the low-frequency part, efficient residual convolutional units are used in consideration of less noise information. Experimental results demonstrate that HHDNet effectively achieves underwater image denoising tasks, surpassing other existing methods not only in denoising effectiveness but also in maintaining computational efficiency, and thus HHDNet provides more flexibility in underwater image noise removal. [ABSTRACT FROM AUTHOR]

Recently, the low-rank representation (LRR) model has been widely used in the field of remote sensing image denoising due to its excellent noise suppression capability. However, those low-rank-based methods always discard important edge details as residuals, leading to a common issue of blurred edges in denoised results. To address this problem, we take a new look at low-rank residuals and try to extract edge information from them. Therefore, a hierarchical denoising framework was combined with a low-rank model to extract edge information from low-rank residuals within the edge subspace. A prior knowledge matrix was designed to enable the model to learn necessary structural information rather than noise. Also, such traditional model-driven approaches require multiple iterations, and the solutions may be very complex and computationally intensive. To further enhance the noise suppression performance and computing efficiency, a hierarchical low-rank denoising model based on deep unrolling (HLR-DUR) was proposed, integrating deep neural networks into the hierarchical low-rank denoising framework to expand the information capture and representation capabilities of the proposed shallow model. Sufficient experiments on optical images, hyperspectral images (HSI), and synthetic aperture radar (SAR) images showed that HLR-DUR achieved state-of-the-art (SOTA) denoising results. [ABSTRACT FROM AUTHOR]

Image denoising and super-resolution play vital roles in imaging systems, greatly reducing the preprocessing cost of many AI techniques for object detection, segmentation, and tracking. Various advancements have been accomplished in this field, but progress is still needed. In this paper, we have proposed a novel technique named the Enhanced Learning Enriched Features (ELEF) mechanism using a deep convolutional neural network, which makes significant improvements to existing techniques. ELEF consists of two major processes: (1) Denoising, which removes the noise from images; and (2) Super-resolution, which improves the clarity and details of images. Features are learned through deep CNN and not through traditional algorithms so that we can better refine and enhance images. To effectively capture features, the network architecture adopted Dual Attention Units (DUs), which align with the Multi-Scale Residual Block (MSRB) for robust feature extraction, working sidewise with the feature-matching Selective Kernel Extraction (SKF). In addition, resolution mismatching cases are processed in detail to produce high-quality images. The effectiveness of the ELEF model is highlighted by the performance metrics, achieving a Peak Signal-to-Noise Ratio (PSNR) of 42.99 and a Structural Similarity Index (SSIM) of 0.9889, which indicates the ability to carry out the desired high-quality image restoration and enhancement. [ABSTRACT FROM AUTHOR]

Infrared images are susceptible to interference from a variety of factors during acquisition and transmission, resulting in the inclusion of mixed noise, which seriously affects the accuracy of subsequent vision tasks. To solve this problem, we designed a mixed noise removal algorithm for infrared images based on improved CycleGAN. First, we proposed a ResNet-E Block that incorporates the EMA (Efficient Multi-Scale Attention Module) and build a generator based on it using the skip-connection structure to improve the network's ability to remove mixed noise of different strengths. Second, we added the PSNR (Peak Signal-to-Noise Ratio) as an extra calculation item of cycle consistency loss, so that the network can effectively retain the detailed information of infrared images while denoising. Finally, we conducted experimental validation on both synthetic noisy images and real noisy images, which proved that our algorithm can effectively remove the mixed noise in infrared images and the denoising effect is better than other similar methods. [ABSTRACT FROM AUTHOR]

Background: Residual image noise is substantial in positron emission tomography (PET) and one of the factors limiting lesion detection, quantification, and overall image quality. Thus, improving noise reduction remains of considerable interest. This is especially true for respiratory-gated PET investigations. The only broadly used approach for noise reduction in PET imaging has been the application of low-pass filters, usually Gaussians, which however leads to loss of spatial resolution and increased partial volume effects affecting detectability of small lesions and quantitative data evaluation. The bilateral filter (BF) — a locally adaptive image filter — allows to reduce image noise while preserving well defined object edges but manual optimization of the filter parameters for a given PET scan can be tedious and time-consuming, hampering its clinical use. In this work we have investigated to what extent a suitable deep learning based approach can resolve this issue by training a suitable network with the target of reproducing the results of manually adjusted case-specific bilateral filtering. Methods: Altogether, 69 respiratory-gated clinical PET/CT scans with three different tracers ( [ 18 F ] FDG, [ 18 F ] L-DOPA, [ 68 Ga ] DOTATATE) were used for the present investigation. Prior to data processing, the gated data sets were split, resulting in a total of 552 single-gate image volumes. For each of these image volumes, four 3D ROIs were delineated: one ROI for image noise assessment and three ROIs for focal uptake (e.g. tumor lesions) measurements at different target/background contrast levels. An automated procedure was used to perform a brute force search of the two-dimensional BF parameter space for each data set to identify the "optimal" filter parameters to generate user-approved ground truth input data consisting of pairs of original and optimally BF filtered images. For reproducing the optimal BF filtering, we employed a modified 3D U-Net CNN incorporating residual learning principle. The network training and evaluation was performed using a 5-fold cross-validation scheme. The influence of filtering on lesion SUV quantification and image noise level was assessed by calculating absolute and fractional differences between the CNN, manual BF, or original (STD) data sets in the previously defined ROIs. Results: The automated procedure used for filter parameter determination chose adequate filter parameters for the majority of the data sets with only 19 patient data sets requiring manual tuning. Evaluation of the focal uptake ROIs revealed that CNN as well as BF based filtering essentially maintain the focal SUV max values of the unfiltered images with a low mean ± SD difference of δ SUV max CNN , STD = (−3.9 ± 5.2)% and δ SUV max BF , STD = (−4.4 ± 5.3)%. Regarding relative performance of CNN versus BF, both methods lead to very similar SUV max values in the vast majority of cases with an overall average difference of δ SUV max CNN , BF = (0.5 ± 4.8)%. Evaluation of the noise properties showed that CNN filtering mostly satisfactorily reproduces the noise level and characteristics of BF with δ Noise CNN , BF = (5.6 ± 10.5)%. No significant tracer dependent differences between CNN and BF were observed. Conclusions: Our results show that a neural network based denoising can reproduce the results of a case by case optimized BF in a fully automated way. Apart from rare cases it led to images of practically identical quality regarding noise level, edge preservation, and signal recovery. We believe such a network might proof especially useful in the context of improved motion correction of respiratory-gated PET studies but could also help to establish BF-equivalent edge-preserving CNN filtering in clinical PET since it obviates time consuming manual BF parameter tuning. [ABSTRACT FROM AUTHOR]

Demosaicking is a popular scientific area that is being explored by a vast number of scientists. Current digital imaging technologies capture colour images with a single monochrome sensor. In addition, the colour images were captured using a sensor coupled with a Colour Filter Array (CFA). Furthermore, the demosaicking procedure is required to obtain a full-colour image. Image denoising and image demosaicking are the two important image restoration techniques, which have increased popularity in recent years. Finding a suitable strategy for multiple image restoration is critical for researchers. Hence, a deep learning (DL) based image denoising and image demosaicking is developed in this research. Moreover, the Autoregressive Circle Wave Optimization (ACWO) based Demosaicking Convolutional Neural Network (DMCNN) is designed for image demosaicking. The Quantum Wavelet Transform (QWT) is used in the image denoising process. Similarly, Quantum Wavelet Transform (QWT) is used to analyse the abrupt changes in the input image with noise. The transformed image is then subjected to a thresholding technique, which determines an appropriate threshold range. Once the threshold range has been determined, soft thresholding is applied to the resulting wavelet coefficients. After that, the extraction and reconstruction of the original image is carried out using the Inverse Quantum Wavelet Transform (IQWT). Finally, the fused image is created by combining the results of both processes using a weighted average. The denoised and demosaicked images are combined using the weighted average technique. Furthermore, the proposed QWT+DMCNN-ACWO model provided the ideal values of Peak signal-to-noise ratio (PSNR), Second derivative like measure of enhancement (SDME), Structural Similarity Index (SSIM), Figure of Merit (FOM) of 0.890, and computational time of 49.549 dB, 59.53 dB, 0.963, 0.890, and 0.571, respectively. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) can effectively extract structural information in image denoising. However, they tend to ignore texture information. To tackle this problem, we present a texture-guided CNN for image denoising (TDCNN), which depends on blocks for texture extraction, refinement, and transformation to realize excellent denoising performance on both quantitative and visual metrics. A texture-extraction block combines non-local similarity and two sub-networks to extract texture and structural information. A refinement block with a stacked architecture mines accurate information from complementary features. A transformation block is used to obtain clean output images. A joint loss function, including perceptual loss and mean square error, enhances the robustness of the proposed denoiser. Experiments show that the proposed TDCNN is superior to some popular methods for denoising synthetic and real images. [ABSTRACT FROM AUTHOR]

Low-dose computed tomography (CT) has been successful in reducing radiation exposure for patients. However, the use of reconstructions from sparse angle sampling in low-dose CT often leads to severe streak artifacts in the reconstructed images.In order to address this issue and preserve image edge details, this study proposes an adaptive orthogonal directional total variation method with kernel regression.The CT reconstructed images are initially processed through kernel regression to obtain the N-term Taylor series, which serves as a local representation of the regression function. By expanding the series to the second order, we obtain the desired estimate of the regression function and localized information on the first and second derivatives. To mitigate the noise impact on these derivatives, kernel regression is performed again to update the first and second derivatives. Subsequently, the original reconstructed image, its local approximation, and the updated derivatives are summed using a weighting scheme to derive the image used for calculating orientation information. For further removal of stripe artifacts, the study introduces the adaptive orthogonal directional total variation (AODTV) method, which denoises along both the edge direction and the normal direction, guided by the previously obtained orientation.Both simulation and real experiments have obtained good results. The results of two real experiments show that the proposed method has obtained PSNR values of 34.5408 dB and 29.4634 dB, which are 1.2392–5.9333 dB and 2.828–6.7995 dB higher than the contrast denoising algorithm, respectively, indicating that the proposed method has good denoising performance.The study demonstrates the effectiveness of the method in eliminating strip artifacts and preserving the fine details of the images. [ABSTRACT FROM AUTHOR]

Digital images are corrupted with noise, and image denoising is an important step in image processing modules. In this review, the latest developments in filtering methods for color image restoration are analyzed. These algorithms are compared in terms of objective image quality measures and divided into major classes, such as spatial domain, switching and wavelet filtering methods. These classes are based on the particular methodology used in image denoising algorithms and further subdivided to show their classification in terms of noise models utilized, application style, and stages the filters applied in images. In particular, we present a review of filtering methods in color image denoising, published over the past two decades. Our classification and succinct descriptions of color image restoration by these mathematical filtering techniques and their characterizations can help choose the appropriate ones for various downstream image processing tasks. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new image denoising technique which consists in applying a stationary wavelet transform (SWT)-based image denoising technique, in the domain of 2D dual-tree discrete wavelet transform (DWT). In fact, this proposed technique consists first of applying the 2D dual-tree DWT to the noisy image. Then, the noisy wavelet coefficients obtained from this application are denoised by applying to each of them, a SWT-based image denoising technique. Finally, the denoised image is reconstructed by applying the inverse of the 2D dual-tree DWT to the obtained denoised wavelet coefficients. For applying this SWT-based image denoising technique, we use the soft thresholding, the Daubechies 4 as the mother wavelet, and the decomposition level is equal to 5. The performance of this image denoising technique proposed in this work is proven by its comparison to three other denoising techniques existing in the literature. These three techniques are the denoising technique based on the soft thresholding in the SWT domain, the image denoising technique based on soft thresholding in the domain of 2D dual-tree DWT and the image denoising approach using deep neural network. All the previously mentioned techniques, including our proposed denoising approach, are applied to a number of noisy images, and the obtained results are in terms of peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). Those results show that this proposed denoising technique outperforms the other three denoising techniques used in this evaluation. [ABSTRACT FROM AUTHOR]

Image denoising is a significant procedure in image processing, and a good denoising method can improve the image quality. This study focuses on enhancing the estimation model of wavelet coefficients by improving the threshold function. Thus, a general construction method for a class of threshold functions is introduced, and sufficient conditions are given to ensure that the threshold functions are continuous, first-order differentiable and higher-order differentiable. It makes an existing class of improved threshold functions a particular case and enables the construction of other needed threshold functions based on this general approach. Experiments have shown that using the new threshold functions yields better denoising results for images containing salt and pepper noise, Gaussian noise and speckle noise. Moreover, as the smoothness of the threshold function is enhanced, the denoising effect is also improved. The improved wavelet coefficients estimation model can effectively boost the quality of image denoising, further enhancing the accuracy and effectiveness of computer vision algorithms. [ABSTRACT FROM AUTHOR]

The traditional methods for 3D reconstruction mainly involve using image processing techniques or deep learning segmentation models for rib extraction. After post-processing, voxel-based rib reconstruction is achieved. However, these methods suffer from limited reconstruction accuracy and low computational efficiency. To overcome these limitations, this paper proposes a 3D rib reconstruction method based on point cloud adaptive smoothing and denoising. We converted voxel data from CT images to multi-attribute point cloud data. Then, we applied point cloud adaptive smoothing and denoising methods to eliminate noise and non-rib points in the point cloud. Additionally, efficient 3D reconstruction and post-processing techniques were employed to achieve high-accuracy and comprehensive 3D rib reconstruction results. Experimental calculations demonstrated that compared to voxel-based 3D rib reconstruction methods, the 3D rib models generated by the proposed method achieved a 40% improvement in reconstruction accuracy and were twice as efficient as the former. [ABSTRACT FROM AUTHOR]

Image-space denoising of rendered images has become a commonly adopted approach since this post-rendering process often drastically reduces required sample counts (thus rendering times) for producing a visually pleasing image without noticeable noise. It is a common practice to conduct such denoising while preserving image details by exploiting auxiliary information (e.g., G-buffers) as well as input colors. However, it is still challenging to devise an ideal denoising framework that fully considers the two inputs with different characteristics, e.g., noisy but complete shading information in the input colors and less noisy but partial shading information in the auxiliary buffers. This paper proposes a transformer-based denoising framework with a new self-attention mechanism that infers a joint self-attention map, i.e., self-similarity in input features, through dual attention scores: one from noisy colors and another from auxiliary buffers. We demonstrate that this separate consideration of the two inputs allows our framework to produce more accurate denoising results than state-of-the-art denoisers for various test scenes. [ABSTRACT FROM AUTHOR]

Scanning electron microscope (SEM) enables imaging of micro-nano scale objects. It is an analytical tool widely used in the material, earth and life sciences. However, SEM images often suffer from high noise levels, influenced by factors such as dwell time, the time during which the electron beam remains per pixel during acquisition. Slower dwell times reduce noise but risk damaging the sample, while faster ones introduce uncertainty. To this end, the latest state-of-the-art denoising techniques must be explored. Experimentation is crucial to identify the most effective methods that balance noise reduction and sample preservation, ensuring high-quality SEM images with enhanced clarity and accuracy. A thorough analysis tracing the evolution of image denoising techniques was conducted, ranging from classical methods to deep learning approaches. A comprehensive taxonomy of this reverse problem solutions was established, detailing the developmental flow of these methods. Subsequently, the latest state-of-the-art techniques were identified and reviewed based on their reproducibility and the public availability of their source code. The selected techniques were then tested and investigated using scanning electron microscope images. After in-depth analysis and benchmarking, it is clear that the existing deep learning-based denoising techniques fall short in maintaining a balance between noise reduction and preserving crucial information for SEM images. Issues like information removal and over-smoothing have been identified. To address these constraints, there is a critical need for the development of SEM image denoising techniques that prioritize both noise reduction and information preservation. Additionally, one can see that the combination of several networks, such as the generative adversarial network and the convolutional neural network (CNN), known as BoostNet, or the vision transformer and the CNN, known as SCUNet, improves denoising performance. It is recommended to use blind techniques to denoise real noise while taking into account detail preservation and tackling excessive smoothing, particularly in the context of SEM. In the future the use of explainable AI will facilitate the debugging and the identification of these problems. [ABSTRACT FROM AUTHOR]

In this paper, a novel non-convex fractional-order image denoising model is proposed to suppress the staircase effect produced by the TV model while maintaining a neat contour. The model combines ℓ q (0 < q < 1) quasi-norm and fractional-order regularization, and employs a diffusion coefficient with a faster convergence rate to preserve more image edges and details. Additionally, an adaptive regularization parameter is designed to adjust the denoising performance of the algorithm. To obtain the optimal approximate solution of the model, an enhanced primal-dual algorithm is adopted and the complexity and convergence of the algorithm are theoretically analyzed. Finally, the effectiveness of the proposed method is demonstrated through numerical experiments. • A new non-convex FOTV model is proposed. • A new diffusion coefficient is introduced to retain more edge details of the image. • The existing primal-dual algorithm is improved, and the convergence of this algorithm is analyzed. • An adaptive regularization parameter is designed. [ABSTRACT FROM AUTHOR]