Search

Objective(s): This study aimed to create a deep learning (DL)-based denoising model using a residual neural network (Res-Net) trained to reduce noise in ringtype dedicated breast positron emission tomography (dbPET) images acquired in about half the emission time, and to evaluate the feasibility and the effectiveness of the model in terms of its noise reduction performance and preservation of quantitative values compared to conventional post-image filtering techniques. Methods: Low-count (LC) and full-count (FC) PET images with acquisition durations of 3 and 7 minutes, respectively, were reconstructed. A Res-Net was trained to create a noise reduction model using fifteen patients' data. The inputs to the network were LC images and its outputs were denoised PET (LC + DL) images, which should resemble FC images. To evaluate the LC + DL images, Gaussian and non-local mean (NLM) filters were applied to the LC images (LC + Gaussian and LC + NLM, respectively). To create reference images, a Gaussian filter was applied to the FC images (FC + Gaussian). The usefulness of our denoising model was objectively and visually evaluated using test data set of thirteen patients. The coefficient of variation (CV) of background fibroglandular tissue or fat tissue were measured to evaluate the performance of the noise reduction. The SUVmax and SUVpeak of lesions were also measured. The agreement of the SUV measurements was evaluated by Bland-Altman plots. Results: The CV of background fibroglandular tissue in the LC + DL images was significantly lower (9.10±2.76) than the CVs in the LC (13.60± 3.66) and LC + Gaussian images (11.51± 3.56). No significant difference was observed in both SUVmax and SUVpeak of lesions between LC + DL and reference images. For the visual assessment, the smoothness rating for the LC + DL images was significantly better than that for the other images except for the reference images. Conclusion: Our model reduced the noise in dbPET images acquired in about half the emission time while preserving quantitative values of lesions. This study demonstrates that machine learning is feasible and potentially performs better than conventional post-image filtering in dbPET denoising. [ABSTRACT FROM AUTHOR]

Noise corrupts ultrasound images and degrades spatial and contrast resolutions. Hence, it is challenging to characterize the lesions precisely using ultrasound images. The present study aims to evaluate 67 denoising filters and select the best one for ultrasound image denoising. Seven test images were synthesized to evaluate the performance of filters at three different noise levels. Eleven full‐reference quantitative image quality metrics (IQMs) were employed to evaluate the performance of the filters. A new filter evaluation method, Rank Analysis, was introduced and utilized at each noise level. The ten best filters with the smallest mean rank in all noise levels were defined for further analysis on real ultrasound images. The Rank Analysis was also employed for real ultrasound images, and filters were evaluated based on 14 IQMs (11 full‐reference and three no‐reference). Finally, the best filter was defined using the repeated measures analysis statistical test. According to the Rank Analysis results, the Spatial correlation (SCorr) filter obtained the best results with the mean rank scores±SD of 1 ± 0, which was significantly better than the other nine filters (p < 0.001). The second‐best results were achieved by three filters, Bitonic, most homogeneous neighborhood, and Lee diffusion (p < 0.05). We concluded that SCorr is the best filter for ultrasound image denoising. It can be used in the pre‐processing step before segmentation and diagnostic procedures. In addition, a new filter evaluation method, Rank Analysis, was introduced in this study, which is easy to use, fast, and provides reliable results. So, it can be used to evaluate newly developed filters in the future studies. [ABSTRACT FROM AUTHOR]

Due to the imaging mechanism of time-of-flight (ToF) sensors, the captured depth images usually suffer from severe noise and degradation. Though many RGB-guided methods have been proposed for depth image enhancement in the past few years, yet the enhancement performance on real-world depth images is still largely unsatisfactory. Two main reasons are the complexity of realistic noise and degradation in depth images, and the difficulty in collecting noise-clean pairs for supervised enhancement learning. This work aims to develop a self-supervised learning method for RGB-guided depth image enhancement, which does not require any noisy-clean pairs but can significantly boost the enhancement performance on real-world noisy depth images. To this end, we exploit the dependency between RGB and depth images to self-supervise the learning of the enhancement model. It is achieved by maximizing the cross-modal dependency between RGB and depth to promote the enhanced depth having dependency with the RGB of the same scene as much as possible. Furthermore, we augment the cross-modal dependency maximization formulation based on the optimal transport theory to achieve further performance improvement. Experimental results on both synthetic and real-world data demonstrate that our method can significantly outperform existing state-of-the-art methods on depth denoising, multi-path interference suppression, and hole filling. Particularly, our method shows remarkable superiority over existing ones on real-world data in handling various realistic complex degradation. Code is available at https://github.com/wjcyt/SRDE. [ABSTRACT FROM AUTHOR]

Enhancing the visibility in extreme low-light environments is a challenging task. Under nearly lightless condition, existing image denoising methods could easily break down due to significantly low SNR. In this paper, we systematically study the noise statistics in the imaging pipeline of CMOS photosensors, and formulate a comprehensive noise model that can accurately characterize the real noise structures. Our novel model considers the noise sources caused by digital camera electronics which are largely overlooked by existing methods yet have significant influence on raw measurement in the dark. It provides a way to decouple the intricate noise structure into different statistical distributions with physical interpretations. Moreover, our noise model can be used to synthesize realistic training data for learning-based low-light denoising algorithms. In this regard, although promising results have been shown recently with deep convolutional neural networks, the success heavily depends on abundant noisy-clean image pairs for training, which are tremendously difficult to obtain in practice. Generalizing their trained models to images from new devices is also problematic. Extensive experiments on multiple low-light denoising datasets – including a newly collected one in this work covering various devices – show that a deep neural network trained with our proposed noise formation model can reach surprisingly-high accuracy. The results are on par with or sometimes even outperform training with paired real data, opening a new door to real-world extreme low-light photography. [ABSTRACT FROM AUTHOR]

This paper introduces deformable convolution in deep learning based joint denoising and demosaicing (JDD), which yields more adaptable representation and larger receptive fields in features extraction for a superior restoration performance. However, the deformable convolution generally leads to considerable computational load and irregular memory access bottleneck, limiting its extensive deployment on edge devices. To address this issue, we develop grouping strategy and assign independent offsets to each kernel group to reduce the computation latency while keeping the accuracy. Motivated by the exploration for aggregate distribution characteristics of deformable offsets, we present the offset sharing methodology to simplify the memory access complexity of deformable convolution. As for hardware acceleration, we specially design a novel deformable matrix multiplication workflow incorporated with a deformable memory mapping unit to boost the computational throughput. The verification experiments on FPGA demonstrate that the proposed deformable convolution based JDD can restore 4K Ultra High Definition (UHD) images at 70FPS and yields significant promotion in visual effect and objective quality assessment. [ABSTRACT FROM AUTHOR]

Optical coherence tomography (OCT) is a widely-used modality in clinical imaging, which suffers from the speckle noise inevitably. Deep learning has proven its superior capability in OCT image denoising, while the difficulty of acquiring a large number of well-registered OCT image pairs limits the developments of paired learning methods. To solve this problem, some unpaired learning methods have been proposed, where the denoising networks can be trained with unpaired OCT data. However, majority of them are modified from the cycleGAN framework. These cycleGAN-based methods train at least two generators and two discriminators, while only one generator is needed for the inference. The dual-generator and dual-discriminator structures of cycleGAN-based methods demand a large amount of computing resource, which may be redundant for OCT denoising tasks. In this work, we propose a novel triplet cross-fusion learning (TCFL) strategy for unpaired OCT image denoising. The model complexity of our strategy is much lower than those of the cycleGAN-based methods. During training, the clean components and the noise components from the triplet of three unpaired images are cross-fused, helping the network extract more speckle noise information to improve the denoising accuracy. Furthermore, the TCFL-based network which is trained with triplets can deal with limited training data scenarios. The results demonstrate that the TCFL strategy outperforms state-of-the-art unpaired methods both qualitatively and quantitatively, and even achieves denoising performance comparable with paired methods. Code is available at: https://github.com/gengmufeng/TCFL-OCT. [ABSTRACT FROM AUTHOR]

We consider the reconstruction problem of video snapshot compressive imaging (SCI), which captures high-speed videos using a low-speed 2D sensor (detector). The underlying principle of SCI is to modulate sequential high-speed frames with different masks and then these encoded frames are integrated into a snapshot on the sensor and thus the sensor can be of low-speed. On one hand, video SCI enjoys the advantages of low-bandwidth, low-power and low-cost. On the other hand, applying SCI to large-scale problems (HD or UHD videos) in our daily life is still challenging and one of the bottlenecks lies in the reconstruction algorithm. Existing algorithms are either too slow (iterative optimization algorithms) or not flexible to the encoding process (deep learning based end-to-end networks). In this paper, we develop fast and flexible algorithms for SCI based on the plug-and-play (PnP) framework. In addition to the PnP-ADMM method, we further propose the PnP-GAP (generalized alternating projection) algorithm with a lower computational workload. We first employ the image deep denoising priors to show that PnP can recover a UHD color video with 30 frames from a snapshot measurement. Since videos have strong temporal correlation, by employing the video deep denoising priors, we achieve a significant improvement in the results. Furthermore, we extend the proposed PnP algorithms to the color SCI system using mosaic sensors, where each pixel only captures the red, green or blue channels. A joint reconstruction and demosaicing paradigm is developed for flexible and high quality reconstruction of color video SCI systems. Extensive results on both simulation and real datasets verify the superiority of our proposed algorithm. [ABSTRACT FROM AUTHOR]

Sinter ore is the main raw material of the blast furnace, and burn-through point (BTP) has a direct influence on the yield, quality, and energy consumption of the ironmaking process. Since iron ore sintering is a very complex industrial process with strong nonlinearity, multivariable coupling, random noises, and time variation, traditional soft-sensor models are hard to learn the knowledge of the sintering process. In this article, a multistep prediction model, called denoising spatial–temporal encoder–decoder, is developed to predict BTP in advance. First, the mechanism analysis is carried out to determine the relevant-BTP variables, and the BTP prediction is defined as a sequence-to-sequence modeling problem. Second, motivated by the random noises of industrial data, a denoising gated recurrent unit (DGRU) is designed to alleviate the impact of noise by adding a denoising gate into the GRU. In this case, the encoder with DGRU can better extract the latent variables of original sequence data. Then, spatial–temporal attention is embedded into the decoder to simultaneously capture the time-wise and variable-wise correlations between the latent variables and the target variable BTP. Finally, the experimental results on the real-world dataset of a sintering process demonstrated that the integrated multistep prediction model is effective and feasible. [ABSTRACT FROM AUTHOR]

Atmospheric lidar is susceptible to the influence of light attenuation, sky background light, and detector dark currents during the detection process. This results in a large amount of noise in the lidar return signal. To reduce noise and extract a useful signal, a novel denoising method combined with variational modal decomposition (VMD), the sparrow search algorithm (SSA) and singular value decomposition (SVD) is proposed. The SSA is used to optimize the number of decomposition layers K and the quadratic penalty factor α values of the VMD algorithm. Some intrinsic mode function (IMF) components obtained from the VMD-SSA decomposition are grouped and reconstructed according to the interrelationship number selection criterion. Then, the reconstructed signal is further denoised by combining the strong noise-reduction ability of SVD to obtain a clean lidar return signal. To verify the effectiveness of the VMD-SSA-SVD method, the method is compared and analysed with wavelet packet decomposition, empirical modal decomposition (EMD), ensemble empirical modal decomposition (EEMD), and adaptive noise-complete ensemble empirical modal decomposition (CEEMD), and its noise-reduction effect is considerably improved over that of the other four methods. The method can eliminate the complex noise in the lidar return signal while retaining all the details of the signal. The signal is not distorted, the waveform is smoother, and far-field noise interference can be suppressed. The denoised signal is closer to the real signal with higher accuracy, which shows the feasibility and the practicality of the proposed method. [ABSTRACT FROM AUTHOR]

As a powerful statistical signal modeling technique, sparse representation has been widely used in various image restoration (IR) applications. The sparsity-based methods have achieved leading performance in the past few decades. However, in recent years it has been surpassed by other methods, especially the recent deep learning based methods. In this paper, we address the question that whether sparse representation can be competitive again. The way we answer this question is to redesign it with a deep architecture. To be specific, we propose an end-to-end deep architecture that follows the process of the sparse representation based IR. In particular, we learn a sparse convolutional dictionary to replace the traditional dictionary, and a convolutional neural network (CNN) denoising prior to replace the image prior. Through end-to-end training, the parameters in convolutional dictionary and CNN denoiser can be jointly optimized. Experimental results on several representative IR tasks, including image denoising, deblurring and super-resolution, demonstrate that the proposed deep network can achieve superior performance against state-of-the-art model-based and learning-based methods. [ABSTRACT FROM AUTHOR]

Laser osteotomy promises precise cutting and minor bone tissue damage. We proposed Optical Coherence Tomography (OCT) to monitor the ablation process toward our smart laser osteotomy approach. The OCT image is helpful to identify tissue type and provide feedback for the ablation laser to avoid critical tissues such as bone marrow and nerve. Furthermore, in the implementation, the tissue classifier’s accuracy is dependent on the quality of the OCT image. Therefore, image denoising plays an important role in having an accurate feedback system. A common OCT image denoising technique is the frame-averaging method. Inherent to this method is the need for multiple images, i.e., the more images used, the better the resulting image quality. However, this approach comes at the price of increased acquisition time and sensitivity to motion artifacts. To overcome these limitations, we applied a deep-learning denoising method capable of imitating the frame-averaging method. The resulting image had a similar image quality to the frame-averaging and was better than the classical digital filtering methods. We also evaluated if this method affects the tissue classifier model’s accuracy that will provide feedback to the ablation laser. We found that image denoising significantly increased the accuracy of the tissue classifier. Furthermore, we observed that the classifier trained using the deep learning denoised images achieved similar accuracy to the classifier trained using frame-averaged images. The results suggest the possibility of using the deep learning method as a pre-processing step for real-time tissue classification in smart laser osteotomy. [ABSTRACT FROM AUTHOR]

Deep neural network based methods are the state of the art in various image restoration problems. Standard supervised learning frameworks require a set of noisy measurement and clean image pairs for which a distance between the output of the restoration model and the ground truth, clean images is minimized. The ground truth images, however, are often unavailable or very expensive to acquire in real-world applications. We circumvent this problem by proposing a class of structured denoisers that can be decomposed as the sum of a nonlinear image-dependent mapping, a linear noise-dependent term and a small residual term. We show that these denoisers can be trained with only noisy images under the condition that the noise has zero mean and known variance. The exact distribution of the noise, however, is not assumed to be known. We show the superiority of our approach for image denoising, and demonstrate its extension to solving other restoration problems such as image deblurring where the ground truth is not available. Our method outperforms some recent unsupervised and self-supervised deep denoising models that do not require clean images for their training. For deblurring problems, the method, using only one noisy and blurry observation per image, reaches a quality not far away from its fully supervised counterparts on a benchmark dataset. [ABSTRACT FROM AUTHOR]

Image denoising methods using deep neural networks have achieved a great progress in the image restoration. However, the recovered images restored by these deep denoising methods usually suffer from severe over-smoothness, artifacts, and detail loss. To improve the quality of restored images, we first propose Supplemental Priors (SP) method to adaptively predict depth-directed and sample-directed prior information for the reconstruction (decoder) networks. Furthermore, the over-parameterized deep neural networks and too precise supplemental prior information may cause an over-fitting, restricting the performance promotion. To improve the generalization of denoising networks, we further propose Regularization Priors (RP) method to flexibly learn depth-directed and dataset-directed regularization noise for the retrieving (encoder) networks. By respectively integrating the encoder and decoder with these plug-and-play RP block and SP block, we propose the final Adaptive Prior Denoising Networks, called APD-Nets. APD-Nets is the first attempt to simultaneously regularize and supplement denoising networks from the adaptive priors’ view with drawing learning-based mechanism into producing adaptive regularization noise and supplemental information. Extensive experiment results demonstrate our method significantly improves the generalization of denoising networks and the quality of restored images with greatly outperforming the traditional deep denoising methods both quantitatively and visually. The code will be released at https://github.com/JiangBoCS/APD-Nets. [ABSTRACT FROM AUTHOR]

Due to occlusion among views and temporal inconsistency in depth video, spatio-temporal distortion occurs in 3D synthesized video with depth image-based rendering. In this paper, we propose a deep Convolutional Neural Network (CNN)-based synthesized video denoising algorithm to reduce temporal flicker distortion and improve perceptual quality of 3D synthesized video. First, we analyze the spatio-temporal distortion, and model eliminating spatio-temporal distortion as a perceptual video denoising problem. Then, a deep learning-based synthesized video denoising network is proposed, in which a CNN-friendly spatio-temporal loss function is derived from a synthesized video quality metric and integrated with a single image denoising network architecture. Finally, specific schemes, i.e., specific Synthesized Video Denoising Networks (SynVD-Nets), and a general scheme, i.e., General SynVD-Net (GSynVD-Net), based on existing CNN-based denoising models, are developed to handle synthesized video with different distortion levels more effectively. Experimental results show that the proposed SynVD-Net and GSynVD-Net can outperform deep learning-based counterparts and conventional denoising methods, and significantly enhance perceptual quality of 3D synthesized video. [ABSTRACT FROM AUTHOR]

The conventional denoising method in Rayleigh imaging in a general sense requires an additional hardware investment and the use of the underlying physics. This work demonstrates an alternative image denoising reconstruction model based on unsupervised learning that aims to remove Mie scattering and shot noise interference from two-dimensional (2D) Rayleigh images. The model has two generators and two discriminators whose parameters can be trained with either feature-paired or feature-unpaired data independently. The proposed network was extensively evaluated with a qualitative examination and quantitative metrics, such as PSNR, ER, and SSIM. The results demonstrate that the feature-paired training network exhibits a better performance compared with several other networks reported in the literature. Moreover, when the flame features are not paired, the feature-unpaired training network still yields a good agreement with ground truth data. Specific indicators of the quantitative evaluation show a promising denoising ability with a peak signal-to-noise ratio of ~37 dB, an overall reconstruction error of ~1%, and a structure similarity index of ~0.985. Additionally, the pre-trained unsupervised model based on unpaired training can be generalized to denoise Rayleigh images with extra noise or a different Reynolds number without updating the model parameters. [ABSTRACT FROM AUTHOR]

Multidimensional (M-D) seismic data denoising is cast as an underdetermined inverse problem whose solution hinges on effective image priors extracted from machine learning knowledge. However, modeling seismic image priors is challenging due to the M-D nature of seismic images. Among the most promising prevailing image prior techniques is learning prior knowledge of the underlying structure by various 2-D or 3-D deep learning (DL)-based methods. However, for higher dimensional seismic data such as 4-D prestack data, these DL denoising schemes undoubtedly fail to capture the complete image structure in the absence of the flattening operation. To address this challenge, we present a framelet-based order- $p$ tensor neural network (dubbed the FPTNN) model to implicitly learn the priors reflecting the typical behavior of clear M-D seismic images in a data-driven manner. First, motivated by the supremacy of the framelet transform over the Fourier transform, replacing the Fourier transform with the framelet gives a new definition with respect to the order- $p$ tensor–tensor product (t-product). Then, through the redefined order- $p$ t-product, the order- $p$ tNN framework is a straightforward extension of the tNN with a standard t-product for M-D seismic denoising. By exploiting the fact that the order- $p$ t-product can be computed through matrix multiplication in the framelet domain, we can readily reach the optimal weighted parameters in FPTNN via DL on a set of transformed matrix frontal slices. The experiments on both the synthetic and real field seismic datasets comprehensively demonstrate the advantages of our method against other state-of-the-art (SOTA) methods. [ABSTRACT FROM AUTHOR]

In this paper, the bounded variation property of fuzzy models with smooth compositions have been studied, and they have been compared with the standard fuzzy composition (e.g., min–max). Moreover, the contribution of the bounded variation of the smooth fuzzy model for the noise removal and edge preservation of the digital images has been investigated. Different simulations on the test images have been employed to verify the results. The performance index related to the detected edges of the smooth fuzzy models in the presence of both Gaussian and Impulse (also known as salt-and-pepper noise) noises of different densities has been found to be higher than the standard well-known fuzzy models (e.g., min–max composition), which demonstrates the efficiency of smooth compositions in comparison to the standard composition. [ABSTRACT FROM AUTHOR]

A 3D point cloud is typically constructed from depth measurements acquired by sensors at one or more viewpoints. The measurements suffer from both quantization and noise corruption. To improve quality, previous works denoise a point cloud a posteriori after projecting the imperfect depth data onto 3D space. Instead, we enhance depth measurements directly on the sensed images a priori, before synthesizing a 3D point cloud. By enhancing near the physical sensing process, we tailor our optimization to our depth formation model before subsequent processing steps that obscure measurement errors. Specifically, we model depth formation as a combined process of signal-dependent noise addition and non-uniform log-based quantization. The designed model is validated (with parameters fitted) using collected empirical data from a representative depth sensor. To enhance each pixel row in a depth image, we first encode intra-view similarities between available row pixels as edge weights via feature graph learning. We next establish inter-view similarities with another rectified depth image via viewpoint mapping and sparse linear interpolation. This leads to a maximum a posteriori (MAP) graph filtering objective that is convex and differentiable. We minimize the objective efficiently using accelerated gradient descent (AGD), where the optimal step size is approximated via Gershgorin circle theorem (GCT). Experiments show that our method significantly outperformed recent point cloud denoising schemes and state-of-the-art image denoising schemes in two established point cloud quality metrics. [ABSTRACT FROM AUTHOR]

Deep learning (DL) based hyperspectral images (HSIs) denoising approaches directly learn the nonlinear mapping between noisy and clean HSI pairs. They usually do not consider the physical characteristics of HSIs. This drawback makes the models lack interpretability that is key to understanding their denoising mechanism and limits their denoising ability. In this paper, we introduce a novel model-guided interpretable network for HSI denoising to tackle this problem. Fully considering the spatial redundancy, spectral low-rankness, and spectral-spatial correlations of HSIs, we first establish a subspace-based multidimensional sparse (SMDS) model under the umbrella of tensor notation. After that, the model is unfolded into an end-to-end network named SMDS-Net, whose fundamental modules are seamlessly connected with the denoising procedure and optimization of the SMDS model. This makes SMDS-Net convey clear physical meanings, i.e., learning the low-rankness and sparsity of HSIs. Finally, all key variables are obtained by discriminative training. Extensive experiments and comprehensive analysis on synthetic and real-world HSIs confirm the strong denoising ability, strong learning capability, promising generalization ability, and high interpretability of SMDS-Net against the state-of-the-art HSI denoising methods. The source code and data of this article will be made publicly available at https://github.com/bearshng/smds-net for reproducible research. [ABSTRACT FROM AUTHOR]

This paper presents a scalable approximate Bayesian method for image restoration using Total Variation (TV) priors, with the ability to offer uncertainty quantification. In contrast to most optimization methods based on maximum a posteriori estimation, we use the Expectation Propagation (EP) framework to approximate minimum mean squared error (MMSE) estimates and marginal (pixel-wise) variances, without resorting to Monte Carlo sampling. For the classical anisotropic TV-based prior, we also propose an iterative scheme to automatically adjust the regularization parameter via Expectation Maximization (EM). Using Gaussian approximating densities with diagonal covariance matrices, the resulting method allows highly parallelizable steps and can scale to large images for denoising, deconvolution, and compressive sensing (CS) problems. The simulation results illustrate that such EP methods can provide a posteriori estimates on par with those obtained via sampling methods but at a fraction of the computational cost. Moreover, EP does not exhibit strong underestimation of posteriori variances, in contrast to variational Bayes alternatives. [ABSTRACT FROM AUTHOR]

This paper presents a new variational inference framework for image restoration and a convolutional neural network (CNN) structure that can solve the restoration problems described by the proposed framework. Earlier CNN-based image restoration methods primarily focused on network architecture design or training strategy with non-blind scenarios where the degradation models are known or assumed. For a step closer to real-world applications, CNNs are also blindly trained with the whole dataset, including diverse degradations. However, the conditional distribution of a high-quality image given a diversely degraded one is too complicated to be learned by a single CNN. Therefore, there have also been some methods that provide additional prior information to train a CNN. Unlike previous approaches, we focus more on the objective of restoration based on the Bayesian perspective and how to reformulate the objective. Specifically, our method relaxes the original posterior inference problem to better manageable sub-problems and thus behaves like a divide-and-conquer scheme. As a result, the proposed framework boosts the performance of several restoration problems compared to the previous ones. Specifically, our method delivers state-of-the-art performance on Gaussian denoising, real-world noise reduction, blind image super-resolution, and JPEG compression artifacts reduction. Our code and more details are available on our project page, https://github.com/JWSoh/VDIR. [ABSTRACT FROM AUTHOR]

Image denoising aims to restore a clean image from an observed noisy one. Model-based image denoising approaches can achieve good generalization ability over different noise levels and are with high interpretability. Learning-based approaches are able to achieve better results, but usually with weaker generalization ability and interpretability. In this paper, we propose a wavelet-inspired invertible network (WINNet) to combine the merits of the wavelet-based approaches and learning-based approaches. The proposed WINNet consists of $K$ -scale of lifting inspired invertible neural networks (LINNs) and sparsity-driven denoising networks together with a noise estimation network. The network architecture of LINNs is inspired by the lifting scheme in wavelets. LINNs are used to learn a non-linear redundant transform with perfect reconstruction property to facilitate noise removal. The denoising network implements a sparse coding process for denoising. The noise estimation network estimates the noise level from the input image which will be used to adaptively adjust the soft-thresholds in LINNs. The forward transform of LINNs produces a redundant multi-scale representation for denoising. The denoised image is reconstructed using the inverse transform of LINNs with the denoised detail channels and the original coarse channel. The simulation results show that the proposed WINNet method is highly interpretable and has strong generalization ability to unseen noise levels. It also achieves competitive results in the non-blind/blind image denoising and in image deblurring. [ABSTRACT FROM AUTHOR]

This work tackles the issue of noise removal from images, focusing on the well-known DCT image denoising algorithm. The latter, stemming from signal processing, has been well studied over the years. Though very simple, it is still used in crucial parts of state-of-the-art “traditional” denoising algorithms such as BM3D. For a few years however, deep convolutional neural networks (CNN), especially DnCNN, have outperformed their traditional counterparts, making signal processing methods less attractive. In this paper, we demonstrate that a DCT denoiser can be seen as a shallow CNN and thereby its original linear transform can be tuned through gradient descent in a supervised manner, improving considerably its performance. This gives birth to a fully interpretable CNN called DCT2net. To deal with remaining artifacts induced by DCT2net, an original hybrid solution between DCT and DCT2net is proposed combining the best that these two methods can offer; DCT2net is selected to process non-stationary image patches while DCT is optimal for piecewise smooth patches. Experiments on artificially noisy images demonstrate that two-layer DCT2net provides comparable results to BM3D and is as fast as DnCNN algorithm. [ABSTRACT FROM AUTHOR]

Low-light images captured in the real world are inevitably corrupted by sensor noise. Such noise is spatially variant and highly dependent on the underlying pixel intensity, deviating from the oversimplified assumptions in conventional denoising. Existing light enhancement methods either overlook the important impact of real-world noise during enhancement, or treat noise removal as a separate pre- or post-processing step. We present Coordinated Enhancement for Real-world Low-light Noisy Images (CERL), that seamlessly integrates light enhancement and noise suppression parts into a unified and physics-grounded optimization framework. For the real low-light noise removal part, we customize a self-supervised denoising model that can easily be adapted without referring to clean ground-truth images. For the light enhancement part, we also improve the design of a state-of-the-art backbone. The two parts are then joint formulated into one principled plug-and-play optimization. Our approach is compared against state-of-the-art low-light enhancement methods both qualitatively and quantitatively. Besides standard benchmarks, we further collect and test on a new realistic low-light mobile photography dataset (RLMP), whose mobile-captured photos display heavier realistic noise than those taken by high-quality cameras. CERL consistently produces the most visually pleasing and artifact-free results across all experiments. Our RLMP dataset and codes are available at: https://github.com/VITA-Group/CERL. [ABSTRACT FROM AUTHOR]

In recent years, image denoising has benefited a lot from deep neural networks. However, these models need large amounts of noisy-clean image pairs for supervision. Although there have been attempts in training denoising networks with only noisy images, existing self-supervised algorithms suffer from inefficient network training, heavy computational burden, or dependence on noise modeling. In this paper, we proposed a self-supervised framework named Neighbor2Neighbor for deep image denoising. We develop a theoretical motivation and prove that by designing specific samplers for training image pairs generation from only noisy images, we can train a self-supervised denoising network similar to the network trained with clean images supervision. Besides, we propose a regularizer in the perspective of optimization to narrow the optimization gap between the self-supervised denoiser and the supervised denoiser. We present a very simple yet effective self-supervised training scheme based on the theoretical understandings: training image pairs are generated by random neighbor sub-samplers, and denoising networks are trained with a regularized loss. Moreover, we propose a training strategy named BayerEnsemble to adapt the Neighbor2Neighbor framework in raw image denoising. The proposed Neighbor2Neighbor framework can enjoy the progress of state-of-the-art supervised denoising networks in network architecture design. It also avoids heavy dependence on the assumption of the noise distribution. We evaluate the Neighbor2Neighbor framework through extensive experiments, including synthetic experiments with different noise distributions and real-world experiments under various scenarios. The code is available online: https://github.com/TaoHuang2018/Neighbor2Neighbor. [ABSTRACT FROM AUTHOR]

Denoising videos in real-time is critical in many applications, including robotics and medicine, where varying-light conditions, miniaturized sensors, and optics can substantially compromise image quality. This work proposes the first video denoising method based on a deep neural network that achieves state-of-the-art performance on dynamic scenes while running in real-time on VGA video resolution with no frame latency. The backbone of our method is a novel, remarkably simple, temporal network of cascaded blocks with forward block output propagation. We train our architecture with short, long, and global residual connections by minimizing the restoration loss of pairs of frames, leading to a more effective training across noise levels. It is robust to heavy noise following Poisson-Gaussian noise statistics. The algorithm is evaluated on RAW and RGB data. We propose a denoising algorithm that requires no future frames to denoise a current frame, reducing its latency considerably. The visual and quantitative results show that our algorithm achieves state-of-the-art performance among efficient algorithms, achieving from two-fold to two-orders-of-magnitude speed-ups on standard benchmarks for video denoising. [ABSTRACT FROM AUTHOR]

Image noise removal is a common problem with many proposed solutions. The current standard is set by learning-based approaches, however these are not appropriate in all scenarios, perhaps due to lack of training data or the need for predictability in novel circumstances. The bitonic filter is a non-learning-based filter for removing noise from signals, with a mathematical morphology (ranking) framework in which the signal is postulated to be locally bitonic (having only one minimum or maximum) over some domain of finite extent. A novel version of this filter is developed in this paper, with a domain that is locally-adaptive to the signal, and other adjustments to allow application to real image sensor noise. These lead to significant improvements in noise reduction performance at no cost to processing times. The new bitonic filter performs better than the block-matching 3D filter for high levels of additive white Gaussian noise. It also surpasses this and other more recent non-learning-based filters for two public data sets containing real image noise at various levels. This is despite an additional adjustment to the block-matching filter, which leads to significantly better performance than has previously been cited on these data sets. The new bitonic filter has a signal-to-noise ratio 2.4dB lower than the best learning-based techniques when they are optimally trained. However, the performance gap is closed completely when these techniques are trained on data sets not directly related to the benchmark data. This demonstrates what can be achieved with a predictable, explainable, entirely local technique, which makes no assumptions of repeating patterns either within an image or across images, and hence creates residual images which are well behaved even in very high noise. Since the filter does not require training, it can still be used in situations where training is either difficult or inappropriate. [ABSTRACT FROM AUTHOR]

Recent deep convolutional neural networks for real-world noisy image denoising have shown a huge boost in performance by training a well-engineered network over external image pairs. However, most of these methods are generally trained with supervision. Once the testing data is no longer compatible with the training conditions, they can exhibit poor generalization and easily result in severe overfitting or degrading performances. To tackle this barrier, we propose a novel denoising algorithm, dubbed as Meta PID Attention Network (MPA-Net). Our MPA-Net is built based upon stacking Meta PID Attention Modules (MPAMs). In each MPAM, we utilize a second-order attention module (SAM) to exploit the channel-wise feature correlations with second-order statistics, which are then adaptively updated via a proportional-integral-derivative (PID) guided meta-learning framework. This learning framework exerts the unique property of the PID controller and meta-learning scheme to dynamically generate filter weights for beneficial update of the extracted features within a feedback control system. Moreover, the dynamic nature of the framework enables the generated weights to be flexibly tweaked according to the input at test time. Thus, MPAM not only achieves discriminative feature learning, but also facilitates a robust generalization ability on distinct noises for real images. Extensive experiments on ten datasets are conducted to inspect the effectiveness of the proposed MPA-Net quantitatively and qualitatively, which demonstrates both its superior denoising performance and promising generalization ability that goes beyond those of the state-of-the-art denoising methods. [ABSTRACT FROM AUTHOR]

A lightweight blind image denoiser, called blind compact denoising network (BCDNet), is proposed in this paper to achieve excellent trade-offs between performance and network complexity. With only 330K parameters, the proposed BCDNet is composed of the compact denoising network (CDNet) and the guidance network (GNet). From a noisy image, GNet extracts a guidance feature, which encodes the severity of the noise. Then, using the guidance feature, CDNet filters the image adaptively according to the severity to remove the noise effectively. Moreover, by reducing the number of parameters without compromising the performance, CDNet achieves denoising not only effectively but also efficiently. Experimental results show that the proposed BCDNet yields state-of-the-art or competitive denoising performances on various datasets while requiring significantly fewer parameters. [ABSTRACT FROM AUTHOR]

Constructing effective priors is critical to solving ill-posed inverse problems in image processing and computational imaging. Recent works focused on exploiting non-local similarity by grouping similar patches for image modeling, and demonstrated state-of-the-art results in many image restoration applications. However, compared to classic methods based on filtering or sparsity, non-local algorithms are more time-consuming, mainly due to the highly inefficient block matching step, i.e., distance between every pair of overlapping patches needs to be computed. In this work, we propose a novel Self-Convolution operator to exploit image non-local properties in a unified framework. We prove that the proposed Self-Convolution based formulation can generalize the commonly-used non-local modeling methods, as well as produce results equivalent to standard methods, but with much cheaper computation. Furthermore, by applying Self-Convolution, we propose an effective multi-modality image restoration scheme, which is much more efficient than conventional block matching for non-local modeling. Experimental results demonstrate that (1) Self-Convolution with fast Fourier transform implementation can significantly speed up most of the popular non-local image restoration algorithms, with two-fold to nine-fold faster block matching, and (2) the proposed online multi-modality image restoration scheme achieves superior denoising results than competing methods in both efficiency and effectiveness on RGB-NIR images. The code for this work is publicly available at https://github.com/GuoLanqing/Self-Convolution. [ABSTRACT FROM AUTHOR]

The principal rank-one (RO) components of an image represent the self-similarity of the image, which is an important property for image restoration. However, the RO components of a corrupted image could be decimated by the procedure of image denoising. We suggest that the RO property should be utilized and the decimation should be avoided in image restoration. To achieve this, we propose a new framework comprised of two modules, i.e., the RO decomposition and RO reconstruction. The RO decomposition is developed to decompose a corrupted image into the RO components and residual. This is achieved by successively applying RO projections to the image or its residuals to extract the RO components. The RO projections, based on neural networks, extract the closest RO component of an image. The RO reconstruction is aimed to reconstruct the important information, respectively from the RO components and residual, as well as to restore the image from this reconstructed information. Experimental results on four tasks, i.e., noise-free image super-resolution (SR), realistic image SR, gray-scale image denoising, and color image denoising, show that the method is effective and efficient for image restoration, and it delivers superior performance for realistic image SR and color image denoising. Our source code is available online. [ABSTRACT FROM AUTHOR]

Low-rank tensor completion (LRTC) that aims to restore the latent clean data from an incomplete and/or degraded observation, shows promising results in ubiquitous tensorial data completion applications. Most tensor completion approaches are vulnerable to outliers since their derivations are based on $\ell _{2}$ -space to be robust against Gaussian noise. In this work, to tackle this issue, $\ell _{p}$ -regression $(0 < p < 2)$ is employed to achieve outlier resistance, where a factored form of tensor train (TT)-format representation is regularized by the low-TT-rank prior to exploit the inter-fibers correlation. On the basis of that, an effective iterative $\ell _{p}$ -regression TT completion method (referred to $\ell _{p}$ -TTC) is proposed, with the advantage of not requiring the hard-to-determine user-defined weights in TT rank model. Extensive experiment results are presented to demonstrate the outlier resistance of the proposed $\ell _{p}$ -TTC, and showing the effective and superior performance in both bistatic MIMO radar localization and color image inpainting and denoising, compared with state-of-the-art tensor completion approaches. [ABSTRACT FROM AUTHOR]

Recently, deep-learning-based denoising methods for hyperspectral images (HSIs) have been comprehensively studied and achieved impressive performance because they can effectively extract complex and nonlinear image features. Compared with deep-learning-based methods, the nonlocal similarity-based denoising methods are more suitable for images containing edges or regular textures. We propose a powerful HSI denoising method, termed non-local 3-D convolutional neural network (NL-3DCNN), combining traditional machine learning and deep learning techniques. NL-3DCNN exploits the high spectral correlation of an HSI using subspace representation, and the corresponding representation coefficients are termed eigenimages. The high spatial correlation in eigenimages is exploited by grouping nonlocal similar patches, which are denoised by a 3-D convolutional neural network. The numerical and graphical denoising results of the simulated and real data show that the proposed method is superior to the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

In this article, an algorithm is introduced which not only focuses on enhancing low light images but also denoises images to produce more visually pleasing outputs. It is observed that various methods ignore noise during enhancement processes. This causes, enhancement of noise which leads to significant information lost. The paper projected a novel framework for low light images that performs enhancement and denoising jointly. The proposed paper uses $L_{2}$ - $L_{P}$ image decomposition to obtain reflectance and illumination concurrently. The illumination layer is corrected using the proposed weighting distribution and generates enhanced output. Further to this, noise suppressed bilateral filter is employed here for denoising process and gamma function is applied in subsequent step for additional contrast improvement. Experimental trials illustrate that the proposed method yields result with good contrast and brightness when it is compared to various enhancement techniques. [ABSTRACT FROM AUTHOR]

Noise interference during the acquisition of digital images can severely degrade image quality, particularly for images captured under low-light conditions; however, the removal of image noise requires sophisticated digital image processing systems. This study presents a hardware-based solution to real-time image denoising using an existing algorithm designed for the removal of mixed impulse noise (salt-and-pepper and random-valued impulse noise), while preserving image edge details and image borders, without the need for additional computation time or memory capacity. Note that mixed impulse noise is typical of most real-world situations, such as the video noise associated with dashboard cameras. The proposed design was implemented using 180 nm complementary metal-oxide-semiconductor (CMOS) technology, consuming only 21.7 mW when operated at 200 MHz. This operating frequency allows the proposed chip to process noisy video streams with resolution of $1920\mathbf {\times }1080$ at 60 frames per second in real time. In terms of image restoration, the proposed algorithm achieved image quality on par with that achieved using software simulation. We also demonstrated the efficacy of the proposed scheme in denoising noisy video images from a dashboard camera. [ABSTRACT FROM AUTHOR]

Uniquely capable of simultaneous imaging of the hemoglobin concentration, blood oxygenation, and flow speed at the microvascular level in vivo, multi-parametric photoacoustic microscopy (PAM) has shown considerable impact in biomedicine. However, the multi-parametric PAM acquisition requires dense sampling and thus a high laser pulse repetition rate (up to MHz), which sets a strict limit on the applicable pulse energy due to safety considerations. A similar limitation is shared by high-speed PAM, which also uses lasers with high pulse repetition rates. To achieve high quantitative accuracy besides good structural visualization at low levels of laser fluence in PAM, we have developed a new, sparse coding-based two-step denoising technique. In the setting of intravital brain imaging, we demonstrated that this unsupervised learning approach enabled the reduction of the laser fluence in PAM by 5 times without compromise of the image quality (structural similarity index measure or SSIM: >0.92) and the quantitative accuracy (errors: <4.9%). Offering a significant relaxation in the requirement of PAM on laser fluence while maintaining the quality of structural imaging and accuracy of quantitative measurements, this sparse coding-based approach is expected to facilitate the application and clinical translation of multi-parametric PAM and high-speed PAM, which have a tight photon budget due to either safety considerations or laser source limitations. [ABSTRACT FROM AUTHOR]

Erratic seismic noise, following a (known or unknown) non-Gaussian distribution, poses a formidable challenge to conventional methods of random noise attenuation. Many erratic noise cancellation methods, for instance, robust reduced-rank and sparsity-promoting filtering, have been proven to achieve promising results in overcoming this challenge. Among them, deep learning (DL) methods require no assumptions about the underlying clear seismic image and are also more robust against erratic and random noise. However, the success of existing DL-based denoising methods strongly depends on supervised learning from a large number of ground-truth seismic images affected by erratic noise and their clean counterparts, which are typically unavailable in a real-world setting. As an alternative, this article presents an unsupervised DL method for erratic-plus-Gaussian noise removal based on a robust deep convolutional autoencoder (RDCAE). In the RDCAE, the mean squared error (mse) loss in a classic DCAE is replaced by the smooth Welsch function to exploit the concept of robust image denoising. In this way, the erratic noise is downweighted by means of a curbed weight defined in terms of the Welsch function. In contrast, the random noise is diluted by combining the mean square in the Welsch function and the total variation (TV). Subsequently, the training procedures required for solving the RDCAE are derived on the basis of the backpropagation (BP) algorithm for a neural network. Experiments conducted on both synthetic and real field datasets are reported to illustrate the efficacy of the proposed method. [ABSTRACT FROM AUTHOR]

Magnetic resonance sounding (MRS) measurements commonly suffer from a notably low signal-to-noise ratio (SNR). In recent years, many denoising methods have been developed, which have demonstrated the useful capability to improve the SNR. However, when MRS measurements are implemented on the sites with high noise levels, i.e., the human living environment, the conventional methods are helpless to recover the effective MRS signal, which is submerged in extensive environmental noise. In addition, the conventional methods that depend on signal models and the corresponding prior assumptions commonly rely on manual experience, which brings obstacles to the automation and efficiency of signal processing. To solve the above problems, we attempt to apply an intelligent denoising framework with a novel neural network as the basic tool for deep learning, called Dn-ResUnet in this article. The network extracts the features of the MRS signal through the encoder and decoder layers of the Dn-ResUnet structure, in which residual learning is adopted to accelerate the training process and improve denoising performance. Once the training is completed, the deep learning realizes adaptive denoising with no need for 1) prior assumptions of the MRS signal and noise; 2) optimal filter parameter tuning; or 3) expensive time cost. The comparison experiments demonstrate that the Dn-ResUnet model provides superior noise cancellation performance, especially it can replace the conventional methods to recover the effective MRS signals in noise levels down to an SNR of −30 dB. In addition, the noise attenuation tests are performed on synthetic and real data. The results show that the framework of deep learning yields a convincing performance in MRS signal denoising. [ABSTRACT FROM AUTHOR]

This article proposes a denoising method based on sparse spectral–spatial and low-rank representations (SSSLRR) using the 3-D orthogonal transform (3-DOT). SSSLRR can be effectively used to remove the Gaussian and mixed noise. SSSLRR uses 3-DOT to decompose noisy HSI to sparse transform coefficients. The 3-D discrete orthogonal wavelet transform (3-D DWT) is a representative 3-DOT suitable for denoising since it concentrates on the signal in few transform coefficients, and the 3-D discrete orthogonal cosine transform (3-D DCT) is another example. An SSSLRR using 3-D DWT will be called SSSLRR-DWT. SSSLRR-DWT is an iterative algorithm based on the alternating direction method of multipliers (ADMM) that uses sparse and nuclear norm penalties. We use an ablation study to show the effectiveness of the penalties we employ in the method. Both simulated and real hyperspectral datasets demonstrate that SSSLRR outperforms other comparative methods in quantitative and visual assessments to remove the Gaussian and mixed noise. [ABSTRACT FROM AUTHOR]

Remote sensing images, especially hyperspectral images (HSIs), are extremely vulnerable to random noise and stripe noise. As a key aspect of HSI data quality improvement, stripe noise removal has always been a pervasive issue in remote sensing image processing. Convolutional neural networks have been applied for HSI data destriping. However, the existing methods lose the stripe-free component of the original image to a certain extent. These models also ignore the global spatial context of images and the correlation between spatial information and spectral information. Therefore, we propose a novel destriping convolutional network to overcome the problems with the existing methods. Octave convolution is used to extract cross-frequency features, and separate and compress the low-frequency information of the images, while dilation convolution (Dila-Conv) is used to reduce the amount of required calculation and also preserve the key image information. In addition, Dila-Conv can expand the receptive field to obtain multiscale features. Finally, a cross-channel enhanced spatial–spectral feature fusion module is used to acquire and integrate spatial context information and interchannel dependencies on a global scale as auxiliary information so that the network model can learn and pay attention to key feature information, specifically, “what to look for” and “where to look at,” which can facilitate the distinction between stripe and stripe-free components. Experimental results obtained using multiple datasets demonstrated that the proposed method can outperform the existing comparable methods and can produce satisfactory results in terms of visual effects and quantitative evaluation. [ABSTRACT FROM AUTHOR]

Hyperspectral image (HSI) denoising is a crucial preprocessing task to improve the performance of the subsequent HSI interpretation and applications. With recent progress in deep learning, HSI denoising methods based on deep neural networks have attracted increasing interest and achieved the state-of-the-art performance. Nevertheless, most of these methods are based on network structures originally developed for grayscale and color images and require a change of network structure to be applicable to HSIs. The new network architectures often lead to complicated models and limited flexibility, which, in turn, result in difficulty in learning and demand of a large number of training samples. In this article, we propose an innovative two-stage learning method including pretraining and fine-tuning procedures. In the first stage, a denoising convolutional neural network can be pretrained with pairs of corrupted and clean images. In the second stage, the pretrained network is fine-tuned via a self-supervised learning strategy to capture the spectral correlation in HSIs. The training pairs in the second stage are constructed from the neighboring band images in the target noisy HSI, leading to a novel idea of embedding spectral information into denoiser through the target image, rather than the change of the network architecture. This model has strong adaptability such that many image denoising networks can be easily adopted for HSIs, while the external hyperspectral training set is optional but not mandatory. Experimental results show that our method has competitive performance compared with the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Hyperspectral image (HSI) denoising is an ill-posed inverse problem. The underlying physical model is always important to tackle this problem, which is unfortunately ignored by most of the current deep learning (DL)-based methods, producing poor denoising performance. To address this issue, this article introduces an end-to-end model-aided nonlocal neural network (MAC-Net) which simultaneously takes the spectral low-rank model and spatial deep prior into account for HSI noise reduction. Specifically, motivated by the success of the spectral low-rank model in depicting the strong spectral correlations and the nonlocal similarity prior in capturing spatial long-range dependencies, we first build a spectral low-rank model and then integrate a nonlocal U-Net into the model. In this way, we obtain a hybrid model-based and DL-based HSI denoising method where the spatial local and nonlocal multi-scale and spectral low-rank structures are effectively exploited. After that, we cast the optimization and denoising procedure of the hybrid method as a forward process of a neural network and introduce a set of learnable modules to yield our MAC-Net. Compared with traditional model-based methods, our MAC-Net overcomes the difficulties of accurate modeling, thanks to the strong learning and representation ability of DL. Unlike most “black-box” DL-based methods, the spectral low-rank model is beneficial to increase the generalization ability of the network and decrease the requirement of training samples. Experimental results on the natural and remote-sensing HSIs show that MAC-Net achieves state-of-the-art performance over both model-based and DL-based methods. The source code and data of this article will be made publicly available at https://github.com/bearshng/mac-net for reproducible research. [ABSTRACT FROM AUTHOR]

Currently, the diagnosis of single fault marked by distinct characteristics has received mass concern, and the related research achievements are remarkable. However, the diagnosis of early multiple intermittent (EMI) faults commonly existing in industrial systems is still an intractable problem, owing to: 1) the scarcity of fault data and the faintness of features and 2) the mutual interaction of components and the coupling of fault characteristics. In order to address the problem, this article proposes an improved sparse autoencoder and multilevel denoising strategy (MDS-ISAE) for diagnosing EMI faults. First, a relational constraint term is constructed to mitigate the effect of data correlation. Second, a multilevel denoising strategy is designed to enhance the robustness of AE feature learning with strong background noise. Third, a resizable resampling strategy is planned to tackle the skew distribution of diagnosis data. Based on the above strategies, an MDS-ISAE-based model is constructed to achieve EMI faults diagnosis. Further, the evaluation criteria of diagnosis performance are proposed and the applicability of the method is tested. Finally, the effectiveness and practicability of the proposed method are verified by artificial damage and real fault experiments, respectively. [ABSTRACT FROM AUTHOR]

Structural abnormalities and functional changes of renal microvascular networks play a significant pathophysiologic role in the occurrence of kidney diseases. Super-resolution ultrasound imaging has been successfully utilized to visualize the microvascular network and provide valuable diagnostic information. To prevent the burst of microbubbles, a lower mechanical index (MI) is generally used in ultrasound localization microscopy (ULM) imaging. However, high noise levels lead to incorrect signal localizations in relatively low-MI settings and deep tissue. In this study, we implemented a block-matching 3-D (BM3D) image-denoising method, after the application of singular value decomposition filtering, to further suppress the noise at various depths. The in vitro flow-phantom results show that the BM3D method helps the significant reduction of the error localizations, thus improving the localization accuracy. In vivo rhesus macaque experiments help conclude that the BM3D method improves the resolution more than other image-based denoising techniques, such as the nonlocal means method. The obtained clutter-filtered images with fewer incorrect localizations can enable robust ULM imaging, thus helping in establishing an effective diagnostic tool. [ABSTRACT FROM AUTHOR]

Medical imaging denoising faces great challenges, yet is in great demand. With its distinctive characteristics, medical imaging denoising in the image domain requires innovative deep learning strategies. In this study, we propose a simple yet effective strategy, the content-noise complementary learning (CNCL) strategy, in which two deep learning predictors are used to learn the respective content and noise of the image dataset complementarily. A medical image denoising pipeline based on the CNCL strategy is presented, and is implemented as a generative adversarial network, where various representative networks (including U-Net, DnCNN, and SRDenseNet) are investigated as the predictors. The performance of these implemented models has been validated on medical imaging datasets including CT, MR, and PET. The results show that this strategy outperforms state-of-the-art denoising algorithms in terms of visual quality and quantitative metrics, and the strategy demonstrates a robust generalization capability. These findings validate that this simple yet effective strategy demonstrates promising potential for medical image denoising tasks, which could exert a clinical impact in the future. Code is available at: https://github.com/gengmufeng/CNCL-denoising. [ABSTRACT FROM AUTHOR]

Diffusion kurtosis imaging (DKI) has been shown to be valuable in a wide range of neuroscientific and clinical applications. However, reliable estimation of DKI tensors is often compromised by noise, especially for the kurtosis tensor (KT). Here, we propose a joint denoising and estimating framework that integrates multiple sources of prior information, including nonlocal structural self-similarity (NSS), local spatial smoothness (LSS), physical relevance (PR) of the DKI model, and noise characteristics of magnitude diffusion MRI (dMRI) images for improved estimation of DKI tensors. The local and nonlocal spatial smoothing constraints are complementary to each other, making the proposed framework highly effective in reducing the noise fluctuations on DKI tensors, especially KT. As an additional refinement, we propose to impose a physically relevant constraint within our joint denoising and estimation framework. We further adopt the first-moment noise-corrected fitting model (M1NCM) to remove the noncentral ${\chi }$ -distribution noise bias. The effectiveness of integrating multiple sources of priors into the joint framework is verified by comparing the proposed M1NCM-NSS-LSS-PR method with various versions of M1NCM-based estimators and two state-of-the-art methods. Results show that the proposed method outperformed the compared methods in simulations and in-vivo dMRI datasets of both spatially stationary and nonstationary noise distributions. The in-vivo experiments also show that the proposed M1NCM-NSS-LSS-PR method was robust to the number of diffusion directions. [ABSTRACT FROM AUTHOR]

Global monitoring for complex large-scale chemical processes is often challenging because of complex correlations among variables. This article proposes an optimized denoising autoencoder (DAE)-based distributed monitoring method to achieve efficient and robust monitoring of multiunit, nonlinear processes. First, a process is decomposed into multiple units, and then stacked DAE is used to extract the robust features of each unit and represent variable correlations within each unit. Second, deep regression neural networks are established between a local unit and its neighboring units to represent the correlations among units. A reinforcement learning-based neural architecture search method is proposed to avoid the tedious manual tuning process and obtain a high-performance neural network. Finally, a numerical simulation example, the Tennessee–Eastman benchmark process, and a laboratory-scale distillation process are used to verify the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

3-D imaging devices (e.g., depth cameras and optical and laser scanners) are frequently used to measure outdoor/indoor scenes. The measurement data represented by 3-D point clouds are, however, usually noisy and should be denoised to facilitate subsequent applications. Existing point cloud denoising methods typically perform: 1) point position updating directly or 2) point normal filtering followed by point position updating, and seldom consider the correlation between position updating and normal filtering, leading to less desirable denoised results. This article proposes a nonlocal low-rank point cloud denoising framework (NL-PCD) to handle 3-D measurement surfaces with different-scale and -type noise. We first design a rotation-invariant feature descriptor, called height and normal patch (HNP), to encode the position and normal information of each point, and search nonlocal yet geometrically similar HNPs in the whole point cloud. Similar HNPs are then grouped and packed into a noisy matrix which exhibits high rank due to the existence of the noise. Finally, we remove the noise from the noisy matrix through low-rank matrix recovery by making use of nonlocal similarities among HNPs. In such a way, we can optimize both point positions and normals (i.e., dual geometry domains) in a joint framework to fully exploit the correlation between the two domains for point cloud denoising. Experimental results on synthetic and real-world data demonstrate that our NL-PCD outperforms both traditional and deep learning-based denoising methods in terms of noise removal and feature preservation. [ABSTRACT FROM AUTHOR]