Explore the vast range of titles available.

Removing noise from acquired images is a crucial step in various image processing and computer vision tasks. However, the existing methods primarily focus on removing specific noise and ignore the ability to work across modalities, resulting in limited generalization performance. Inspired by the iterative procedure of image processing used by professionals, we propose a pixel-wise crossmodal image-denoising method based on deep reinforcement learning to effectively handle noise across modalities. We proposed a similarity reward to help teach an optimal action sequence to model the step-wise nature of the human processing process explicitly. In addition, We designed an action set capable of handling multiple types of noise to construct the action space, thereby achieving successful crossmodal denoising. Extensive experiments against state-of-the-art methods on publicly available RGB, infrared, and terahertz datasets demonstrate the superiority of our method in crossmodal image denoising.

Image denoising is a challenging task that is essential in numerous computer vision and image processing problems. This study proposes and applies a generative adversarial network-based image denoising training architecture to multiple-level Gaussian image denoising tasks. Convolutional neural network-based denoising approaches come across a blurriness issue that produces denoised images blurry on texture details. To resolve the blurriness issue, we first performed a theoretical study of the cause of the problem. Subsequently, we proposed an adversarial Gaussian denoiser network, which uses the generative adversarial network-based adversarial learning process for image denoising tasks. This framework resolves the blurriness problem by encouraging the denoiser network to find the distribution of sharp noise-free images instead of blurry images. Experimental results demonstrate that the proposed framework can effectively resolve the blurriness problem and achieve significant denoising efficiency than the state-of-the-art denoising methods.

The lung diagnosis is one of the essential needs of the medical world. Lung CT images are often affected by salt and pepper noise (or impulse noise) that results the diagnosis output as an imperfect one. The occurrence of impulse noise reduces the accuracy of lung diagnosis which leads the pulmonologists to prescribe wrong treatments or surgery. Image denoising techniques reduce the impulse noise to enhance the quality of medical images. The existing denoising methods are suffered by less denoising-quality, incapable for huge level noise and high time consumption. Hence, there is a need of a new denoising method for the removal of impulse noise in lung CT images. This paper proposes a novel denoising method for impulse noises of lung CT images namely 'Noise reduction using Soft Threshold-based Fuzzy Trimmed Switching Median filter (STFTSM)'. The STFTSM filter removes the noise based on the four concepts, viz. soft threshold computation, fuzzy logic, trimming process and switching median technique. The main contributions of this paper are: (a) soft computation-based max-window-size determination and (b) fuzzy membership determination using switching median-based fuzzy absolute luminance difference computation, soft thresholding approach and fused parallelogram shaped windows. The performance analysis proves that this filter is robust one against the heavy noise environment of lung CT images, and it has less time consumption and significant improvement in peak signal-to-noise ratio by achieving 26.16 db for 90% noise environment.

Terahertz imaging technology has great potential applications in areas, such as remote sensing, navigation, security checks, and so on. However, terahertz images usually have the problems of heavy noises and low resolution. Previous terahertz image denoising methods are mainly based on traditional image processing methods, which have limited denoising effects on the terahertz noise. Existing deep learning‐based image denoising methods are mostly used in natural images and easily cause a large amount of detail loss when denoising terahertz images. Here, a residual‐learning‐based multiscale hybrid‐convolution residual network (MHRNet) is proposed for terahertz image denoising, which can remove noises while preserving detail features in terahertz images. Specifically, a multiscale hybrid‐convolution residual block (MHRB) is designed to extract rich detail features and local prediction residual noise from terahertz images. Specifically, MHRB is a residual structure composed of a multiscale dilated convolution block, a bottleneck layer, and a multiscale convolution block. MHRNet uses the MHRB and global residual learning to achieve terahertz image denoising. Ablation studies are performed to validate the effectiveness of MHRB. A series of experiments are conducted on the public terahertz image datasets. The experimental results demonstrate that MHRNet has an excellent denoising effect on synthetic and real noisy terahertz images. Compared with existing methods, MHRNet achieves comprehensive competitive results.

Deep learning has proven to be an effective mechanism for computer vision tasks, especially for image denoising and burst image denoising. In this paper, we focus on solving the burst image denoising problem and aim to generate a single clean image from a burst of noisy images. We propose to combine the power of block matching and 3D filtering (BM3D) and a convolutional neural network (CNN) for burst image denoising. In particular, we design a CNN with a divide-and-conquer strategy. First, we employ BM3D to preprocess the noisy burst images. Then, the preprocessed images and noisy images are fed separately into two parallel CNN branches. The two branches produce somewhat different results. Finally, we use a light CNN block to combine the two outputs. In addition, we improve the performance by optimizing the two branches using two different constraints: a signal constraint and a noise constraint. One maps a clean signal, and the other maps the noise distribution. In addition, we adopt block matching in the network to avoid frame misalignment. Experimental results on synthetic and real noisy images show that our algorithm is competitive with other algorithms.

Variational mode decomposition (VMD) is a new adaptive multi-resolution technique suitable for signal denoising purpose. The main focus of this work has been to study the feasibility of several image denoising techniques in empirical mode decomposition (EMD) and VMD domains. A comparative study is made using 11 techniques widely used in the literature, including Wiener filter, first-order local statistics, fourth partial differential equation, nonlinear complex diffusion process, linear complex diffusion process (LCDP), probabilistic non-local means, non-local Euclidean medians, non-local means, non-local patch regression, discrete wavelet transform and wavelet packet transform. On the basis of comparison of 396 denoising based on peak signal-to-noise ratio, it is found that the best performances are obtained in VMD domain when appropriate denoising techniques are applied. Particularly, it is found that LCDP in combination with VMD performs the best and that VMD is faster than EMD.

In this study, an improved method based on evolutionary algorithms for denoising of satellite images is proposed. In this approach, the stochastic global optimisation techniques such as Cuckoo Search (CS) algorithm, artificial bee colony (ABC), and particle swarm optimisation (PSO) technique and their different variants are exploited for learning the parameters of adaptive thresholding function required for optimum performance. It was found that the CS algorithm and ABC algorithm-based denoising approach give better performance in terms of edge preservation index or edge keeping index (EPI or EKI) peak signal-to-noise ratio (PSNR) and signal-to-noise ratio (SNR) as compared to PSO-based denoising approach. The proposed technique has been tested on satellite images. The quantitative (EPI, PSNR and SNR) and visual (denoised images) results show superiority of the proposed technique over conventional and state-of-the-art image denoising techniques.

Deep convolutional networks have become a popular tool for image generation and restoration. Generally, their excellent performance is imputed to their ability to learn realistic image priors from a large number of example images. In this paper, we show that, on the contrary, the structure of a generator network is sufficient to capture a great deal of low-level image statistics prior to any learning. In order to do so, we show that a randomly-initialized neural network can be used as a handcrafted prior with excellent results in standard inverse problems such as denoising, super-resolution, and inpainting. Furthermore, the same prior can be used to invert deep neural representations to diagnose them, and to restore images based on flash-no flash input pairs. Apart from its diverse applications, our approach highlights the inductive bias captured by standard generator network architectures. It also bridges the gap between two very popular families of image restoration methods: learning-based methods using deep convolutional networks and learning-free methods based on handcrafted image priors such as self-similarity (Code and supplementary material are available at https://dmitryulyanov.github.io/deep_image_prior).

Self-similarity refers to the image prior widely used in image restoration algorithms that small but similar patterns tend to occur at different locations and scales. However, recent advanced deep convolutional neural network-based methods for image restoration do not take full advantage of self-similarities by relying on self-attention neural modules that only process information at the same scale. To solve this problem, we present a novel Pyramid Attention module for image restoration, which captures long-range feature correspondences from a multi-scale feature pyramid. Inspired by the fact that corruptions, such as noise or compression artifacts, drop drastically at coarser image scales, our attention module is designed to be able to borrow clean signals from their “clean” correspondences at the coarser levels. The proposed pyramid attention module is a generic building block that can be flexibly integrated into various neural architectures. Its effectiveness is validated through extensive experiments on multiple image restoration tasks: image denoising, demosaicing, compression artifact reduction, and super resolution. Without any bells and whistles, our PANet (pyramid attention module with simple network backbones) can produce state-of-the-art results with superior accuracy and visual quality. Our code is available at https://github.com/SHI-Labs/Pyramid-Attention-Networks

The Vision Transformer (ViT) architecture has been remarkably successful in image restoration. For a while, Convolutional Neural Networks (CNN) predominated in most computer vision tasks. Now, both CNN and ViT are efficient approaches that demonstrate powerful capabilities to restore a better version of an image given in a low-quality format. In this study, the efficiency of ViT in image restoration is studied extensively. The ViT architectures are classified for every task of image restoration. Seven image restoration tasks are considered: Image Super-Resolution, Image Denoising, General Image Enhancement, JPEG Compression Artifact Reduction, Image Deblurring, Removing Adverse Weather Conditions, and Image Dehazing. The outcomes, the advantages, the limitations, and the possible areas for future research are detailed. Overall, it is noted that incorporating ViT in the new architectures for image restoration is becoming a rule. This is due to some advantages compared to CNN, such as better efficiency, especially when more data are fed to the network, robustness in feature extraction, and a better feature learning approach that sees better the variances and characteristics of the input. Nevertheless, some drawbacks exist, such as the need for more data to show the benefits of ViT over CNN, the increased computational cost due to the complexity of the self-attention block, a more challenging training process, and the lack of interpretability. These drawbacks represent the future research direction that should be targeted to increase the efficiency of ViT in the image restoration domain.