Explore the vast range of titles available.

Joint image filters are used to transfer structural details from a guidance picture used as a prior to a target image, in tasks such as enhancing spatial resolution and suppressing noise. Previous methods based on convolutional neural networks (CNNs) combine nonlinear activations of spatially-invariant kernels to estimate structural details and regress the filtering result. In this paper, we instead learn explicitly sparse and spatially-variant kernels. We propose a CNN architecture and its efficient implementation, called the deformable kernel network (DKN), that outputs sets of neighbors and the corresponding weights adaptively for each pixel. The filtering result is then computed as a weighted average. We also propose a fast version of DKN that runs about seventeen times faster for an image of size 640×480. We demonstrate the effectiveness and flexibility of our models on the tasks of depth map upsampling, saliency map upsampling, cross-modality image restoration, texture removal, and semantic segmentation. In particular, we show that the weighted averaging process with sparsely sampled 3×3 kernels outperforms the state of the art by a significant margin in all cases.

Underwater image restoration is of significant importance in unveiling the underwater world. Numerous techniques and algorithms have been developed in recent decades. However, due to fundamental difficulties associated with imaging/sensing, lighting, and refractive geometric distortions in capturing clear underwater images, no comprehensive evaluations have been conducted with regard to underwater image restoration. To address this gap, we constructed a large-scale real underwater image dataset, dubbed Heron Island Coral Reef Dataset (‘HICRD’), for the purpose of benchmarking existing methods and supporting the development of new deep-learning based methods. We employed an accurate water parameter (diffuse attenuation coefficient) to generate the reference images. There are 2000 reference restored images and 6003 original underwater images in the unpaired training set. Furthermore, we present a novel method for underwater image restoration based on an unsupervised image-to-image translation framework. Our proposed method leveraged contrastive learning and generative adversarial networks to maximize the mutual information between raw and restored images. Extensive experiments with comparisons to recent approaches further demonstrate the superiority of our proposed method. Our code and dataset are both publicly available.

In image processing, sparse coding has been known to be relevant to both variational and Bayesian approaches. The regularization parameter in variational image restoration is intrinsically connected with the shape parameter of sparse coefficients’ distribution in Bayesian methods. How to set those parameters in a principled yet spatially adaptive fashion turns out to be a challenging problem especially for the class of nonlocal image models. In this work, we propose a structured sparse coding framework to address this issue—more specifically, a nonlocal extension of Gaussian scale mixture (GSM) model is developed using simultaneous sparse coding (SSC) and its applications into image restoration are explored. It is shown that the variances of sparse coefficients (the field of scalar multipliers of Gaussians)—if treated as a latent variable—can be jointly estimated along with the unknown sparse coefficients via the method of alternating optimization. When applied to image restoration, our experimental results have shown that the proposed SSC–GSM technique can both preserve the sharpness of edges and suppress undesirable artifacts. Thanks to its capability of achieving a better spatial adaptation, SSC–GSM based image restoration often delivers reconstructed images with higher subjective/objective qualities than other competing approaches.

In recent years, underwater exploration for deep-sea resource utilization and development has a considerable interest. In an underwater environment, the obtained images and videos undergo several quality degradations resulting from light absorption and scattering, low contrast, color deviation, blurred details, and nonuniform illumination. Therefore, the restoration and enhancement of degraded images and videos are critical. Numerous techniques of image processing, pattern recognition, and computer vision have been proposed for image restoration and enhancement, but many challenges remain. This survey has been estimated to be superior to other reviews because it collects all their shortcomings and lacks and gives researchers many ideas for the future. This survey presents a comparison of the most prominent approaches in underwater image processing and analysis. It also discusses an overview of the underwater environment with a broad classification into enhancement and restoration techniques and introduces the main underwater image degradation reasons in addition to the underwater image model. The existing underwater image analysis techniques, methods, datasets, and evaluation metrics are presented in detail. Furthermore, the existing limitations are analyzed, which are classified into image-related and environment-related categories. In addition, the performance is validated on images from the UIEB dataset for qualitative, quantitative, and computational time assessment. Areas in which underwater images have recently been applied are briefly discussed. Finally, recommendations for future research are provided and the conclusion is presented.

Owing to the flexible architectures of deep convolutional neural networks (CNNs) are successfully used for image denoising. However, they suffer from the following drawbacks: (i) deep network architecture is very difficult to train. (ii) Deeper networks face the challenge of performance saturation. In this study, the authors propose a novel method called enhanced convolutional neural denoising network (ECNDNet). Specifically, they use residual learning and batch normalisation techniques to address the problem of training difficulties and accelerate the convergence of the network. In addition, dilated convolutions are used in the proposed network to enlarge the context information and reduce the computational cost. Extensive experiments demonstrate that the ECNDNet outperforms the state-of-the-art methods for image denoising.

Because of the unique physical and chemical properties of water, obtaining high-quality underwater images directly is not an easy thing. Hence, recovery and enhancement are indispensable steps in underwater image processing and have therefore become research hotspots. Nevertheless, existing image-processing methods generally have high complexity and are difficult to deploy on underwater platforms with limited computing resources. To tackle this issue, this paper proposes a simple and effective baseline named UIR-Net that can recover and enhance underwater images simultaneously. This network uses a channel residual prior to extract the channel of the image to be recovered as a prior, combined with a gradient strategy to reduce parameters and training time to make the operation more lightweight. This method can improve the color performance while maintaining the style and spatial texture of the contents. Through experiments on three datasets (MSRB, MSIRB and UIEBD-Snow), we confirm that UIR-Net can recover clear underwater images from original images with large particle impurities and ocean light spots. Compared to other state-of-the-art methods, UIR-Net can recover underwater images at a similar or higher quality with a significantly lower number of parameters, which is valuable in real-world applications.

Underwater image processing has received tremendous attention in the past few years. The reason for increased research in this area is that the process of taking images underwater is very difficult. Images obtained underwater frequently suffer from quality deterioration issues such as poor contrast, blurring features, colour variations, non-uniform lighting, the presence of dust particles, noise at the bottom of the sea, different properties of the water medium, and so on. The improvement of underwater images is a critical problem in image processing and computer vision for a variety of practical applications. To address this problem, we need to find some other methods to increase the quality of the image while capturing it underwater. But capturing the image in normal circumstances as well as underwater is the same, so once we get an image, some mechanism to increase the quality of the captured image will also be required. A complete and in-depth study of relevant accomplishments and developments, particularly the survey of underwater image methods and datasets, which are a critical issue in underwater image processing and intelligent application, is still lacking. In this paper, we first provide a review of more than 85 articles on the most recent advancements in underwater image restoration methods, underwater image enhancement methods, and underwater image enhancement using deep learning and machine learning methods, along with the techniques, data sets, and evaluation criteria. To provide a thorough grasp of underwater image restoration, enhancement, and enhancement using deep learning and machine learning, we explore the strengths and limits of existing techniques. Additionally, we offer thorough, unbiased reviews and evaluations of the representative methodologies for five distinct types of underwater situations, which vary their usefulness in various underwater circumstances. Two main evaluations, subjective image quality evaluation and objective image quality evaluation; are used for evaluating the quality of images. These evaluations are useful to determine the efficiency of the predefined methods. With the help of these image quality evaluations, we come to the conclusion that the image enhancement methods and image enhancement methods using deep learning and machine learning are superior in comparison to the image restoration methods. As deep learning and machine learning based enhancement methods are newer and give far better results in comparison to the other two methods, lots of researchers are moving towards these methods. Finally, we also explore the potential difficulties and unresolved problems associated with underwater image enhancement and offer potential future research areas.

Numerous image restoration algorithms have been proposed in the last several decades. These algorithms usually optimize an objective function consisting of an ℓ2 norm based fidelity and a regularization term, whose optimality could be justified from the view of maximum a posteriori estimation with an assumption that the noise is Gaussian. However, it is known that the ℓ2 norm based fidelity is very sensitive to gross errors that may appear in the observation. Since real-world image restoration tasks are usually hindered by abnormal pixels, impulsive noise, and other heavy-tailed noise, the utility of these traditional algorithms is limited. Although some robust algorithms have been proposed by replacing the ℓ2 norm based fidelity with a robust one, they are designed for specific restoration tasks (e.g., multi-frame super-resolution) with a fixed image prior (e.g., the total-variation) and have not provided a principled way to justify the choice of a robust fidelity term. Currently designing a robust algorithm for general image restoration tasks is still an open problem. This paper studies the problem of robust image restoration in both theoretical and algorithmic manners. In the theoretical part, we point out that Huber function based fidelity could be justified from the pespective of minimax estimation, which facilities the choice of the robust fidelity term. In the algorithmic part, we first propose an adaptive approach to set the threshold of the Huber function, and then we derive an efficient and flexible method to solve the proposed robust formulation of the image restoration problem, which enables the proposed algorithm to incorporate various image priors. Experiments have demonstrated the robustness of the proposed algorithm and its utility in real-world image restoration tasks.

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

Restoring multi-weather-degraded images is significant for subsequent high-level computer vision tasks. However, most existing image restoration algorithms only target single-weather-degraded images, and there are few general models for multi-weather-degraded image restoration. In this paper, we propose a diffusion model for multi-weather-degraded image restoration, namely a universal transformer-based diffusion model (UTDM) for multi-weather-degraded images restoration, by combining the denoising diffusion probability model and Vision Transformer (ViT). First, UTDM uses weather-degraded images as conditions to guide the diffusion model to generate clean background images through reverse sampling. Secondly, we propose a Cascaded Fusion Noise Estimation Transformer (CFNET) based on ViT, which utilizes degraded and noisy images for noise estimation. By introducing cascaded contextual fusion attention in a cascaded manner to compute contextual fusion attention mechanisms for different heads, CFNET explores the commonalities and characteristics of multi-weather-degraded images, fully capturing global and local feature information to improve the model’s generalization ability on various weather-degraded images. UTDM outperformed the existing algorithm by 0.14–4.55,dB on the Raindrop-A test set, and improved by 0.99 dB and 1.24 dB compared with Transweather on the Snow100K-L and Test1 test sets. Experimental results show that our method outperforms general and specific restoration task algorithms on synthetic and real-world degraded image datasets. Code and dataset are available at: https://github.com/RHEPI/UTDM .