Search

Underwater Image Enhancement (UIE) addresses challenges in marine resource exploitation such as absorption, noise, and low contrast. This paper employs bibliometric methods and data from Web of Science to analyze UIE literature. The analysis reveals that research on UIE entered a rapid development stage starting from 2017. Three main areas of technical support for research: underwater image enhancement methods, deep learning-based methods, and underwater image restoration and depth estimation. Hotspots in research include enhancement, deep learning, restoration, feature extraction, and quality assessment. Drawing from the bibliometric analysis, this paper proposes a conceptual framework for UIE research and presents five research suggestions: enhancing method robustness and adaptability, improving real-time performance, integrating software and hardware, establishing underwater image benchmark datasets, and refining quality evaluation systems for underwater images. This study offers valuable references and guidance for the future exploration and development of the UIE field. • Bibliometric analysis of underwater image enhancement (UIE) literature using Web of Science data. • Three main technical areas: enhancement methods, deep learning, restoration/depth estimation. • Research hotspots: enhancement, deep learning, restoration, feature extraction, quality assessment. • Proposes conceptual framework and five suggestions for future UIE research direction. • Recommendations include enhancing robustness, real-time performance, software–hardware integration, benchmark datasets, refined quality evaluation. [ABSTRACT FROM AUTHOR]

Domain adaptation has achieved great success in using labeled source domain samples to identify unlabeled target domain samples. Here, we aim to solve the open-set domain adaptation, which is different from the closed-set domain adaptation in that it contains categories in target domain that do not appear in source domain. To solve this problem, this paper proposes open-set domain adaptation model based on subdomain alignment, which uses variable weights for discriminative training of unknown samples in target domain. Aiming at the distribution differences between domains, the model aligns the distributions of the category subspaces of source and target domains, enhancing the distribution similarity within the subspaces of the same category. Through experiments on different domain adaptation datasets, the results show that the model proposed in this paper effectively improves the accuracy of open-set domain adaptation classification. [ABSTRACT FROM AUTHOR]

• Proposing a shift-insensitive perceptual feature based on GM and LoG signals, and theoretically selecting a ratio parameter to balance them. • Building FR-IQA models based on the proposed QGL feature maps that achieve good performance on three benchmark databases. • Achieving the best shift-insensitive performance on images with spatial changes compared with other metrics. • Combining QGL with deep neural networks and validating that QGL can help improving the accuracy in texture classification. Most existing full-reference (FR) Image quality assessment (IQA) models work in the premise of that the two images should be well registered. Shifting an image would lead to an inaccurate evaluation of image quality, because small spatial shifts are far less noticeable than structural distortion for human observers. To this regard, we propose to study an IQA feature that is shift-insensitive to the basic primitive structure of images, i.e., image edge. According to previous studies, the image gradient magnitude (GM) and the Laplacian of Gaussian (LoG) operator that depict the edge profiles of natural images are highly efficient structural features in IQA tasks. In this paper, we find that the Quadratic sum of the normalized GM and the LoG signals (QGL) has excellent shift-insensitive property in representing image edges after theoretically solving the selection problem of a ratio parameter to balance the GM and LoG signals. Based on the proposed QGL feature, two FR-IQA models can be built directly by measuring the similarity map with mean and standard deviation pooling strategies, named mQGL and sQGL, respectively. Experimental results show that the proposed sQGL and mQGL work robustly on four benchmark IQA databases, and QGL-based models show great shift-insensitive property to spatial translation and image rotation while judging the image quality. In addition, we explore the feasibility of combining QGL feature with deep neural networks, and verify that it can help to promote image pattern recognition in texture classification tasks. [ABSTRACT FROM AUTHOR]

Images taken in low-light conditions frequently encounter visibility problems, such as severe noise, reduced brightness, and low contrast. This paper introduces an approach to enhance low-light images using the Metropolis Theorem (MT). The method begins by applying a global gamma correction to the input image, followed by transforming the globally corrected image into the HSV (Hue, Saturation, Value - V) domain. To achieve multi-scale decomposition, an application of the MT is proposed, resulting in approximation and detail sub-images of the V component. Subsequently, local gamma correction is employed on both the final approximation and detail images to enhance local contrast. The refined approximation and detail images are then combined to reconstruct the refined V component. The reconstructed image is obtained by weighting each band of the image with the refined V component. Experimental results demonstrate that the proposed method outperforms state-of-the-art methods, providing improved visual quality and more natural colors. [ABSTRACT FROM AUTHOR]

• A unified adversarial attack framework is designed to reveal the security of the state-of-the-art image tampering localization algorithms. • Two effective attack methods are proposed by relying on the optimization-based and gradient-based adversarial example strategies. • Extensive experimental evaluations verify that the proposed attacks can sharply reduce the tampering localization accuracy while preserving high visual quality for the attacked images. It is significant to evaluate the security of existing digital image tampering localization algorithms in real-world applications. In this paper, we propose an adversarial attack scheme to reveal the reliability of such deep learning-based tampering localizers, which would be fooled and fail to predict altered regions correctly. Specifically, two practical adversarial example methods are presented in a unified attack framework. In the optimization-based adversarial attack, the victim image forgery is treated as the parameter to be optimized via Adam optimizer. In the gradient-based adversarial attack, the invisible perturbation yielded by Fast Gradient Sign Method (FGSM) is added to the tampered image along gradient ascent direction. The black-box attack is achieved by relying on the transferability of such adversarial examples to different localizers. Extensive experiments verify that our attacks can sharply reduce the tampering localization accuracy while preserving high visual quality for attacked images. Source code is available at https://github.com/multimediaFor/AttackITL. [ABSTRACT FROM AUTHOR]

Despite the widespread availability of HDR (High Dynamic Range) display devices, the majority of video sources are still stored in SDR (Standard Dynamic Range) format, leading to an urgent need for UHD (Ultra High Definition) video reconstruction. A simple solution is to divide the task into two sub-tasks: video super-resolution (SR) and video Bit-Depth Enhancement (BDE). While some joint enhancement tasks led by SR have been explored in multiple dimensions, the quantitative dimension has often been overlooked. In this paper, we address the first joint task of BDE and SR and propose a succinct network called MSTG. We conduct a systematic analysis to explain how this effect can be achieved and overcome the core challenge arising from distortions exacerbated by the differing optimization directions of BDE and SR. This challenge is attributed to indistinguishable contours and detailed textures. To tackle this, we employ a dual-branch module that leverages both gradient and image information to discern between BDE and SR. Furthermore, we propose a novel model named Cross-scale Transformer (CTF) embedded with Cross-scale Attention (CSA). This model facilitates information aggregation while adaptively utilizing structural similarity features. It jointly extracts, aligns, and fuses frame features at multiple scales, forming the MST module. Experiments demonstrate that the proposed algorithm outperforms the cascaded video enhancement methods by large margins on both synthetic and realistic datasets. [ABSTRACT FROM AUTHOR]

The single image dehazing (SID) is challenging because of ill-posed characteristic, since there exist multiple possible dehazed images for a single hazy image due to multiple possible values of transmission. The SID is solved using scattering model, which requires computation of two parameters (transmission and atmospheric light) for its solution. The existing methods have presented priors and techniques to estimate transmission with limited focus on structure of the transmission. This paper proposes a lower bound on transmission using structural measure. The proposed lower bound is utilized to estimate the value of transmission, while preserving structural. Further, a quality control parameter is introduced to ensure non-negative value of the transmission for images with brighter objects than atmospheric light. The accuracy and efficiency of the proposed method is established by comparing with renowned SID methods using benchmark datasets. [ABSTRACT FROM AUTHOR]

Low-light conditions present a myriad of intricacies for object detection, with many existing methods relying primarily on image enhancement before detection. Sometimes, the enhancement methods are unable to improve the detection performance in low-light conditions. In this paper, we present a new Multi-exposure refinement network for low-light object detection (MRN-LOD) to avoid the need for enhancement before detection. The MRN-LOD contains: multi-exposure feature extractor, adaptive refinement network, and detection head. The developed multi-exposure feature extractor extracts features from the multi-exposure images generated by the low-light image. We introduced the notion of feature extraction from multi-exposure images for object detection in low light. In addition, we proposed an adaptive refinement network to refine the features of low-light images for better detection performance. The detection head uses the refined features to perform object detection. Extensive experimentation on real-world and synthetic datasets shows the superiority of the proposed MRN-LOD. [ABSTRACT FROM AUTHOR]

Light field imaging can capture rich information of real scenes, but various distortions will inevitably be introduced in the process of light field image processing. Therefore, it is very important to effectively evaluate the quality of light field images. Due to the lack of commercial light field displays, this paper proposes a blind quality assessment method of light field image based on view and focus stack, based on the visualization technology used in the subjective evaluation of light field images and the human brain's perception process of visual information in the study of visual physiology. First, spatiotemporal Gabor filtering is performed on distorted sub-aperture images (SAIs) to extract the spatial and angular information. On the other hand, the SAIs are refocused to obtain the refocused images with different focusing depths, and then the focus stack is filtered by spatiotemporal Gabor filtering to extract the angular information. In addition, the focus stack is detected to form in-focus area and out-of-focus area, and the features related to spatial structure, depth and semantic information of the refocused images are extracted to evaluate the spatial quality. Finally, support vector regression (SVR) is performed to predict the objective scores by establishing the relationship between the features and subjective scores. Experimental results show that our method can well predict the human eye's perception quality of light field images. [ABSTRACT FROM AUTHOR]

Graphical Abstract of the proposed network, Module 1 shows the Global-local network, Module 2 shows RGB histogram equalizer, and Module 3 shows the attention module. (b) The structure of B_Block, and (c) The structure of C_block in the proposed network. [Display omitted] • An end-to-end synergetic integration of classic image processing and CNNs. • Using an attention module to emphasize meaningful parts of underwater images. • Proper employing histogram equalization to avoid producing color artifacts. • Introducing a lightweight model, suitable for different types of underwater images. This paper presents a deep learning-based underwater image enhancement method supported by a classical image processing technique. The proposed method includes an end-to-end three-module structure. The first module is a lightweight two-branch network that retrieves lost colors and to some extent overall appearance through the global and local image enhancement. The second module is the modified histogram equalization to improve the global intensity, contrast and local colors of the image by controlling over-intensity and artificial colors that may result from histogram equalization. The last part is the attention module, utilized to help the proposed framework have a synergistic combination of the previous modules. The attention module is designed to combine the advantages of the previous modules and evade their drawbacks. Experiments to objectively and subjectively evaluate the performance of the proposed model show that the proposed model is superior to existing underwater image enhancement methods. [ABSTRACT FROM AUTHOR]

The existing deraining methods have obtained noteworthy improvements, but it is a challenging problem to extend the methods for complicated rain conditions where rain streaks exhibit different distribution densities, sizes, shapes , etc. The main challenges are the ability to fully explore and utilize the multi-scale context information of rain streaks that maintain both global structure completeness and local detail accurateness. To this end, this paper proposes an E xploring C ontext- G ated N etwork, known as ECG Net. To adequately explore the richer context information, the proposed method consists of two key elements: context-enhanced feature block (CEFB) and multi-scale-gated aggregation block (MGAB). Specifically, the various scale features can be captured by CEFB with the multi-scale operation, to better remove the rain streaks and effectively restore the local detail textures. Subsequently, the captured features from different spaces are sent to MGAB, to aggregate and transmit these different scale features from the encoder to the decoder and reduce the transmission loss of information. Massive experiments on the commonly used benchmarks have demonstrated that the proposed method obtains more appealing performances against other competitive methods. • Capturing multi-scale features and enhancing contextual information, obtaining local modeling and long-range dependency. • Gated aggregation information from different levels, reducing redundant features and loss of informational transmission. • Better rain streaks removal and recovering image details and textures. [ABSTRACT FROM AUTHOR]

Domain Generalization (DG) model is an important tool to improve the robustness of person re-identification algorithm, but the domain gap makes it difficult to transfer knowledge cross-domain effectively. To solve the above problems, this paper proposes a generalization model based on a Meta-Bond Domain Alignment (M−BDA) model. To learn a generalizable model, a meta -learning strategy is introduced to simulate the training–testing process of the domain generalization. Then a bond-domain module is constructed in the training to align the source domain, which can reduce the domain gap between the source domain and the target domain, and facilitate the knowledge transfer. Finally, the bond-domain loss is counted on the feature space of the bond-domain to prevent the generated bond-domain from overfitting to the source domain. The experimental results show that the proposed algorithm achieves better performance in DukeMTMC-ReID, Market1501 and MSMT17 alternating as the source and the target domain tasks. In the generalization experiments of Market-1501 → DukeMTMC-ReID, mAP and Rank-1 increased by 7.7 % and 3.6 %, respectively, and in the generalization experiments of DukeMTMC-ReID → Market-1501, mAP and Rank-1 are increased by 9.3 % and 3.5 %, respectively, which are significantly better than the newer representative algorithms. [ABSTRACT FROM AUTHOR]

Domain generalizable person re-identification (DG ReID) aims to obtain a model that can be applied directly to unseen domains once trained on a set of source domains (datasets collected from different camera networks). Among current DG ReID methods, instance normalization is a promising solution to reduce the effect of domain bias, but it inevitably filters out some discriminative information. Besides, since most pioneering approaches cannot effectively address the loss of discriminative information, this paper proposes a Style Elimination and Information Restitution (SEIR) module and constructs a generalizable framework. Specifically, we utilize instance normalization to reinforce the generalization capability on unseen domains. Then, the instance-specific mean and variance are employed to construct a feature vector that includes discriminative and style information. Besides, an encoder–decoder structure is designed to restitute the discriminative information to ensure a high recognition rate. Finally, a dual optimization strategy is devised to update the proposed module by simulating a real train-test process to enhance the generalization robustness further and prevent SEIR from overfitting to the source domain. Extensive experimental results demonstrate that the proposed method outperforms the state-of-the-art methods by a large margin on the public DG ReID benchmarks. • A Style Elimination and Information Restitution module for handling domain bias. • An optimization strategy for improving the generalization ability. • We propose a framework for generalizable person re-identification. • Significant results were achieved for addressing the generalizable person re-identification. [ABSTRACT FROM AUTHOR]

In the last decade, the exploration of deep-sea ecosystems has surged, offering exciting prospects for discovering untapped resources such as medical drugs, food and energy sources, and renewable energy products. Consequently, research in underwater image processing has witnessed substantial growth. However, underwater imaging poses significant challenges, particularly without sophisticated, specialized cameras. Traditional cameras are impacted by absorption and scattering in the aquatic environment, producing hazy images with a blue–green tint. This phenomenon holds implications for marine research and other disciplines that rely on underwater imaging. While hardware advancements have been made over the years, image processing remains a valuable, cost-effective, and practical approach for underwater enhancement. Despite the existence of state-of-the-art techniques for underwater enhancement and restoration, their performance is often inconsistent. While some methods excel in contrast restoration, color restoration remains a pervasive challenge. In this paper, we introduce Sea-Pix-GAN, a Generative Adversarial Network (GAN)-based model that addresses these issues in underwater image enhancement. We redefine the problem as an image-to-image translation task and tailor the objective and loss functions to achieve color, content, and style transfer. The model is trained on a large dataset of underwater scenes, encompassing the diverse color dynamics of underwater subjects. Sea-Pix-GAN demonstrates promising results in restoring color, contrast, texture, and saturation. To validate its effectiveness, we compare the performance of Sea-Pix-GAN quantitatively based on metrics like PSNR, SSIM, and UIQM and qualitatively against several existing techniques. [ABSTRACT FROM AUTHOR]

Transformer has achieved impressive successes for various computer vision tasks. However, most of existing studies require to pretrain the Transformer backbone on a large-scale labeled dataset (e.g., ImageNet) for achieving satisfactory performance, which is usually unavailable for medical images. Additionally, due to the gap between medical and natural images, the improvement generated by the ImageNet pretrained weights significantly degrades while transferring the weights to medical image processing tasks. In this paper, we propose Bootstrap Own Latent of Transformer (BOLT), a self-supervised learning (SSL) approach specifically for medical image classification with the Transformer backbone. Our BOLT consists of two networks, namely online and target branches, for self-supervised representation learning. Concretely, the online network is trained to predict the target network representation of the same patch embedding tokens with a different perturbation. To maximally excavate the impact of Transformer from limited medical data, we propose an auxiliary difficulty ranking task. The Transformer is enforced to identify which branch (i.e., online/target) is processing the more difficult perturbed tokens. Overall, the Transformer endeavours itself to distill the transformation-invariant features from the perturbed tokens to simultaneously achieve difficulty measurement and maintain the consistency of self-supervised representations. The proposed BOLT is evaluated on three medical image processing tasks, i.e., skin lesion classification, knee fatigue fracture grading and diabetic retinopathy grading. The experimental results validate the superiority of our BOLT for medical image classification, compared to ImageNet pretrained weights and state-of-the-art SSL approaches. [ABSTRACT FROM AUTHOR]

• A two-branch end-to-end dehazing network is proposed, which can solve the imbalances weight distribution problem between the detail and structural features. • Coordinate channel attention module is employed to extract the structural features and the dense pixel attention modules is employed to extract the detail features. • Extensive experiments are conducted on both synthetic and real-world dataset and performed well. Image dehazing is an ill-posed problem that has been extensively studied in recent years. Unfortunately, most existing deep dehazing models have high computational complexity and lack the dynamic adjustment of details, which hinders their application to high-resolution images in computational vision tasks. In this paper, we propose an efficient dual-path adaptive fusion dehazing network (DPAFD-Net) to directly restore a clear image from a hazy input. Moreover, we propose a pure subnetwork with encoder and decoder structures to further extract the structural information and progressively restore the haze-free image. To evaluate the effectiveness of the proposed method, we validate our approach on synthetic and real hazy images, where our method performs favourably against the state-of-the-art dehazing approaches. [ABSTRACT FROM AUTHOR]

In social networks, people usually communicate online by posting and passing images, people will find that there are many similar or even visually identical images. When the images determine whether the published information is true or false, original images became crucial, and at the same time, deep learning excelled in image identification. Combining the original image identification and deep learning methods, this paper proposes the original image identification method based on the deep network models, aiming to use the deep network models to identify the original images between the original images and a bunch of variant images of the original images, and obtain satisfactory results. In this way, through the trained network models, the original images can be identified and can help the viewers to determine the correctness of the information. Experimental results verify the feasibility, effectiveness and security of the proposed method. • The method can prevent the images from being stolen during transmission. • The method can achieve good identification results on the image databases. • The method is feasible and flexible in actual operation. [ABSTRACT FROM AUTHOR]

• An image fusion method is proposed that can effectively highlight infrared target features and retain visible visual information. • Infrared targets are analyzed based on the saliency weight map. • The target contour and background texture are refined by a method based on weight refinement of guided filtering. • A multi-layer fusion strategy is used to fuse saliency weight maps at multiple scales. Image fusion is the fusion of multiple images from the same scene to produce a more informative image, and infrared and visible image fusion is an important branch of image fusion. To tackle the issues of diminished luminosity in the infrared target, inconspicuous target features, and blurred texture of the fused image after the fusion of infrared and visible images. This paper introduces a novel effective fusion framework that merges multi-scale Convolutional Neural Networks (CNN) with saliency weight maps. First, the method measures the source image features to estimate the initial saliency weight map. Then, the initial weight map is segmented and optimized using a guided filter before being further processed by CNN. Next, a trained Siamese convolutional network is used to solve the two key problems of activity measure and weight assignment. Meanwhile, a multi-layer fusion strategy is designed to effectively retain the luminance of the infrared target and the texture information in the visible background. Finally, adaptive adjustment of the fusion coefficients is achieved by employing saliency. The experimental results show that the method outperforms the state-of-the-art algorithms in terms of both subjective visual quality and objective evaluation effects. [ABSTRACT FROM AUTHOR]

• A small target detection algorithm based on feature interaction and guided learning. • A feature guided alignment module is designed to obtain more effective features. • Gaussian distribution sample allocation strategy is introduced to obtain better samples. • Feature interaction and decoupling detection enhance the detection task capability. • A new regression loss function is used to optimize the localization ability to a certain extent. At present, for the diverse target sizes, different angles, and complex environment in aerial images, how to detect small objects effectively in aerial images is still a challenge task. In order to further improve the detection accuracy and reduce the missing rate, in this paper, we proposes a small target detection algorithm based on feature interaction and guided learning. Firstly, the feature guided alignment module is designed to deal with the problem of information loss and overlap. Secondly, the misallocation of small object samples is optimized by introducing gaussian sample allocation strategy. Then the interactive parallel detection header is designed to solve the detection task conflict problem. Finally, the new regression loss function is designed to enhance the localization ability of the target. The experimental results on the Tinyperson dataset and Visdrone dataset show that this model can improve the detection accuracy and reduce the missing rate of small targets effectively. [ABSTRACT FROM AUTHOR]