Search

• Combines HRAT and QHWT for improved image quality for contrast enhancement, noise reduction, texture preservation. • Accurately delineates iris boundaries, enhancing precision in segmentation processes. • Efficiently reduces feature space dimensions while preserving relevant information for faster image processing. • Enables high-accuracy iris pattern recognition, crucial for versatile biometric authentication applications. Iris recognition, a precise biometric identification technique, relies on the distinct epigenetic patterns within the iris. Existing methods often face challenges related to segmentation accuracy and classification efficiency. To improve the accuracy and efficiency of iris recognition systems, this research proposes an innovative approach for iris recognition, focusing on efficient segmentation and classification using Convolutional neural networks with Sheaf Attention Networks (CSAN). Main objective is to develop an integrated framework that optimizes iris segmentation and classification. Subsequently, dense extreme inception multipath guided up sampling network is employed for accurate segmentation. Finally, classifiers including convolutional neural network with sheaf attention networks are evaluated. The findings indicate that the proposed method achieves superior iris recognition accuracy and robustness, making it suitable for applications such as secure authentication and access control. By comparing with existing approaches CSAN obtains 99.98%, 99.35%, 99.45% and 99.65% accuracy for the four different proposed datasets respectively. [ABSTRACT FROM AUTHOR]

• This paper reviews state-of-the-art low-light image enhancement techniques (LLIE) and their variants used in recent years. • The effectiveness of each method is compared both subjectively/objectively using author's own image and two data set images. • Section 2 presents a classification of (LLIE) methods and tracing their developments starting from the earliest/simplest form. • Use of AI techniques, CNN and GAN are also discussed with conceptual introduction underscoring the merits and drawbacks. • Section 3 opens a discussion on challenges and future scope of low light image enhancement. Low-light image enhancement is an effective solution for improving image recognition by both humans and machines. Due to low illuminance, images captured in such conditions possess less color information compared to those taken in daylight, resulting in occluded images characterized by distortion, low contrast, low brightness, a narrow gray range, and noise. Low-light image enhancement techniques play a crucial role in enhancing the effectiveness of object detection. This paper reviews state-of-the-art low-light image enhancement techniques and their developments in recent years. Techniques such as gray transformation, histogram equalization, defogging, Retinex, image fusion, and wavelet transformation are examined, focusing on their working principles and assessing their ability to improve image quality. Further discussion addresses the contributions of deep learning and cognitive approaches, including attention mechanisms and adversarial methods, to image enhancement. [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]

A novel approach to image cropping, called crop region comparator (CRC), is proposed in this paper, which learns ordering relationships between aesthetic qualities of different crop regions. CRC employs the single-region refinement (SR) module and the inter-region correlation (IC) module. First, we design the SR module to identify essential information in an original image and consider the composition of each crop candidate. Thus, the SR module helps CRC to adaptively find the best crop region according to the essential information. Second, we develop the IC module, which aggregates the information across two crop candidates to analyze their differences effectively and estimate their ordering relationship reliably. Then, we decide the crop region based on the relative aesthetic scores of all crop candidates, computed by comparing them in a pairwise manner. Extensive experimental results demonstrate that the proposed CRC algorithm outperforms existing image cropping techniques on various datasets. [ABSTRACT FROM AUTHOR]

This manuscript introduces an innovative bilevel optimization approach designed to improve the deblurring process by incorporating a nonlocal p -Laplacien model with variable weights. The study includes a theoretical analysis to examine the model's solution, and an effective algorithm is devised for computing the pristine image, incorporating the learning of parameters associated with weights and nonlocal regularization terms. By carefully selecting these parameters, the suggested nonlocal deblurring model demonstrates superior effectiveness and performance when compared to other existing models. [ABSTRACT FROM AUTHOR]

High-quality images are of prime importance for vision tasks in underwater environment, ocean exploitation and marine eco-environment protection. However, due to attenuation and scattering related to wavelength and distance, underwater images often suffer from severe distortion, like color cast and loss of detail, challenging the capture of high-quality images. Existing methods mostly focus on pixel-wise mapping from input to output images, which disrupts the latent relationships between neighboring pixels and suffers limited flexibility of linear mapping. Additionally, most methods operate solely within RGB color space, which is insensitive to some image properties such as luminance and saturation, may be inconsistent with human visual perception. In this paper, we combine global and local enhancement, formulating underwater image global enhancement as a task of image-specific piecewise curve estimation based on a deep network, introducing three color spaces (RGB, HSV, CIELab). Our network learns piecewise nonlinear curves specific to different channels of multiple color spaces, thereby introducing highly flexible nonlinear mapping and achieving targeted adjustment. Besides, we employ channel-wise attention mechanism to allocate weights for different adjustment results from multiple color spaces, combining their advantages to further enhance image properties such as luminance, saturation, and color, aiming to improve image quality and align it more closely with human visual perception. To assess the performance of the network, extensive experiments are conducted on synthetic and real-world underwater image datasets, with comparisons made against state-of-the-art methods. Both quantitative and qualitative results indicate our network's remarkable performance in both visual quality and quantitative metrics. • Enhancement of underwater images by curve estimation. • Enhance underwater images in multiple color spaces. • Flexible non-linear mapping. [ABSTRACT FROM AUTHOR]

Low-light environments often lead to complex degradation of captured images. However, most deep learning-based image enhancement methods for low-light conditions only learn a single-channel mapping relationship between the input image in low-light conditions and the desired image in normal light without considering semantic priors. This may cause the network to deviate from the original color of the region. In addition, deep network architectures are not suitable for low-light image recovery due to low pixel values. To address these issues, we propose a novel network called SAGNet. It consists of two branches:the main branch extracts global enhancement features at the level of the original image, and the other branch introduces semantic information through region-based feature learning and learns local enhancement features for semantic regions with multi-level perception to maintain color consistency. The extracted features are merged with the global enhancement features for semantic consistency and visualization. We also propose an unsupervised loss function to improve the network's adaptability to general scenes and reduce the effect of sparse datasets. Extensive experiments and ablation studies show that SAGNet maintains color accuracy better in all cases and keeps natural luminance consistency across the semantic range. [ABSTRACT FROM AUTHOR]

Underwater image enhancement, especially in color restoration and detail reconstruction, remains a significant challenge. Current models focus on improving accuracy and learning efficiency through neural network design, often neglecting traditional optimization algorithms' benefits. We propose FAIN-UIE, a novel approach for color and fine-texture recovery in underwater imagery. It leverages insights from the Fast Iterative Shrink-Threshold Algorithm (FISTA) to approximate image degradation, enhancing network fitting speed. FAIN-UIE integrates the residual degradation module (RDM) and momentum calculation module (MC) for gradient descent and momentum simulation, addressing feature fusion losses with the Feature Merge Block (FMB). By integrating multi-scale information and inter-stage pathways, our method effectively maps multi-stage image features, advancing color and fine-texture restoration. Experimental results validate its robust performance, positioning FAIN-UIE as a competitive solution for practical underwater imaging applications. • Utilizing FISTA to accelerate image recovery, improving network fitting speed. • Integrating output image features to address color deviation and detail texture blur. • Using the algorithm unfolding method effectively improves the quality of underwater images. [ABSTRACT FROM AUTHOR]

A segmentation map, either static or dynamic, refers to a two-dimensional picture that may vary with time and indicates the segmentation label per pixel. Both the semantic map and the occupancy map in video-based point cloud compression (V-PCC) belong to the segmentation map we referred to. The semantic map can work for many machine vision tasks like tracking and has been used as a layer of image representation in some image compression methods. The occupancy map constitutes a part of the point cloud coding bitstream. Since segmentation maps are widely used, how to efficiently compress them is of interest. We propose a segmentation map lossless compression scheme namely CC-SMC, exploiting the nature of segmentation maps that usually contain limited colors and sharp edges. Specifically, we design a chain coding-based scheme combined with quadtree-based block partitioning. For intraframe coding, one block is partitioned recursively with a quadtree structure, until the block contains only one color, is smaller than a threshold, or satisfies the defined chain coding condition. We revise the three-orthogonal chain coding method to incorporate contextual information and design effective intraframe prediction methods. For interframe coding, one block may find a reference block; the chain difference between the current and the reference blocks is coded. We implement the proposed scheme and test it on several different kinds of segmentation maps. Compared with advanced lossless image compression techniques, our proposed scheme obtains more than 10% bits reduction as well as more than 20% decoding time-saving. The code is available at https://github.com/Yang-Runyu/CC-SMC. • A chain coding-based scheme for segmentation map compression, named CC-SMC. • Interframe chain coding to exploit the correlation of chain codes between blocks. • CC-SMC saves >10% bitrate and >20% decoding time compared to previous methods. [ABSTRACT FROM AUTHOR]

Image dehazing has now gained the dominant popularity in the field of image processing, particularly in inhomogeneous scene. Recent years have witnessed great progress in handling homogeneous dehazing problems. Due to the unknown haze distribution of the real world, it is extremely intractable to offer a clear view of the observed scene in limited inhomogeneous datasets. Furthermore, it is impossible to completely avoid artifacts of color distortion, over-enhancement, halo, and blur errors in order to provide reliable and stable results. To this end, we propose an end-to-end Dual-branch Residual Network (DBRN) for inhomogeneous dehazing that is composed of Hybrid Feature Subnet (HFS) and Attention Feature Fusion Subnet (AFFS). HFS explores high-quality global and local hazy features with long-range spatial fusion at different scales in an encoder–decoder manner, while AFFS makes artifact removal possible with a stack of Residual Convolution Attention Module (RCAM). Besides, the joint loss function aims to ensure that the recovered image is close to the ground-truth in the aspects of texture, color, structure index, and so on. Through this design, the model exhibits robustness in inhomogeneous hazy scenes, enabling high-quality visual restoration in scenes with varying haze densities. Extensive experimental results demonstrate that the proposed model performs favorably against the state-of-the-art methods on synthetic datasets and real-world hazy images. In addition, ablation studies are carried out to demonstrate the effectiveness of each component. The source code of the proposed method is available at https://github.com/jing-1196/DBRN/. • Our method explores a dual-branch dehazing network consisting of HFS and AFFS. • Our method proposes RCAM to enhance the discriminative capacity. • Our method outperforms other methods on three public datasets. [ABSTRACT FROM AUTHOR]

Since the camouflaged objects share very similar colors and textures with the surroundings, there is still a great challenge in accurately locating and segmenting target objects with the varying sizes and shapes in different scenes. In this paper, we propose a novel Attention Fusion and Interaction network (AFINet) to detect the camouflaged objects by exploring the cross-level complementary information. Specifically, we first propose a Multi-Attention Interaction (MAI) module to fuse the cross-level features containing different characteristics by the attention interaction, thereby fully making use of the specific and complementary information from different levels to deal with scale variation. Furthermore, we design a Location and Boundary Guidance (LBG) module to make each side-output feature aware of where to learn, which can avoid the disturbances of the non-camouflaged regions by distinguishing the subtle differences. Comprehensive experiments and comparisons are conducted on four widely used benchmark datasets, demonstrating that the proposed network achieves state-of-the-art performance. The code and prediction maps will be available at https://github.com/ZhangQing0329/AFINet. • We propose a Attention Fusion and Interaction Network (AFINet) for COD. • We design a MAI module to fully utilize the multi-level attention maps. • We design a LBG module to directly fuse the global context and global details cues. • The proposed method performs competitively against the recent methods. [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]

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]

• Domain Specific Super Resolution technique. • Impact of k-NN distance measure algorithms in face hallucination. • Position patch based Locality- Constraint representation. • Reconstruction of low resolution images into high resolution images. • Importance of high resolution face images in the field of surveillance and security. Face hallucination (FaceH), the domain specific super resolution technique has significant importance in the field of image processing and computer vision. These methods provide visually convincing high-resolution face images using the low-resolution input images. To do this, all the state-of-the-art methods make use of distance measure algorithms. The performance of distance measure is one of the core components that impact the performance of FaceH. However, there are many k-NN distance measure algorithms, to the best of our knowledge, the most commonly used metric is the Euclidean distance, though it is the best, a little deviation may result in large elevation on estimating the reconstructed weight of the pixel. To overcome this, it is necessary to find an alternative method and this motivated to develop Minkowski Locality-constrained Representation (MinLcR) FaceH that makes use of Minkowski distance and after which it is integrated with Locality-constrained Representation (LcR) that incorporates the contextual information of the neighboring pixel for better hallucination. The main idea of MinLcR is to make a difference in the distance metric and compare it with methods that make use of Euclidean distance. Experimental analysis carried out using FEI database shows that the proposed method has an effective improvement over other methods. [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]

To achieve a fused image that contains rich texture details and prominent targets, we present a progressive dual-branch infrared and visible image fusion network called PDFusion, which incorporates the Transformer module. Initially, the proposed network is divided into two branches to extract infrared and visible features independently. Subsequently, the image-wise transfer block (ITB) is introduced to fuse the infrared and visible features at different layers, facilitating the exchange of information between features. The fused features are then fed back into both pathways to contribute to the subsequent feature extraction process. Moreover, in addition to conventional pixel-level and structured loss functions, the contrastive language-image pretraining (CLIP) loss is introduced to guide the network training. Experimental results on publicly available datasets demonstrate the promising performance of PDFusion in the task of infrared and visible image fusion. The exceptional fusion performance of the proposed fusion network can be attributed to the following reasons: (1) The ITB block, particularly with the integration of the Transformer, enhances the capability of representation learning. The Transformer module captures long-range dependencies among image features, enabling a global receptive field that integrates contextual information from the entire image. This leads to a more comprehensive fusion of features. (2) The feature loss based on the CLIP image encoder minimizes the discrepancy between the generated and target images. Consequently, it promotes the generation of semantically coherent and visually appealing fused images. The source code of our method can be found at https://github.com/Changfei-Zhou/PDFusion. [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]

• A new adaptive blind image watermarking technology, utilizing artificial intelligence (AI) and named AwDD, has been proposed for detecting color image deepfakes. • The AI technology used includes face detection, denoising autoencoder (DAE), and the gray wolf optimizer (GWO). • The proposed method employs mixed modulation (MM) with partly sign-altered mean value (PSAMV) to embed a set of coefficients, thereby increasing robustness against attacks while maintaining high image quality. • Blind adaptive deepfake detection (BADD) with the tamper detection mean value (TDMV) is applied to adaptively detect changes in the relative position when a face image is modified or deepfaked. • The GWO optimizes parameters to enhance imperceptibility and robustness, while the DAE improves the visual recognizability of the extracted watermark. This paper proposes a new adaptive blind watermarking technology for deepfake detection, which can embed deepfake detection information into the image and verify the image's authenticity without requiring additional information. The proposed scheme utilizes mixed modulation combined with partly sign-altered mean value to embed a set of coefficients that enhance robustness against attacks while maintaining high image quality. Additionally, blind adaptive deepfake detection technology with the tamper detection mean value is employed to detect relative positions adaptively, even when face images are slightly modified or deepfaked. To further improve the performance of the proposed scheme, a gray wolf optimizer is introduced to optimize parameters, and a denoising autoencoder is employed to facilitate the identification of extracted watermarks. This technology will adaptively embed watermark information while preserving the original face image, thereby maintaining the authenticity of the face in the image and verifying the owner of the image. The code is available at https://github.com/lyhsu01/AwDD. [ABSTRACT FROM AUTHOR]

• A novel Residual Global Attention (RGA) to flexibly focus on different types of information, such as thin haze regions and thick haze regions. • A CNN-Transformer architecture to capture both detail texture information and global context information. • A Gated Strength-Operation-Subtract Boosting (GSOS) strategy to effectively integrate cross-layer feature information, thereby overcoming the problem of incomplete noise removal and detail loss. Single image dehazing is one of crucial tasks in the field of computer vision. However, existing methods are challenged on how to handle unevenly distributed haze, capture global contextual information, and filter noise while preserving details. To overcome these limitations, a novel dehazing network with residual global attention and gated boosting strategy based on a CNN-Transformer hybrid architecture (CTHD-Net) is proposed. Firstly, a feature encoder with a residual global attention (RGA) module is presented to improve the representation capability of the entire network by adaptively assigning different weights to feature maps. Subsequently, a CNN-Transformer hybrid architecture is designed to enhance the features encoding via the improved Swin-transformer and to capture the long-range dependencies among features by shifted-window Multi-head Self-attention. Finally, an effective Gated Strength-Operation-Subtract (GSOS) Boosting decoder is developed to reuse the key information required for image reconstruction in the shallow features, while effectively preventing haze noise. Extensive evaluation demonstrates that our proposed CTHD-Net significantly outperforms the previous state-of-the-arts in terms of quantity and quality. The source code has been made available at https://github.com/RC-Qiao/CTHD-Net. [ABSTRACT FROM AUTHOR]

Due to the absorption and scattering of light on the water surface, underwater images often face challenges such as low contrast, color deviation, insufficient exposure, and blurred details, exacerbating the difficulty of underwater tasks. In recent years, underwater image enhancement has become increasingly crucial in marine applications. Among existing underwater enhancement methods, the focus has often been on pixel-level learning, which may lead to image noise and an inability to finely adjust the image. In this paper, we propose a dual-branch Transformer-CNN Parameter Filtering network for underwater image enhancement, referred to as DTCPF. Specifically, to better aggregate window information, we introduce an overlapping window self-attention module to enhance interaction between windows. Additionally, we employ an improved Transformer encoder and decoder, utilizing long-distance attention and reversible neural networks to extract low-frequency and high-frequency information from the image. Moreover, we introduce a regression parameter filtering group for regression prediction, using the predicted parameters to enhance the image and obtain a reliable underwater enhancement model. Our approach undergoes qualitative and quantitative analyses on four real underwater datasets, demonstrating outstanding performance. [ABSTRACT FROM AUTHOR]

Occluded person re-identification (ReID) remains challenging due to the misaligned body parts. Existing works, mainly utilizing extra clues, excel in predicting holistic person images but falter when confronting substantial occlusion. This paper proposes a transformer-based Mask-guided Part-to-Part Matching (MP2PMatch) network for fine-grained matching. Firstly, the Consistency Occlusion Augmentation (COA) processes holistic person images and corresponding body part masks to construct occluded "image-mask" pairs. Next, we introduce learnable part tokens to capture semantic features of various body parts, performing "pull close" and "push apart" operations based on identity labels and part visibility, ensuring the one-to-one correspondence between part features and body parts. Additionally, the proposed Body Region Attention (BRA) utilizes the overall attention on body regions to guide the network to overcome interference from both occlusion and background. Extensive experiments demonstrate that MP2PMatch achieves exceptional occluded ReID performance. • Our proposed MP2PMatch aims to address the Occluded Person ReID problem. • Designing a COA to construct reliable occluded image-mask pairs. • Proposing a BRA to enhance attention within the human body region. • Proposing a PTA to guide the model to extract discriminative part features. • Experimental results demonstrate the effectiveness of our method. [ABSTRACT FROM AUTHOR]

Convolutional neural networks have achieved remarkable success in single image dehazing tasks, and previous studies verified the dehazing performance of the U-shaped framework. However, most existing U-shaped architecture dehazing networks still face challenges in sufficiently dealing with a large area of haze with low visibility. In this paper, we propose a novel dehazing network named Double U-Net(DU-Net). Specifically, to reduce the interference of haze features in the encoder to the recovery stage when skip-connecting to the decoder directly, we develop a new architecture firstly, which is composed of an extended encoder–decoder. Besides, the hierarchical depth-wise convolution block(HDCB) is designed to gradually increase the receptive field by leveraging the depth-wise convolution, enriching the global information. Moreover, we propose a multi-branch interactive fusion(MIF) which achieves efficient cross-branch and cross-channel interaction through parallel multiple 1D convolutions. Extensive experiments on both synthetic and real-world hazy images demonstrate the effectiveness of our proposed method. • We construct a Double U-Net for image dehazing, by extending the encoder–decoder. • We build hierarchical convolution blocks to obtain a multi-scale receptive field. • A branch fusion is proposed to enhance cross-branch and cross-channel interaction. [ABSTRACT FROM AUTHOR]

Restoring image quality in low-light environments is an intriguing topic. While deep learning models have made significant strides in low-light enhancement, most models do not take into account the inherent characteristics of objects themselves. In this paper, we use the characteristics of the image itself to construct a Signal-to-Noise Ratio (SNR) map that guides the signal space variation to dynamically stretch the pixel values. Specifically, we propose a novel signal-to-noise ratio image-guided enhancement framework that uses the feature information of the original image to guide spatial variations in the image. It involves step-wise guidance for image feature fusion, gradually emphasizing high-frequency feature information within the image. Meanwhile, we introduced a texture optimization module that utilizes the feature information extracted by the feature fusion module to address the issues of overexposure and detail loss. We performed qualitative and quantitative evaluations on synthetic and real low-light image datasets to demonstrate the performance of our method. The experimental results show that our model outperforms other state-of-the-art methods (SOTA) in robust low-light enhancement, especially in processing images captured in complex scenes. • SNR map focus on noise distribution to guide model denoising. • Using a step-by-step guided feature fusion module and a texture optimization module. • Fusion of features from different images for spatially varying LLIE. • Texture optimization module emphasizes high-frequency feature information. [ABSTRACT FROM AUTHOR]

Weakly supervised shadow detection has been spreading as cheaper labeling costs in recent years. However, these works tend to use a single annotation manner, i.e., scribble, it may not be the best choice for each shadow scene and thereby cannot exploit more valuable cues for better training. To tackle this issue, this work explores a more flexible labeling strategy, containing scribble, box and point. During the training, rather than only using cross-entropy (CE) loss on the available points, we formulate the supervisions between given annotations with the model's predictions as a bipartite matching problem, and then design efficient weak learning losses from other valuable perspectives of shadow location, quantity and size. Moreover, considering the challenge of poor boundary localization in one-stage weakly supervised image segmentation, we propose a CNN-assisted tuning strategy to inherit boundary knowledge from the vision foundation model (i.e. , SAM), and learn task-specific knowledge from our hybrid annotations by introducing a light-weight CNN branch along with the SAM backbone, namely ShadowSAM. This approach has lower requirements on GPU memory and extracts more local information for identifying tiny shadow regions. Extensive experiments demonstrate that our proposed methods can achieve comparable performance with state-of-the-art (SOTA) fully supervised shadow detectors. Our code will be available at https://github.com/wuwen1994/omni-shadow. [ABSTRACT FROM AUTHOR]

Tracking pedestrians in crowded scenes is a challenging task. Existing transformer-based tracking methods integrate detection and tracking into a unified model, which simplifies the tracking process. However, these methods also introduce complicated attention mechanisms that increase the model complexity and cost. To address this issue, we propose SOTTrack, a simple online transformer-based method for crowd tracking. Our method enhances feature learning and training strategies without sacrificing simplicity and efficiency. Specifically, we introduce the Sequential Feature Aggregation (SFA) module and the Hybrid Group Training (HGT) approach. The SFA module fuses features from sequential images to improve the temporal consistency of visual features within short time intervals. The HGT approach assigns different queries to multiple guided tasks, such as label assignment and de-noising, which are only used during training and do not incur any inference cost. We evaluate our method on the MOT17 and MOT20 datasets and demonstrate its competitive performance. • We propose a new online tracker based on Transformer that learns both detection and tracking pedestrians from static images. • We use sequential feature aggregation, SFA to enable the model to capture temporal information from historical frames. • We adopt a hybrid multi-group training strategy, HGT, that employs multiple query groups with concurrent label assignment training and de-noising training. [ABSTRACT FROM AUTHOR]

Face super-resolution is an important low-level vision task that has wide applications. Existing deep-learning-based face super-resolution (SR) methods often optimize the image super-resolution network by directly minimizing the pixel or feature level distance between the synthetic low-resolution face and the ground truth face image. These methods usually generate blur or over smooth results and lack of high-frequency face details. These are especially true for making high super-resolution of faces. Say for example, a super-resolution of 16x, only 0.4 % of the reference data points are available. To address the problem, we propose a novel network with edge fusion, back projection, and GAN prior (EFBPGAN) which can significantly improve the visual quality and generate realistic faces. To further make use of the spatial information and keep the structural consistency, we have developed new edge fusion and spatial fusion modules. We also propose a back projection extensive based coarse to fine SR pipeline to suppress the distortion and artifacts caused by GAN. Much experimental work has been done, results of which show that our proposed EFBPGAN can outperform the state-of-the-art approaches not only on numerical metrics but also on subjective visual evaluations. [ABSTRACT FROM AUTHOR]

The adage "a picture is worth a thousand words" resonates in the digital video domain, suggesting that a video could be seen as a composition of millions of these words. Videos are composed of countless frames. Video summarization creates cohesive visual units in scenes by condensing shots from segments. Video summarization gains prominence by condensing lengthy videos while retaining crucial content. Despite effective techniques using keyframes or keyshots in video summarization, integrating audio components is imperative. This paper focuses on integrating deep learning techniques to generate dynamic summaries enriched with audio. To address that gap, an efficient model employs audio-visual features, enriching summarization for more robust and informative video summaries. The model selects keyshots based on their significance scores, safeguarding essential content. Assigning these scores to specific video shots is a pivotal yet demanding task for video summarization. The model's evaluation occurs on benchmark datasets, TVSum and SumMe. Experimental outcomes reveal its efficacy, showcasing considerable performance enhancements. On the TVSum, SumMe datasets, an F-Score metric of 79.33% and 66.78%, respectively, is achieved, surpassing previous state-of-the-art techniques. [ABSTRACT FROM AUTHOR]

Face reenactment is a task to transfer the facial pose and expression from one driving face to the source face. It can be done by adding many condition information, such as the landmark, 3D Morphable Model (3DMM). Because the landmark information is easy to get and contains face structure and expression information, many works rely on it. One of the key points for the landmark-based method is to generate landmarks that keep the face shape of the source image while having the same expression and pose as the driving image. Concentrating on this problem, we propose a novel and effective method to transfer the expression and pose based on the motion of the key points between driving images. Besides, we also try to improve the fit ability of the current popular backbone by adding an enhancement module. [ABSTRACT FROM AUTHOR]

Recently, Transformer-based architecture has been introduced into single image deraining tasks due to its advantage in modeling non-local information. However, existing approaches typically utilize self-attention along single spatial or channel dimension. They neglect feature fusion in different dimensions to explore contextual information fully, which limits the effective receptive field of the network and makes it challenging to learn image degradation relationships. To fully explore potential correlations between different dimensions of degraded images, we develop a D ual-branch C ollaborative Trans former , called DCformer. To be specific, we employ parallel multi-head self-attention (PMSA) as the core block to extract long-range contextual relationships across spatial and channel dimensions. Additionally, a local perception block (LPB) is introduced to provide the ability of local information acquisition in the network, which is complementary to the global modeling ability of the parallel hybrid self-attention mechanism. Finally, we design a feature interaction block (FIB) to further enhance the interaction of features at different resolutions. Extensive experiments on benchmark datasets demonstrate the effectiveness of our proposed method. [ABSTRACT FROM AUTHOR]

Seam carving is a method of resizing images based on content awareness. It can realize image retargeting while retaining the main content of the image. However, it may also be maliciously used to tamper with images, such as changing image semantic content by object removal. Therefore, seam carving detection has become important in image forensics. In this paper, a noise residual-based deep learning method is proposed to detect seam carving images. We try to learn the local noise in-consistency of images to recognize them. Firstly, a noise residual extraction segment is used to learn local noise features in the image, and a noise augmentation module is designed to enrich the features, which leverages the noise features extracted from a steganalysis rich model filter to discover the noise in-consistency between authentic and tampered regions. Then, through the feature dimensionality reduction section, the features are further learned and the size of feature maps are reduced. Finally, the output is obtained through global average pooling and a fully-connected layer. A careful testing strategy is further proposed, which greatly improves the detection performance, especially for seam carving with small scaling ratios. The experimental results demonstrate that our method achieves state-of-the-art performance at various scales, and has good robustness and generalization compared with other methods. [ABSTRACT FROM AUTHOR]

• Grayscale probabilistic matrix (GPM) with multi-level grayscale pixels is introduced into the construction of secret shares. • A general model of size-invariant TiOISSS based on GPMs is proposed which has no limit on the number of participants. • The visual quality of previewing images is improvedunder the gray mixing model while that of computed image is not degraded. TiOISSS (Two-in-One Image Secret Sharing Scheme) can reconstruct the secret through computation and realize secret preview recovery when the power system is destroyed or the network is paralyzed. However, the visual quality of previewing images obtained by the existing TiOISSS is not satisfactory and usually affected by pixel expansion. To resolve the two problems, this paper introduces multiple gray values in the share image generation stage and establishes an optimization model to obtain the grayscale probabilistic matrix needed in the encoding stage. By using the probability matrix, a secret sharing algorithm is designed to obtain size-invariant shares with multiple gray values. Then, the secret information of another image can be shared and embedded into the multi-level gray shares through Lagrange polynomials over finite fields. In the decryption stage, the electronic shares can be directly superimposed based on a gray mixing model, or they can be printed to transparent films by a multi-level gray printer and then superimposed to obtain the preview image. If computational devices are available, a high-resolution gray image can be obtained by Lagrange interpolation over finite fields. Experimental results indicate that the proposed scheme is effective for generating shares without pixel expansion and improving the preview image quality. [ABSTRACT FROM AUTHOR]

Images taken in low-light conditions often suffer from various types of degradation. While most current methods primarily focus on spatial domain information to address these degradation issues, they often overlook the importance of frequency domain information. In order to better solve the degradation problems of low-light images, the Multi-Frequency Field Perception and Sparse Progressive Network (MFSPNet) for low-light image enhancement is proposed through Leveraging the complementary strengths of the frequency domain and the spatial domain, aiming to tackle the challenges of degraded images in intricate scenarios. Specifically, we propose the frequency domain field feature filtering (FDFF) module, which utilizes image frequency distribution information to address issues such as noise and artifacts in low-light images while complementing the spatial domain. Subsequently, we embed different scales of FDFF into four heterogeneous branches to flexibly handle features at various levels of complexity. Furthermore, we design a sparse wing-shaped transformer block (SWTB) that enhances the focus on critical information and complex multi-scale details through adaptive sparse attention unit (ASAU) and illumination multi-scale fusion feedforward network (IMF-FN). In addition, we propose a progressive enhancement strategy for self-knowledge sublimation to gradually improve image quality. At last, we comprehensively assess the proposed network across multiple datasets. Compared to other methods, our approach achieved the highest PSNR scores, with improvements of 3.014 dB and 0.215 dB, respectively, over the next best results. Additionally, our method exhibited the highest SSIM gain. Abundant experimental outcomes demonstrate that our approach outperforms numerous present low-light image enhancement approaches in both objective evaluation metrics and subjective visual effects, showcasing outstanding performance and significant potential. [ABSTRACT FROM AUTHOR]

This paper investigates the generation of large field-of-view (FOV) and high-resolution (HR) panorama images for smartphones. Existing techniques like image stitching struggle to produce satisfactory results due to geometry misalignment and inconsistent appearance. To circumvent the inherent challenges of image stitching methods and generate high-quality panoramas, we treat the image stitching problem as a multiple-reference-based super-resolution problem. Specifically, one large-FOV low-resolution (LR) image and several overlapped small-FOV HR images are taken as inputs, where the LR image acts as a base and multi-view references provide rich HR information. Building on this foundation, a novel multi-view references image super-resolution framework (MVRefSR) is proposed. Within this framework, to address the residual geometric misalignment between the LR-Ref image pairs after coarse alignment, a flow-based RefSR network (FlowSRNet) is proposed, which super-resolves LR patches with corresponding HR references. To facilitate adaptive feature fusion and minimize distortion in structured regions, a fusion weight estimation module and a gradient branch are introduced in FlowSRNet. Finally, the large-FOV HR image is generated by combining these SR patches together. Furthermore, the lack of real-world RefSR datasets for smartphones is addressed by designing an innovative dataset construction pipeline. Extensive experiments demonstrate the superior performance of FlowSRNet and MVRefSR over the compared SR methods and image stitching software, which proves the effectiveness of generating panoramas from a new perspective. • A novel multi-view references image super-resolution framework (MVRefSR) is proposed to generate the large field-of-view and high-resolution panoramas from a new perspective. • Two modules, a fusion weight estimation module and a gradient branch, are adopted to enhance the performance of our reference-based super-resolution (RefSR) methods within our MVRefSR framework. • A new RefSR dataset generation pipeline and a real-world RefSR dataset are presented to address the lack of datasets and facilitate the study of real-world RefSR. • Experimental results demonstrate the superiority of our RefSR network and our framework MVRefSR, which proves the effectiveness of generating panoramas from a new perspective. [ABSTRACT FROM AUTHOR]

Recent self-supervised learning methods, where instance discrimination task is a fundamental way of pretraining convolutional neural networks (CNN), excel in transfer learning performance. Even though instance discrimination task is a well suited pretraining method for classification with its image-level learning, lack of dense representation learning makes it sub-optimal for localization tasks such as object detection. In this paper, we aim to mitigate this shortcoming of instance discrimination task by extending it to jointly learn dense representations alongside image-level representations. We add a segmentation branch parallel to the image-level learning to predict class-agnostic masks, enhancing location-awareness of the representations. We show the effectiveness of our pretraining approach on localization tasks by transferring the learned representations to object detection and segmentation tasks, providing relative improvements by up to 1.7% AP on PASCAL VOC and 0.8% AP on COCO object detection, 0.8% AP on COCO instance segmentation and 3.6% mIoU on PASCAL VOC semantic segmentation respectively. • Convolutional Neural Networks lose localization info with instance discrimination task. • Augmenting instance discrimination with an extra dense task enhances localization. • Unsupervised foreground segmentation boosts localization in (non-)contrastive methods. • Improved localization in SSL enhances transfer learning in dense downstream tasks. [ABSTRACT FROM AUTHOR]

Transparent or specular objects, such as mirrors, glass windows, and glass walls, have a significant impact on computer vision tasks. Glass-like Objects (GLOS) encompass transparent or specular objects that lack distinctive visual appearances and specific external shapes, posing challenges for GLO segmentation. In this study, we propose a novel bidirectional cross-modal fusion framework with a shift-window cross-attention for GLO segmentation. The framework incorporates a Feature Exchange Module (FEM) and a Shifted-window Cross-attention Feature Fusion Module (SW-CAFM) in each transformer block stage to calibrate, exchange, and fuse cross-modal features. The FEM employs coordinate and spatial attention mechanisms to filter out the noise and recalibrate the features from two modalities. The Shifted-Window Cross-Modal Attention Fusion (SW-CAFM) uses cross-attention to fuse RGB and depth features, leveraging the shifted-window self-attention operation to reduce the computational complexity of cross-attention. The experimental results demonstrate the feasibility and high performance of the proposed method, achieving state-of-the-art results on various glass and mirror benchmarks. The method achieves mIoU accuracies of 90.32%, 94.24%, 88.76%, and 87.47% on the GDD, Trans10K, MSD, and RGBD-Mirror datasets, respectively. • A depth-aware dual-stream mutual interactive cross-modal attention fusion network, referred to as DAGNet, is proposed for the task of GLOS segmentation. • A Feature Exchange Module(FEM) is specifically designed to enhance the interaction between RGB and depth modalities by leveraging spatial and channel self-attention mechanisms. • The Shifted-window Cross-attention Fusion Module (SW-CAFM) is created to utilize a cross-fusion attention method to combine attention information from two modalities, facilitating the learning of relevant features. • Comparative evaluation of the proposed DAGNet against state-of-the-art methods on four standard GLOS bench marks. [ABSTRACT FROM AUTHOR]

• Our method is based on TinyVit and graph convolutional network. • We propose the object localization module to improve the local feature representation. • We propose a spatial relation feature learning module to learn richer image features. • Experimenting on three public datasets, our method demonstrates very competitive results. Fine-grained image classification is a branch of image classification. Recently, vision transformer has made excellent progress in the field of image recognition. Its self-attention mechanism can extract very effective image feature information. However, feeding fixed-size image blocks into the network introduces additional noise, which is detrimental to extract discriminative features for fine-grained images. The vision transformer's network model is large, making it difficult to utilize in practice. Moreover, many of today's fine-grained image classification methods focus on mining discriminative features while ignoring the connections within the image. To address these problems, we propose a novel method based on the lightweight TinyVit backbone network. Our approach utilizes the self-attention weight values of TinyVit as a guide to construct an effective object location (OL) module that cuts and enlarges the object area, providing the network with the opportunity to concentrate on the local object. Additionally, we employ the graph convolutional network (GCN) to create a spatial relationship feature learning (SRFL) module that captures spatial context information between image blocks in TinyVit with the help of the transformer's self-attention weights. OL and SRFL collaborate to jointly guide the classification task. The experimental results show that the proposed method achieved competitive performance, with the second-highest classification faccuracy on both the CUB-200–2011 and NABirds datasets. When tested on the Stanford Dogs dataset, our approach outperformed many popular methods. Our code is uploaded on https://github.com/hhhj1999/SRFL_OL. [ABSTRACT FROM AUTHOR]

Small particles present in the air degrade the visual clarity of images due to light scattering phenomena caused by particles. This degradation of the image is in the context of attenuation of light intensity and poor contrast, which ultimately have an impact on the image's quality. Thus, image dehazing is a necessity for better visualization and image analysis. The proposed method uses an unsupervised approach to dehaze the image without using any ground truth image or transmission map, which overcomes the necessity of a paired dataset and a true depth map. The majority of current state-of-the-art haze removal approaches observe color shifts in the sky region. By utilizing the contour process and RGB color plane data, the proposed innovative "ContourDCP" technique can effectively identify the sky area. After applying the Dark Channel Prior (DCP) to obtain the initial transmission map, it is further reformulate through the contour method to achieve an accurate color representation of the sky area during the image dehazing process. We proposed atmospheric light estimation based on the haze concentration present in the Y-plane after conversion from RGB to YCbCr color space. These modified transmission map and atmospheric light are used in the atmospheric scattering model to recover the scene radiance. Performance evaluation of the method shows the robustness of the proposed method compared to existing state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Thanks to the powerful modeling capabilities of multi-head self attention (MSA), transformers have shown significant performance gains in vision tasks. However, as transformers require heavy computation, more efficient designs are required. In this paper, we present an efficient transformer architecture named GoLDFormer for image restoration. GoLDFormer extends the capability of window-based self-attention through two core designs. First, We propose a globally-enhanced window-based transformer block (G-WTB), which applies transposed attention to a compressed window representation rather than the spatial features, thus establishing connections between all windows with less computational complexity. Second, since the interactions between image content and window attention weights can be interpreted as spatially varying convolution, we introduce an adaptive filter structure into transformer models and propose a deformable filtering block (DFB) to enable cross-window connections. By adjusting the shape of the generated filters in the DFB, we can balance the computational costs and the degree of adjacent window interaction. Extensive experiments on several image restoration tasks demonstrate that GoLDFormer achieves competitive results against recent methods but with optimal computational costs. • We propose GoLDFormer, including two blocks, to enhance W-MSA globally and locally. • Globally-enhanced attention block captures global dependencies between all windows. • Deformable filtering block captures local dependencies by modifying filter size. • Our GoLDFormer achieves competitive results against recent lightweight methods. [ABSTRACT FROM AUTHOR]

Image features in low-light scenes become hard to distinguish and full of noise, which makes the performance of current popular instance segmentation models drastically degraded. We propose a two-stage approach for instance segmentation of low-light images with enhancement followed by segmentation. Stage-I corresponds to the Low-Light Image Enhancement (LLIE) process. We propose a post-processing Detail Enhancement Denoising Module (DEDM) to suppress degradation effects caused by the enhancement in the preprocessing stage. Stage-II represents the segmentation process of enhanced images. We construct the W-BCNet instance segmentation network and design a Wavelet Feature Fusion Module (WFFM) in the feature extraction stage to preserve more fine-grained features. We achieve great segmentation results on LIS, detailed comparative experiments and ablation studies show the advantages and excellent generalization ability of our model. [ABSTRACT FROM AUTHOR]

• We propose a cascading Transformer to address the computational bottleneck of the Transformer in handling complex tasks with blurry images. • We propose the Deep Separable Attention (DSA) mechanism to replace the vanilla self-attention mechanism, which can capture specific areas of blur in the image and calculate attention scores across feature dimensions. • We propose the Double-Flow Gate (DFG) to enhance the model's nonlinearity, control the output of specific blurry information, and improve deblurring performance. In dynamic scenes, motion blur can often occur, which is non-uniform and can be difficult to remove. Recently, the Transformer has shown excellent performance in various image-related tasks such as classification, recognition, and segmentation. Using a Transformer-based backbone network has also shown potential advantages in image deblurring. However, the computational complexity of Transformers increases quadratically with spatial resolution, making it difficult to apply to high-resolution images. To address the above issue, we propose a cascade Transformer (Casformer) that consists of two key modules: Deep Separable Attention (DSA) and Double-Flow Gate (DFG). Our approach effectively reduces computational complexity while suppressing blurry information. Additionally, we discovered an inconsistency between training and testing images during the image restoration process. We addressed this issue by experimentally verifying an inference aggregation method (IAM) that independently predicts patches during inference to address the problem of imbalanced information distribution. Experimental results demonstrate that our design performs well on GoPro and other datasets, e.g. 29.20 dB PSNR on RealBlur-J, exceeding the previous state-of-the-art (SOTA) 0.14 dB. [ABSTRACT FROM AUTHOR]

In this paper, an approach to the semantic segmentation of 3D LiDAR point clouds obtained from natural scenes is introduced. Using a state-of-the-art projection-based semantic segmentation model as the core segmentation network, several recent advances in projection-based 3D semantic segmentation methods are aggregated into a single model. These adaptions include: scan unfolding, soft-kNN post-processing, and multi-projection fusion. A novel Naïve Bayesian approach to multi-projection fusion which weights class probabilities based on the outputs of the base classifiers is proposed to further increase robustness. Quantitative and qualitative evaluations on several datasets, including scenes from both urban and natural environments; show that aggregating these adaptions into a single model can further improve the accuracy of state-of-the-art projection-based approaches. Finally, it is demonstrated that the novel Naïve Bayesian approach to multi-projection fusion addresses a number of the challenges inherent to natural data while also improving results on urban data. • Natural data is difficult to analyse due to its complex structures and features. • Aggregating existing adaptations can improve 3D semantic analysis. • Natural data analysis can be improved on without degrading urban data performance. • Projection-based methods are an effective means to semantic analysis of 3D data. • Fusion of multiple perspectives improves semantic analysis of natural 3D data. [ABSTRACT FROM AUTHOR]

Blind image quality assessment (BIQA) aims to automatically predict the perceptual quality of an image without requiring access to its pristine reference counterpart. BIQA models are typically developed through supervised learning, optimizing and testing them by comparing their predictions to human ratings, usually expressed as mean opinion scores (MOS), which can be labor-intensive to collect. The performance of these BIQA models is significantly reliant on the amount of labeled training data. When there is a shortage of human-rated data, these BIQA models may perform inadequately. In this study, we investigate the potential of incorporating unlabeled data to mitigate this issue and enhance the performance of BIQA models. To achieve this, we propose a deep ensemble-based BIQA model (referred to as the "target model") with two heads: one for quality estimation and the other for pseudo-label generation. Initially, we train it on a small set of human-rated images where the supervisory signals are binary labels indicating the pairwise ranking of perceptual quality for image pairs. Then, the head responsible for pseudo-label generation assigns pseudo-binary labels to unlabeled pairs. Subsequently, we re-train the target model using a combination of labeled and pseudo-labeled datasets. This process can be iterated, allowing for the progressive improvement of the target model's performance. We conduct comprehensive case studies to illustrate the advantages of utilizing unlabeled data for BIQA, particularly in terms of model generalization and identifying cases of model failure. [ABSTRACT FROM AUTHOR]

The images in foggy weather are often degraded which may affect the object detection process. Hence, in recent times, several schemes have been designed to eliminate the haze effect and enhance the performance of computer vision systems. Although these methods reduce the haze effect, they also produce over-saturation and over-degradation on most occasions. These problems occur due to inadequate utilization of the regional haze properties during the dehazing process. Therefore, a new dehazing model is proposed in this paper to address the issues faced by existing dehazing algorithms. The residual convolutional neural network (RCNN) with 14 layers is developed in the present work. In this model, features to indicate the extent of haze are extracted using the regional characteristics of a hazy image and are used as the fourth channel along with the three colour channels of a hazy image. The proposed RCNN is trained with 4-channel hazy images as input and their corresponding haze-free images as output. The results of our model are obtained with several images taken from three different datasets. Through the experimentation, quantitative and qualitative improvements are observed when compared to state-of-the-art dehazing methods. • The local-haze characteristics driven dehazing method is developed in this work. • The regional haze properties are extracted using pixel-wise local max-min difference and pixel intensities of the hazy image. • A 4-channel hazy image is developed by concatenating the regional haze properties map to the hazy image. • A 14-layered RCNN is developed with the 4-channel hazy image as input and the haze-free image as output. [ABSTRACT FROM AUTHOR]

Remote sensing image scene classification has made great progress with deep learning. Due to complex backgrounds and the large number of objects with inhomogeneous sizes, remote sensing image scene classification still remains challenging. In fact, only a few parts of regions are expected to be representative of the scene. In this paper, we propose a dual-stream framework for remote sensing classification with the help of category-related regions. Swin Transformer-based global feature extractor is used to produce coarse classification results. A category-related key region localization module is developed to extract the representative region from the whole image. The ResNet50 is employed as a local feature extractor to mine critical features from prominent regions. Finally, the classification results is obtained with the shared weighted classify head on global-local features. Extensive experiments show that our method provides a promising approach for key region locations and performs best on three public remote sensing datasets. [ABSTRACT FROM AUTHOR]

Long running time due to multiple iterations is the main drawback of existing information hiding in the sharing domain (IHSD) algorithm. To address this problem, we propose non-iterative reversible information hiding in the secret sharing domain (NIIHSD). We calculate the coefficients of the polynomial that make the least significant bit of the shadow pixel equal to '0' or '1' and store them in two forms (A 0 and A 1). According to the information to be embedded, coefficients are randomly selected in A 0 and A 1 to generate qualified shares by once calculation. The comparison with IHSD demonstrates our scheme improves the running speed of the algorithm by a factor of 2 to 4 for different (k , n) thresholds and secret image with different sizes. The coefficient forms only need to be created once to be reused. Our scheme has a greater advantage when sharing a large number of images. • The coefficient forms are created in advance. • The eligible shadow pixels can be generated in one calculation. • The extra information can be embedded in any bit of the shadow pixel. • The forms only need to be created once and can be reused to share multiple images. [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]

The contemporary era faces a widespread issue with digital image forgery, posing a significant challenge due to its ease and the broad reach enabled by high-speed internet. This manipulation of images carries substantial socio-political implications globally. Hence, robust digital image forensic methods are critical for detecting such forgeries. This article presents an innovative algorithm specifically designed to detect and locate copy-move duplication within digital images. By utilising the Discrete Cosine Transform and eigenvalues as distinguishing features, the algorithm precisely identifies and pinpoints replicated image regions from overlapping pixel blocks. Uniquely, another cumulative DCT feature enhances the algorithm's ability to discern duplicated regions, even when subjected to post-processing rotation attacks. Experiments using various datasets demonstrate that this method outperforms avant-garde techniques in detecting and localising forgeries, showcasing promising results. This approach contributes significantly to the field of digital image forensics, providing a valuable tool for identifying and localising manipulated content. • An efficient block-based method that localises Copy Move Forgery in images. • Utilises a combination of DCT and eigenvalues for localising Copy Move Forgery. • Novel sum of DCT feature detects rotation post-processing. • Robust to JPEG compression and blurring. • The method performs better than Neural Network-based and the conventional methods. [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]