Search

The present article proposes a new Legendre wavelet (LW) filter-based image super-resolution technique. The LW basis vector is used in compact form using the unit step function. It is acquired using LW parameters and is discretized via collocation points. The LW basis is used to design a new filter that transforms the low-resolution image into a high-resolution image. This filter matrix is zoomed into a higher dimension using a discretized wavelet basis. The zero-padded low-resolution original image and the zoomed filter matrix are then multiplied by a constant parameter to enhance the information of the reconstructed image. The value of this constant parameter is optimized using the maximization of the entropy of the reconstructed image to further enhance the quality of the image. After the multiplication operation, the zoomed filter matrix and the zero-padded low-resolution original image are added to reconstruct the high-resolution image. Four existing techniques are compared with the proposed technique visually and through spatial frequency, standard deviation, and entropy. The proposed method shows better visual and quantitative feature performance as compared to other schemes. [ABSTRACT FROM AUTHOR]

A Residual Multi-branch Distillation Network (RMDN) is proposed and implemented for efficient image super-resolution (SR) by reducing the redundancies in the convolution operations which exists in current information distillation network-based models. To enhance the model ability, an attention module is designed to fuse the distilled features. By reducing the redundancies and focusing on the distilled features, the network can improve the reconstruction performance with low computation costs. Specifically, the Multi-branch Aware Convolution (MAConv) is introduced in the Residual Multi-branch Distillation Block (RMDB), which is the basic building block of RMDN. MAConv utilizes multiple kernel sizes and dilation rates in depth-wise separable convolutions to reduce redundancies and introduce hierarchical receptive fields to extract multi-level features. Meanwhile, a Residual Hybrid Attention Module (RHAM) integrates the reduction-and-expansion strategy and the Residual Hybrid Attention (RHA) in RMDB to efficiently fuse and enhance the aggregated distilled features. To improve the training stability, pixel normalization is adopted after RHAM. Extensive experiments show that the proposed RMDN performs favorably against other state-of-the-art image SR methods in terms of computation costs and image reconstruction quality. [ABSTRACT FROM AUTHOR]

High-precision and rapid detection of apparent defects in subway tunnel linings is crucial for ensuring the structural integrity of tunnels and the safety of train operations. However, current methods often do not adequately account for the spatial characteristics of these defects and perform poorly in detecting and extracting small-scale defects, which limits the accuracy of detection and geometric parameter extraction. To address these challenges, this paper proposes an efficient algorithm for detecting and extracting apparent defects in subway tunnels. Firstly, YOLOv8 was selected as the foundational architecture due to its comprehensive performance. The coordinate attention module and Bottleneck Transformer 3 were then integrated into the model's backbone to enhance the focus on defect-prone areas and improve the learning of feature relationships between defects and other infrastructure. Subsequently, a high-resolution detection layer was added to the model's head to further improve sensitivity to subtle defects. Additionally, a low-quality crack dataset was created using an open access dataset, and transfer learning combined with Real-ESRGAN was employed to enhance the detail and resolution of fine cracks. The results of the field experiments demonstrate that the proposed model significantly improves detection accuracy in high-incidence areas and for small-scale defects, achieving a mean average precision (mAP) of 87% in detecting cracks, leakage, exfoliation, and related infrastructure defects. Furthermore, the crack enhancement techniques substantially improve the representation of fine-crack details, increasing feature extraction accuracy by a factor of four. The findings of this paper could provide crucial technical support for the automated operation and maintenance of metro tunnels. [ABSTRACT FROM AUTHOR]

In this paper, we propose a Local Global Union Network (LGUN), which effectively combines the strengths of Transformers and Convolutional Networks to develop a lightweight and high-performance network suitable for Single Image Super-Resolution (SISR). Specifically, we make use of the advantages of Transformers to provide input-adaptation weighting and global context interaction. We also make use of the advantages of Convolutional Networks to include spatial inductive biases and local connectivity. In the shallow layer, the local spatial information is encoded by Multi-order Local Hierarchical Attention (MLHA). In the deeper layer, we utilize Dynamic Global Sparse Attention (DGSA), which is based on the Multi-stage Token Selection (MTS) strategy to model global context dependencies. Moreover, we also conduct extensive experiments on both natural and satellite datasets, acquired through optical and satellite sensors, respectively, demonstrating that LGUN outperforms existing methods. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

To address the issues of insufficient receptive fields for extracting low-level features and the lack of reinforcement for local key features in lightweight networks, this paper proposed a multistage feature distillation-weighted lightweight image super-resolution network LMSWN. Firstly, a pyramid- like module is employed to expand the receptive field during shallow feature extraction, integrate feature information of different scales, and enrich the information flow of the network. Secondly, a multi-stage residual distillation-weighted module is designed to enhance the ability of square convolution to extract local key features, recover more detailed information, and improve reconstruction performance. At the same time, the combination of channel separation and 1x1 convolution realizes gradual distillation of features, reducing the number of network parameters. Finally, two adaptive parameters are introduced to jointly learn the features of the two branches of the multi-stage residual distillationweighted module, enhancing the attention to different levels of feature information and further enhancing the representation ability of the network. Experimental results show that the proposed network is fully validated on five benchmark datasets: Set 5, Set 14, BSDS 100, Urban 100, and Manga 109, and its performance exceeds the current mainstream lightweight network [ABSTRACT FROM AUTHOR]

In the field of endoscopic imaging, challenges such as low resolution, complex textures, and blurred edges often degrade the quality of 3D reconstructed models. To address these issues, this study introduces an innovative endoscopic image super-resolution and 3D reconstruction technique named Omni-Directional Focus and Scale Resolution (OmDF-SR). This method integrates an Omnidirectional Self-Attention (OSA) mechanism, an Omnidirectional Scale Aggregation Group (OSAG), a Dual-stream Adaptive Focus Mechanism (DAFM), and a Dynamic Edge Adjustment Framework (DEAF) to enhance the accuracy and efficiency of super-resolution processing. Additionally, it employs Structure from Motion (SfM) and Multi-View Stereo (MVS) technologies to achieve high-precision medical 3D models. Experimental results indicate significant improvements in image processing with a PSNR of 38.2902 dB and an SSIM of 0.9746 at a magnification factor of ×2, and a PSNR of 32.1723 dB and an SSIM of 0.9489 at ×4. Furthermore, the method excels in reconstructing detailed 3D models, enhancing point cloud density, mesh quality, and texture mapping richness, thus providing substantial support for clinical diagnosis and surgical planning. [ABSTRACT FROM AUTHOR]

Anchored neighborhood regression (ANR) single-image super-resolution (SISR) method demonstrates great superiority in speed and performance. However, ridge regression adopted by ANR didn't take the prior knowledge of regression parameters into account, which easily leads to over-fitting and is not robust to noise. To mitigate this problem, a Bayesian ANR method is proposed for SISR, called B-ANR. B-ANR uses sparse Bayesian regression model to build the mapping relationship between the low resolution (LR) image patch and its neighbors. The parameters of Bayesian regression model as well as its variance are estimated using maximum a posterior. Since our proposed B-ANR is deduced in the probabilistic framework, it has stronger generalization performance and robustness to noise. Experimental results verify that our method is superior to ANR in performance. [ABSTRACT FROM AUTHOR]

Magnetic resonance (MR) images are widely used for clinical diagnosis, whereas some surrounding factors always limit the resolution, so under-sampled data is usually generated during imaging. Since high-resolution (HR) MR images contribute to the clinic diagnosis, reconstructing HR MR images from these under-sampled data is pretty important. Recently, deep learning (DL) methods for HR reconstruction of MR images have achieved impressive performance. However, it is difficult to collect enough data for training DL models in practice due to medical data privacy regulations. Fortunately, federated learning (FL) is proposed to eliminate this issue by local/distributed training and encryption. In this paper, we propose a multi-scale channel attention network (MSCAN) for MR image super-resolution (SR) and integrate it into an FL framework named FedAve to make use of data from multiple institutions and avoid privacy risk. Specifically, to utilize multi-scale information in MR images, we introduce a multi-scale feature block (MSFB), in which multi-scale features are extracted and attention among features at different scales is captured to re-weight these multi-scale features. Then, a spatial gradient profile loss is integrated into MSCAN to facilitate the recovery of textures in MR images. Last, we incorporate MSCAN into FedAve to simulate the scenery of collaborated training among multiple institutions. Ablation studies show the effectiveness of the multi-scale features, the multi-scale channel attention, and the texture loss. Comparative experiments with some state-of-the-art (SOTA) methods indicate that the proposed MSCAN is superior to the compared methods and the model with FL has close results to the one trained by centralized data. [ABSTRACT FROM AUTHOR]

Low-dose computed tomography (LDCT) has been widely used in medical diagnosis. In practice, doctors often zoom in on LDCT slices for clearer lesions and issues, while, a simple zooming operation fails to suppress low-dose artifacts, leading to distorted details. Therefore, numerous LDCT super-resolution (SR) methods have been proposed to promote the quality of zooming without the increase of the dose in CT scanning. However, there are still some drawbacks that need to be addressed in existing methods. First, the region of interest (ROI) is not emphasized due to the lack of guidance in the reconstruction process. Second, the convolutional blocks extracting fix-resolution features fail to concentrate on the essential multi-scale features. Third, a single SR head cannot suppress the residual artifacts. To address these issues, we propose an LDCT CT joint SR and denoising reconstruction network. Our proposed network consists of global dual-guidance attention fusion modules (GDAFMs) and multi-scale anastomosis blocks (MABs). The GDAFM directs the network to focus on ROI by fusing the extra mask guidance and average CT image guidance, while the MAB introduces hierarchical features through anastomosis connections to leverage multi-scale features and promote the feature representation ability. To suppress radial residual artifacts, we optimize our network using the feedback feature distillation mechanism (FFDM) which shares the backbone to learn features corresponding to the denoising task. We apply the proposed method to the 3D-IRCADB and PANCREAS datasets to evaluate its ability on LDCT image SR reconstruction. The experimental results compared with state-of-the-art methods illustrate the superiority of our approach with respect to peak signal-to-noise (PSNR), structural similarity (SSIM), and qualitative observations. Our proposed LDCT joint SR and denoising reconstruction network has been extensively evaluated through ablation, quantitative, and qualitative experiments. The results demonstrate that our method can recover noise-free and detail-sharp images, resulting in better reconstruction results. Code is available at https://github.com/neu-szy/ldct_sr_dn_w_ffdm. [ABSTRACT FROM AUTHOR]

Convolutional neural networks depend on deep network architectures to extract accurate information for image super‐resolution. However, obtained information of these convolutional neural networks cannot completely express predicted high‐quality images for complex scenes. A dynamic network for image super‐resolution (DSRNet) is presented, which contains a residual enhancement block, wide enhancement block, feature refinement block and construction block. The residual enhancement block is composed of a residual enhanced architecture to facilitate hierarchical features for image super‐resolution. To enhance robustness of obtained super‐resolution model for complex scenes, a wide enhancement block achieves a dynamic architecture to learn more robust information to enhance applicability of an obtained super‐resolution model for varying scenes. To prevent interference of components in a wide enhancement block, a refinement block utilises a stacked architecture to accurately learn obtained features. Also, a residual learning operation is embedded in the refinement block to prevent long‐term dependency problem. Finally, a construction block is responsible for reconstructing high‐quality images. Designed heterogeneous architecture can not only facilitate richer structural information, but also be lightweight, which is suitable for mobile digital devices. Experimental results show that our method is more competitive in terms of performance, recovering time of image super‐resolution and complexity. The code of DSRNet can be obtained at https://github.com/hellloxiaotian/DSRNet. [ABSTRACT FROM AUTHOR]

Magnetic resonance imaging (MRI) is a medical imaging technique used to show anatomical structures and physiological processes of the human body. Due to limitations like image acquisition time, hardware capabilities, or uncooperative patients, the resolution of MR images is insufficient. Super-resolution (SR) is a crucial method to enhance the resolution of images without expensive scanning equipment. Recent years have witnessed significant progress in MR image super-resolution. Therefore, this survey presents a thorough overview of current developments in deep learning-based MR image super-resolution methods. In general, we can roughly divide the MRI super-resolution methods into single-contrast MR image SR methods and multi-contrast MR image SR methods. Additionally, we introduce the multi-task learning approaches about the MR image super-resolution. We also summarize other crucial topics, such as the degradation model, the definition of the super-resolution problem, the dataset, loss functions, and image quality assessment. Lastly, we indicate the challenges in the field of super-resolution and draw a conclusion to our survey. [ABSTRACT FROM AUTHOR]

Super-resolution imaging has, for more than seventy years, gradually evolved to produce advanced methods for enhancing the resolution of images beyond the diffraction limits. Notwithstanding its foreseeable practical capabilities, we noted that this technology has received undeserved attention. The present work provides an extensive review of super-resolution imaging since its first conception in 1952, contextualizing studies into four research directions: reviews, advances, applications, and hardware implementations. We have discussed achievements, challenges, and potential opportunities of super-resolution imaging to equip researchers, especially those in their early careers, with knowledge to further advance the technology. Our work may open interesting research avenues that may accelerate realization of the technology into commercial imaging devices. [ABSTRACT FROM AUTHOR]

Infrared images hold significant value in applications such as remote sensing and fire safety. However, infrared detectors often face the problem of high hardware costs, which limits their widespread use. Advancements in deep learning have spurred innovative approaches to image super-resolution (SR), but comparatively few efforts have been dedicated to the exploration of infrared images. To address this, we design the Residual Swin Transformer and Average Pooling Block (RSTAB) and propose the SwinAIR, which can effectively extract and fuse the diverse frequency features in infrared images and achieve superior SR reconstruction performance. By further integrating SwinAIR with U-Net, we propose the SwinAIR-GAN for real infrared image SR reconstruction. SwinAIR-GAN extends the degradation space to better simulate the degradation process of real infrared images. Additionally, it incorporates spectral normalization, dropout, and artifact discrimination loss to reduce the potential image artifacts. Qualitative and quantitative evaluations on various datasets confirm the effectiveness of our proposed method in reconstructing realistic textures and details of infrared images. [ABSTRACT FROM AUTHOR]

Due to limited memory and computing resources, the application of deep neural networks on embedded and mobile devices is still a great challenge. To tackle this problem, this paper proposes a lightweight super-resolution network based on asymmetric encoder–decoder (LSRN-AED), which achieves better performance while reducing model parameters and computation. On the basis of rethinking the roles of encoder and decoder, an asymmetric encoder–decoder (AED) composed of complex encoders and simple decoders is designed to achieve feature extraction and reconstruction. Here, the decoder only adopts one inverted residual block, which can reduce the computational cost of the model and the redundancy of mapping features. For the encoder, inspired by the Transformer structure, an epiphany encoder is designed to realize the feature extraction and representation. In the encoder, a multi-way epiphany attention module (MEAM) is constructed, in which inverted residual blocks are used to replace traditional residual blocks to extract features and reduce model complexity. To realize the selection and enhancement of spatial features, an epiphany attention block (EAB) is designed by exploiting depth-wise convolutions which can learn the significant spatial information of the feature maps. Experimental results demonstrate that the proposed LSRN-AED can achieve better performance at lower parameter cost and outperform some existing state-of-the-art lightweight models. For example, compared to the advanced SMSR method, the proposed LSRN-AED has better evaluation metrics while reducing the number of parameters by 45%, 44%, and 44%, and FLOPs by 44%, 42%, and 41% on the × 2/3/4 SR tasks, respectively. The code will be published on GitHub after our paper is accepted for publication. [ABSTRACT FROM AUTHOR]

The accurate detection of electrical equipment states and faults is crucial for the reliable operation of such equipment and for maintaining the health of the overall power system. The state of power equipment can be effectively monitored through deep learning-based visual inspection methods, which provide essential information for diagnosing and predicting equipment failures. However, there are significant challenges: on the one hand, electrical equipment typically operates in complex environments, thus resulting in captured images that contain environmental noise, which significantly reduces the accuracy of state recognition based on visual perception. This, in turn, affects the comprehensiveness of the power system's situational awareness. On the other hand, visual perception is limited to obtaining the appearance characteristics of the equipment. The lack of logical reasoning makes it difficult for purely visual analysis to conduct a deeper analysis and diagnosis of the complex equipment state. Therefore, to address these two issues, we first designed an image super-resolution reconstruction method based on the Generative Adversarial Network (GAN) to filter environmental noise. Then, the pixel information is analyzed using a deep learning-based method to obtain the spatial feature of the equipment. Finally, by constructing the logic diagram for electrical equipment clusters, we propose an interpretable fault diagnosis method that integrates the spatial features and temporal states of the electrical equipment. To verify the effectiveness of the proposed algorithm, extensive experiments are conducted on six datasets. The results demonstrate that the proposed method can achieve high accuracy in diagnosing electrical equipment faults. [ABSTRACT FROM AUTHOR]

3D digital-image correlation (3D-DIC) is a non-contact optical technique for full-field shape, displacement, and deformation measurement. Given the high experimental hardware costs associated with 3D-DIC, the development of high-fidelity 3D-DIC simulations holds significant value. However, existing research on 3D-DIC simulation was mainly carried out through the generation of random speckle images. This study innovatively proposes a complete 3D-DIC simulation method involving optical simulation and mechanical simulation and integrating 3D-DIC, virtual stereo vision, and image super-resolution reconstruction technology. Virtual stereo vision can reduce hardware costs and eliminate camera-synchronization errors. Image super-resolution reconstruction can compensate for the decrease in precision caused by image-resolution loss. An array of software tools such as ANSYS SPEOS 2024R1, ZEMAX 2024R1, MECHANICAL 2024R1, and MULTIDIC v1.1.0 are used to implement this simulation. Measurement systems based on stereo vision and virtual stereo vision were built and tested for use in 3D-DIC. The results of the simulation experiment show that when the synchronization error of the basic stereo-vision system (BSS) is within 10 − 3  time steps, the reconstruction error is within 0.005 mm and the accuracy of the virtual stereo-vision system is between the BSS's synchronization error of 10 − 7  and 10 − 6  time steps. In addition, after image super-resolution reconstruction technology is applied, the reconstruction error will be reduced to within 0.002 mm. The simulation method proposed in this study can provide a novel research path for existing researchers in the field while also offering the opportunity for researchers without access to costly hardware to participate in related research. [ABSTRACT FROM AUTHOR]

Image super-resolution (SR) technology can improve the resolution of images and provide clearer and more reliable remote sensing images of high quality to better serve the subsequent applications. However, when reconstructing high-frequency feature areas of remote sensing images, existing SR reconstruction methods are prone to artifacts that affect visual effects and make it difficult to generate real texture details. In order to address this issue, a texture-detail-enhanced dense generative adversarial network (TDEGAN) for remote sensing image SR is presented. The generator uses multi-level dense connections, residual connections, and Shuffle attention (SA) to improve the feature extraction ability. A PatchGAN-style discrimination network is designed to effectively perform local discrimination and helps the network generate rich, detailed features. To reduce the impact of artifacts, we introduce an artifact loss function, which is combined with the exponential moving average (EMA) technique to distinguish the artifacts generated from the actual texture details through local statistics, which can help the network reduce artifacts and generate more realistic texture details. Experiments show that TDEGAN can better restore the texture details of remote sensing images and achieves certain advantages in terms of evaluation indicators and visualization. [ABSTRACT FROM AUTHOR]

Super-resolution (SR) is a technique that restores image details based on existing information, enhancing the resolution of images to prevent quality degradation. Despite significant achievements in deep-learning-based SR models, their application in underwater sonar scenarios is limited due to the lack of underwater sonar datasets and the difficulty in recovering texture details. To address these challenges, we propose a multi-scale generative adversarial network (SIGAN) for super-resolution reconstruction of underwater sonar images. The generator is built on a residual dense network (RDN), which extracts rich local features through densely connected convolutional layers. Additionally, a Convolutional Block Attention Module (CBAM) is incorporated to capture detailed texture information by focusing on different scales and channels. The discriminator employs a multi-scale discriminative structure, enhancing the detail perception of both generated and high-resolution (HR) images. Considering the increased noise in super-resolved sonar images, our loss function emphasizes the PSNR metric and incorporates the L2 loss function to improve the quality of the output images. Meanwhile, we constructed a dataset for side-scan sonar experiments (DNASI-I). We compared our method with the current state-of-the-art super-resolution image reconstruction methods on the public dataset KLSG-II and our self-built dataset DNASI-I. The experimental results show that at a scale factor of 4, the average PSNR value of our method was 3.5 higher than that of other methods, and the accuracy of target detection using the super-resolution reconstructed images can be improved to 91.4%. Through subjective qualitative comparison and objective quantitative analysis, we demonstrated the effectiveness and superiority of the proposed SIGAN in the super-resolution reconstruction of side-scan sonar images. [ABSTRACT FROM AUTHOR]

License plate recognition is a pivotal challenge in surveillance applications, predominantly due to the low resolution and diminutive size of license plates, which impairs recognition accuracy. The advent of AI-based super-resolution techniques offers a promising avenue to ameliorate the resolution of such images. Despite the deployment of various super-resolution methodologies, including Convolutional Neural Networks (CNNs) and Generative Adversarial Networks (GANs), the quest for satisfactory outcomes in license plate image enhancement persists. This paper introduces "DiffPlate", a novel Diffusion Model specifically tailored for license plate super-resolution. Leveraging the unprecedented capabilities of Diffusion Models in image generation, DiffPlate is meticulously trained on a dataset comprising low-resolution and high-resolution pairs of Saudi license plates, curated for our surveillance application. Our empirical analysis substantiates that DiffPlate markedly eclipses state-of-the-art alternatives such as SwinIR and ESRGAN, evidencing a 26.47% and 37.32% enhancement in Peak Signal-to-Noise Ratio (PSNR) against these benchmarks, respectively. Furthermore, DiffPlate achieves superior performance in terms of Structural Similarity Index (SSIM), with a 4.88% and 16.21% improvement over SwinIR and ESRGAN, respectively. Human evaluative studies further corroborate that images refined by DiffPlate were preferred 92% more frequently compared to those processed by other algorithms. Through DiffPlate, we present a new solution to the license plate super-resolution challenge, demonstrating significant potential for adoption in real-world surveillance systems. [ABSTRACT FROM AUTHOR]

Abstract Convolutional neural networks depend on deep network architectures to extract accurate information for image super‐resolution. However, obtained information of these convolutional neural networks cannot completely express predicted high‐quality images for complex scenes. A dynamic network for image super‐resolution (DSRNet) is presented, which contains a residual enhancement block, wide enhancement block, feature refinement block and construction block. The residual enhancement block is composed of a residual enhanced architecture to facilitate hierarchical features for image super‐resolution. To enhance robustness of obtained super‐resolution model for complex scenes, a wide enhancement block achieves a dynamic architecture to learn more robust information to enhance applicability of an obtained super‐resolution model for varying scenes. To prevent interference of components in a wide enhancement block, a refinement block utilises a stacked architecture to accurately learn obtained features. Also, a residual learning operation is embedded in the refinement block to prevent long‐term dependency problem. Finally, a construction block is responsible for reconstructing high‐quality images. Designed heterogeneous architecture can not only facilitate richer structural information, but also be lightweight, which is suitable for mobile digital devices. Experimental results show that our method is more competitive in terms of performance, recovering time of image super‐resolution and complexity. The code of DSRNet can be obtained at https://github.com/hellloxiaotian/DSRNet.

Abstract Super-resolution imaging has, for more than seventy years, gradually evolved to produce advanced methods for enhancing the resolution of images beyond the diffraction limits. Notwithstanding its foreseeable practical capabilities, we noted that this technology has received undeserved attention. The present work provides an extensive review of super-resolution imaging since its first conception in 1952, contextualizing studies into four research directions: reviews, advances, applications, and hardware implementations. We have discussed achievements, challenges, and potential opportunities of super-resolution imaging to equip researchers, especially those in their early careers, with knowledge to further advance the technology. Our work may open interesting research avenues that may accelerate realization of the technology into commercial imaging devices.

Abstract Existing image super-resolution methods have made remarkable advancements in enhancing the visual quality of real-world images. However, when it comes to restoring Chinese paintings, these methods encounter unique challenges. This is primarily due to the difficulty in preserving intricate non-realistic details and capturing comple semantic information with high dimensionality. Moreover, the preservation of the original artwork’s distinct style and subtle artistic nuances further amplifies this complexity. To address these challenges and effectively restore traditional Chinese paintings, we propose a Convolutional Super-Resolution Generative Adversarial Network for Chinese landscape painting super-resolution, termed ConvSRGAN. We employ Enhanced Adaptive Residual Module to delve deeply into multi-scale feature extraction in images, incorporating an Enhanced High-Frequency Retention Module that leverages an Adaptive Deep Convolution Block to capture fine-grained high-frequency details across multiple levels. By combining the Multi-Scale Structural Similarity loss with conventional losses, our ConvSRGAN ensures that the model produces outputs with improved fidelity to the original image’s texture and structure. Experimental validation demonstrates significant qualitative and quantitative results when processing traditional paintings and murals datasets, particularly excelling in high-definition reconstruction tasks for landscape paintings. The reconstruction effect showcases enhanced visual fidelity and liveliness, thus affirming the effectiveness and applicability of our approach in cultural heritage preservation and restoration.

Image super-resolution (SR) algorithms are placed on high hope to reconstruct ultra-high-definition (UHD) videos from existing low-resolution videos. Efficient image quality assessment (IQA) methods could not only evaluate the performances of SR algorithms but also provide reliable feedback for algorithm optimization. However, only a few IQA databases and metrics have been specially designed for SR images. In this paper, we propose a database SR4KIQA containing 4K pristine images and super-resolution 4K distorted images with mean opinion score (MOS) labels. Distorted SR images are generated by five classic interpolation methods and seven typical DNN-based super-resolution algorithms. Then, a large-scale database SR4K298 owning 16688 pairs of SR distorted images is designed to support the training process of the ranking-based blind image quality assessment (BIQA) metric we proposed. SROCC of our metric Rank-SR has already reached 0.87 on the SR4KIQA database before the fine-tuning, which outperforms the state-of-art IQA metrics. As one of the very first IQA databases for 4K SR images artifacts, our database SR4KIQA has been publicly available on http://www.dx.doi.org/10.11922/sciencedb.00806 to encourage the further study of the research community. [ABSTRACT FROM AUTHOR]

Recent research on image super-resolution (SR) task has greatly progressed with the development of convolutional neural networks (CNNs). Most previous studies with single-scale feature enhance expressiveness by increasing network depth. However, most of them do not adequately extract and utilize multi-scale features. In this paper, we propose a novel residual aggregation U-shaped network (RAU), which fully utilizes multi-scale features to help reconstruct high-quality images. First, we use progressive downsampling structure to obtain multi-scale features and capture context information, and use progressive upsampling structure to fuse multi-scale features and fill detail texture. Second, we introduce auxiliary supervision in the middle layer to provide additional regularization and accelerate the convergence speed. Third, we propose a lightweight model for our network, and we replace the traditional convolution with the Ghost module in multiple locations of network. Extensive experiments on the challenge datasets confirmed the effectiveness of the proposed network. Our algorithm can restore high-quality high-resolution (HR) images and outperform other methods by a large margin. [ABSTRACT FROM AUTHOR]

Super-resolution (SR) for satellite remote sensing images has been recognized as crucial and has found widespread applications across various scenarios. Previous SR methods were usually built upon Convolutional Neural Networks and Transformers, which suffer from either limited receptive fields or a lack of prior assumptions. To address these issues, we propose ESatSR, a novel SR method based on state space models. We utilize the 2D Selective Scan to obtain an enhanced capability in modeling long-range dependencies, which contributes to a wide receptive field. A Spatial Context Interaction Module (SCIM) and an Enhanced Image Reconstruction Module (EIRM) are introduced to combine image-related prior knowledge into our model, therefore guiding the process of feature extraction and reconstruction. Tailored for remote sensing images, the interaction of multi-scale spatial context and image features is leveraged to enhance the network's capability in capturing features of small targets. Comprehensive experiments show that ESatSR demonstrates state-of-the-art performance on both OLI2MSI and RSSCN7 datasets, with the highest PSNRs of 42.11 dB and 31.42 dB, respectively. Extensive ablation studies illustrate the effectiveness of our module design. [ABSTRACT FROM AUTHOR]

Data augmentation (DA) is an effective way to improve the performance of deep networks. Unfortunately, current methods are mostly developed for high-level vision tasks (eg, image classification) and few are studied for low-level (eg, image restoration). In this paper, we provide a comprehensive analysis of the existing DAs in the frequency domain. We find that the methods that largely manipulate the spatial information can hinder the image restoration process and hurt the performance. Based on our analyses, we propose CutBlur and mixture-of-augmentation (MoA). CutBlur cuts a low-quality patch and pastes it to the corresponding high-quality image region, or vice versa. The key intuition is to provide enough DA effect while keeping the pixel distribution intact. This characteristic of CutBlur enables a model to learn not only "how" but also "where" to reconstruct an image. Eventually, the model understands "how much" to restore given pixels, which allows it to generalize better to unseen data distributions. We further improve the restoration performance by MoA that incorporates the curated list of DAs. We demonstrate the effectiveness of our methods by conducting extensive experiments on several low-level vision tasks on both single or a mixture of distortion tasks. Our results show that CutBlur and MoA consistently and significantly improve the performance especially when the model size is big and the data is collected under real-world environments. Our code is available at https://github.com/clovaai/cutblur. [ABSTRACT FROM AUTHOR]

Exploiting both local detail features and global correlation information in low-resolution (LR) images is vital for single-image super-resolution (SISR) reconstruction. Current deep CNN methods often overlook the interaction of local details while focusing on global features, rendering them incapable of accommodating both global and local features of LR images, therefore compromising the reconstruction performance. To address this, we propose a hypergraph convolution super-resolution (HCSR) network, which integrates local detail feature information and global correlation information. Hypergraph convolution is innovatively incorporated into SISR tasks, facilitating the modeling of complex spatial relationships among local features. We devise an incidence matrix for hypergraph convolution and propose a spatial feature interaction module (SFIM) for enriched local texture detail. We also use multi-hyperplane locally sensitive hash for efficient non-local hash attention (NLHA), optimally extracting correlations among global features. Based on this, a feature forward module (FFM) is developed that integrates global dependencies of multi-level features, improving the overall image detail recovery. Evaluated across five benchmark datasets, the proposed demonstrates substantial performance in both quantitative metrics and visual appeal. [ABSTRACT FROM AUTHOR]

Existing image super-resolution methods have made remarkable advancements in enhancing the visual quality of real-world images. However, when it comes to restoring Chinese paintings, these methods encounter unique challenges. This is primarily due to the difficulty in preserving intricate non-realistic details and capturing comple semantic information with high dimensionality. Moreover, the preservation of the original artwork's distinct style and subtle artistic nuances further amplifies this complexity. To address these challenges and effectively restore traditional Chinese paintings, we propose a Convolutional Super-Resolution Generative Adversarial Network for Chinese landscape painting super-resolution, termed ConvSRGAN. We employ Enhanced Adaptive Residual Module to delve deeply into multi-scale feature extraction in images, incorporating an Enhanced High-Frequency Retention Module that leverages an Adaptive Deep Convolution Block to capture fine-grained high-frequency details across multiple levels. By combining the Multi-Scale Structural Similarity loss with conventional losses, our ConvSRGAN ensures that the model produces outputs with improved fidelity to the original image's texture and structure. Experimental validation demonstrates significant qualitative and quantitative results when processing traditional paintings and murals datasets, particularly excelling in high-definition reconstruction tasks for landscape paintings. The reconstruction effect showcases enhanced visual fidelity and liveliness, thus affirming the effectiveness and applicability of our approach in cultural heritage preservation and restoration. [ABSTRACT FROM AUTHOR]

Single image super-resolution (SISR) is an important research field in computer vision, the purpose of which is to recover clear, high-resolution (HR) images from low-resolution (LR) images. With the rapid developments in deep learning theory and technology, deep learning has been introduced into the field of image super-resolution (SR), and has achieved results far beyond traditional methods in many domains. This paper summarizes current image SR algorithms based on deep learning. Firstly, the mainstream frameworks, loss functions, and datasets used for SISR are introduced in detail. Then, the SISR algorithm based on deep learning is explored using three models: a convolutional neural network (CNN), a generative adversarial network (GAN), and a transformer. Next, the evaluation indices used for SR are introduced, and the reconstruction results from various algorithms based on deep learning are compared. Finally, future trends in research on image SR algorithms based on deep learning are summarized. [ABSTRACT FROM AUTHOR]

The use of deep convolutional neural networks has significantly improved the performance of super-resolution. Employing deeper networks to enhance the non-linear mapping capability from low-resolution (LR) to high-resolution (HR) images has inadvertently weakened the information flow and disrupted long-term memory. Moreover, overly deep networks are challenging to train, thus failing to exhibit the expressive capability commensurate with their depth. High-frequency and low-frequency features in images play different roles in image super-resolution. Networks based on CNNs, which should focus more on high-frequency features, treat these two types of features equally. This results in redundant computations when processing low-frequency features and causes complex and detailed parts of the reconstructed images to appear as smooth as the background. To maintain long-term memory and focus more on the restoration of image details in networks with strong representational capabilities, we propose the Frequency-Separated Attention Network (FSANet), where dense connections ensure the full utilization of multi-level features. In the Feature Extraction Module (FEM), the use of the Res ASPP Module expands the network's receptive field without increasing its depth. To differentiate between high-frequency and low-frequency features within the network, we introduce the Feature-Separated Attention Block (FSAB). Furthermore, to enhance the quality of the restored images using heuristic features, we incorporate attention mechanisms into the Low-Frequency Attention Block (LFAB) and the High-Frequency Attention Block (HFAB) for processing low-frequency and high-frequency features, respectively. The proposed network outperforms the current state-of-the-art methods in tests on benchmark datasets. [ABSTRACT FROM AUTHOR]

Underwater image super-resolution is vital for enhancing the clarity and detail of underwater imagery, enabling improved analysis, navigation, and exploration in underwater environments where visual quality is typically degraded due to factors like water turbidity and light attenuation. In this paper, we propose an effective hybrid dynamic Transformer (called HDT-Net) for underwater image super-resolution, leveraging a collaborative exploration of both local and global information aggregation to help image restoration. Firstly, we introduce a dynamic local self-attention to adaptively capture important spatial details in degraded underwater images by employing dynamic weighting. Secondly, considering that visual transformers tend to introduce irrelevant information when modeling the global context, thereby interfering with the reconstruction of high-resolution images, we design a sparse non-local self-attention to more accurately compute self-similarity by setting a top-k threshold. Finally, we integrate these two self-attention mechanisms into the hybrid dynamic transformer module, constituting the primary feature extraction unit of our proposed method. Quantitative and qualitative analyses on benchmark datasets demonstrate that our approach achieves superior performance compared to previous CNN and Transformer models. [ABSTRACT FROM AUTHOR]

For the significant distortion problem caused by the special projection method of equi-rectangular projection (ERP) images, this paper proposes an omnidirectional image super-resolution algorithm model based on position information transformation, taking SwinIR as the base. By introducing a space position transformation module that supports deformable convolution, the image preprocessing process is optimized to reduce the distortion effects in the polar regions of the ERP image. Meanwhile, by introducing deformable convolution in the deep feature extraction process, the model's adaptability to local deformations of images is enhanced. Experimental results on publicly available datasets have shown that our method outperforms SwinIR, with an average improvement of over 0.2 dB in WS-PSNR and over 0.030 in WS-SSIM for ×4 pixel upscaling. [ABSTRACT FROM AUTHOR]

Improving visual quality is crucial as we navigate through the vast world of data. State-of-the-art (SOTA) artificial intelligence (AI) models provide highly effective solutions. Driven by the ever-growing demand for high-fidelity multimedia content, this research explores the groundbreaking capabilities of SOTA AI models to revolutionize video quality enhancement. Existing video capture methods often struggle with limitations in hardware, bandwidth, and compression, leading to subpar visual experiences. To address this challenge, we propose a novel Video Quality Enhancement Solution (VQES) that synergistically combines Google FILM for frame interpolation and Real-ESRGAN for image super-resolution. By applying these models to each video frame and integrating scalable post-processing techniques, a comprehensive VQES has been devised. Extensive experiments demonstrate that our VQES outperforms existing methods in terms of peak signal-to-noise ratio (PSNR) improvement and userperceived visual quality. By advancing video fidelity, this research paves the way for consistently immersive, informative, and enjoyable visual experiences. [ABSTRACT FROM AUTHOR]

Video Super Resolution (VSR) applications extensively utilize deep learning-based methods. Several VSR methods primarily focus on improving the fine-patterns within reconstructed video frames. It frequently overlooks the crucial aspect of keeping conformation details, particularly sharpness. Therefore, reconstructed video frames often fail to meet expectations. In this paper, we propose a Conformation Detail-Preserving Network (CDPN) named as SuperVidConform. It focuses on restoring local region features and maintaining the sharper details of video frames. The primary focus of this work is to generate the high-resolution (HR) frame from its corresponding low-resolution (LR). It consists of two parts: (i) The proposed model decomposes confirmation details from the ground-truth HR frames to provide additional information for the super-resolution process, and (ii) These video frames pass to the temporal modelling SR network to learn local region features by residual learning that connects the network intra-frame redundancies within video sequences. The proposed approach is designed and validated using VID4, SPMC, and UDM10 datasets. The experimental results show the proposed model presents an improvement of 0.43 dB (VID4), 0.78 dB (SPMC), and 0.84 dB (UDM10) in terms of PSNR. Further, the CDPN model set new standards for the performance of self-generated surveillance datasets. [ABSTRACT FROM AUTHOR]

Swin Transformers have been designed and used in various image super-resolution (SR) applications. One of the recent image restoration methods is RSTCANet, which combines Swin Transformer with Channel Attention. However, for some channels of images that may carry less useful information or noise, Channel Attention cannot automatically learn the insignificance of these channels. Instead, it tries to enhance their expression capability by adjusting the weights. It may lead to excessive focus on noise information while neglecting more essential features. In this paper, we propose a new image SR method, RSVTCANet, based on an extension of Swin2SR. Specifically, to effectively gather global information for the channel of images, we modify the Residual SwinV2 Transformer blocks in Swin2SR by introducing the coordinate attention for each two successive SwinV2 Transformer Layers (S2TL) and replacing Multi-head Self-Attention (MSA) with Efficient Multi-head Self-Attention version 2 (EMSAv2) to employ the resulting residual SwinV2 Transformer coordinate attention blocks (RSVTCABs) for feature extraction. Additionally, to improve the generalization of RSVTCANet during training, we apply an optimized RandAugment for data augmentation on the training dataset. Extensive experimental results show that RSVTCANet outperforms the recent image SR method regarding visual quality and measures such as PSNR and SSIM. [ABSTRACT FROM AUTHOR]

While the Transformer-based method has demonstrated exceptional performance in low-level visual processing tasks, it has a strong modeling ability only locally, thereby neglecting the importance of spatial feature information and high-frequency details within the channel for super-resolution. To enhance feature information and improve the visual experience, we propose a multi-attention-driven image super-resolution method based on a Transformer network, called MadFormer. Initially, the low-resolution image undergoes an initial convolution operation to extract shallow features while being fed into a residual multi-attention block incorporating channel attention, spatial attention, and self-attention mechanisms. By employing multi-head self-attention, the proposed method aims to capture global–local feature information; channel attention and spatial attention are utilized to effectively capture high-frequency features in both the channel and spatial domains. Subsequently, deep feature information is inputted into a dynamic fusion block that dynamically fuses multi-attention extracted features, facilitating the aggregation of cross-window information. Ultimately, the shallow and deep feature information is fused via convolution operations, yielding high-resolution images through high-quality reconstruction. Comprehensive quantitative and qualitative comparisons with other advanced algorithms demonstrate the substantial advantages of the proposed approach in terms of peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) for image super-resolution. [ABSTRACT FROM AUTHOR]

The method of image super-resolution reconstruction through the dictionary usually only uses a single-layer dictionary, which not only cannot extract the deep features of the image but also requires a large trained dictionary if the reconstruction effect is to be better. This paper proposes a new deep dictionary learning model. Firstly, after preprocessing the images of the training set, the dictionary is trained by the deep dictionary learning method, and the adjusted anchored neighborhood regression method is used for image super-resolution reconstruction. The proposed algorithm is compared with several classical algorithms on Set5 dataset and Set14 dataset. The visualization and quantification results show that the proposed method improves PSNR and SSIM, effectively reduces the dictionary size and saves reconstruction time compared with traditional super-resolution algorithms. [ABSTRACT FROM AUTHOR]

In addition to susceptibility to performance degradation due to hardware malfunctions and environmental influences, wireless image transmission poses risks of information exposure to eavesdroppers. This paper delves into the image communications within wireless relay networks (WRNs) and proposes a secure cooperative relaying (SCR) protocol over Rayleigh fading channels. In this protocol, a source node (referred to as Alice) transmits superior-resolution (SR) images to a destination node (referred to as Bob) with the assistance of a mediating node (referred to as Relay) operating in decode-and-forward mode, all while contending with the presence of an eavesdropper (referred to as Eve). In order to conserve transmission bandwidth, Alice firstly reduces the size of the original SR images before transmitting them to Relay and Bob. Subsequently, random linear network coding (RLNC) is employed by both Alice and Relay on the downscaled poor-resolution (PR) images to obscure the original images from Eve, thereby bolstering the security of the image communications. Simulation results demonstrate that the proposed SCR protocol surpasses both secure relaying transmission without a direct link and secure direct transmission without relaying links. Additionally, a slight reduction in image quality can be achieved by increasing the scaling factor for saving transmission bandwidth. Furthermore, the results highlight the SCR protocol’s superior effectiveness at Bob’s end when compared to Eve’s, which is due to Eve’s lack of access to the RLNC coefficient matrices and reference images utilised by Alice and Relay in the RLNC process. Finally, the evaluation of reference images, relay allocations and diversity reception over Rayleigh fading channels confirms the effectiveness of the SCR protocol for secure image communications in the WRNs.

Photoacoustic microscopy (PAM) has gained increasing popularity in biomedical imaging, providing new opportunities for tissue monitoring and characterization. With the development of deep learning techniques, convolutional neural networks have been used for PAM image resolution enhancement and denoising. However, there exist several inherent challenges for this approach. This work presents a Unified PhotoAcoustic Microscopy image reconstruction Network (UPAMNet) for both PAM image super-resolution and denoising. The proposed method takes advantage of deep image priors by incorporating three effective attention-based modules and a mixed training constraint at both pixel and perception levels. The generalization ability of the model is evaluated in details and experimental results on different PAM datasets demonstrate the superior performance of the method. Experimental results show improvements of 0.59 dB and 1.37 dB, respectively, for 1/4 and 1/16 sparse image reconstruction, and 3.9 dB for image denoising in peak signal-to-noise ratio.