Super-resolution Task Research Articles

Joint MR image reconstruction and super-resolution via mutual co-attention network

Abstract In the realm of medical diagnosis, recent strides in deep neural network-guided magnetic resonance imaging (MRI) restoration have shown promise. Nevertheless, persistent drawbacks overshadow these advancements. Challenges persist in balancing acquisition speed and image quality, while existing methods primarily focus on singular tasks like MRI reconstruction or super-resolution (SR), neglecting the interplay between these tasks. To tackle these challenges, this paper introduces the mutual co-attention network (MCAN) specifically designed to concurrently address both MRI reconstruction and SR tasks. Comprising multiple mutual cooperation attention blocks (MCABs) in succession, MCAN is tailored to maintain consistency between local physiological details and global anatomical structures. The intricately crafted MCAB includes a feature extraction block, a local attention block and a global attention block. Additionally, to ensure data fidelity without compromising acquired data, we propose the channel-wise data consistency block. Thorough experimentation on the IXI and fastMRI dataset showcases MCAN’s superiority over existing state-of-the-art methods. Both quantitative metrics and visual quality assessments validate the enhanced performance of MCAN in MRI restoration. The findings underscore MCAN’s potential in significantly advancing therapeutic applications. By mitigating the trade-off between acquisition speed and image quality while simultaneously addressing both MRI reconstruction and SR tasks, MCAN emerges as a promising solution in the domain of magnetic resonance image restoration.

Edge-Oriented Compressed Video Super-Resolution.

Due to the proliferation of video data in Internet of Things (IoT) systems, in order to reduce the data burden, most social media platforms typically employ downsampling to reduce the resolution of high-resolution (HR) videos before video coding. Consequently, the loss of detail and the introduction of additional artifacts seriously compromise the quality of experience (QoE). Recently, the task of compressive video super-resolution (CVSR) has garnered significant attention, aiming to simultaneously eliminate compression artifacts and enhance the resolution of compressed videos. In this paper, we propose an edge-oriented compressed video super-resolution network (EOCVSR), which focuses on reconstructing higher-quality details, to effectively address the CVSR task. Firstly, we devised a motion-guided alignment module (MGAM) to achieve precise bi-direction motion compensation in a multi-scale manner. Secondly, we introduced an edge-oriented recurrent block (EORB) to reconstruct edge information by combining the merits of explicit and implicit edge extraction. In addition, benefiting from the recurrent structure, the receptive field of EOCVSR can be enhanced and the features can be effectively refined without introducing additional parameters. Extensive experiments conducted on benchmark datasets demonstrate that our method surpasses the performance of state-of-the-art (SOTA) approaches in both quantitative and qualitative evaluations. Our approach can provide users with high-quality and cost-effective HR videos by integrating with sensors and codecs.

A joint learning method with consistency-aware for low-resolution facial expression recognition

Existing facial expression recognition (FER) methods are mainly devoted to learning discriminative features from high-resolution images. However, when applied to low-resolution images, their performance drops rapidly. This paper proposes a unified learning framework (namely SR-FER) by cascading the image super-resolution (SR) task and FER task to alleviate the low-resolution challenge. It effectively feeds back expression-related information from the FER network to the SR network, and returns the quality-enhanced expression images via a SR network. Specifically, a multi-stage attention-aware consistency loss module is introduced to help the SR network achieve discriminative feature restoration guided by attention information. Furthermore, a prediction consistency loss module is also developed to encourage the SR network to restore discriminative features by reducing the difference in prediction information between the restored and original normal-resolution images. Therefore, more accurate results are obtained by performing FER on the restored images. We conduct extensive experiments to demonstrate that the proposed low-resolution FER solution can help SR methods restore features favorable for FER while maintaining acceptable FER performance in various resolution degradation scenarios. The proposed method effectively improves the FER challenge under resolution degradation conditions, which is of good reference value for real-world applications.

Rapid scanning method for SICM based on autoencoder network

Scanning Ion Conductance Microscopy (SICM) enables non-destructive imaging of living cells, which makes it highly valuable in life sciences, medicine, pharmacology, and many other fields. However, because of the uncertainty retrace height of SICM hopping mode, the time resolution of SICM is relatively low, which makes the device fail to meet the demands of dynamic scanning. To address above issues, we propose a fast-scanning method for SICM based on an autoencoder network. Firstly, we cut under-sampled images into small image lists. Secondly, we feed them into a self-constructed primitive-autoencoder super-resolution network to compute high-resolution images. Finally, the inferred scanning path is determined using the computed images to reconstruct the real high-resolution scanning path. The results demonstrate that the proposed network can reconstruct higher-resolution images in various super-resolution tasks of low-resolution scanned images. Compared to existing traditional interpolation methods, the average peak signal-to-noise ratio improvement is greater than 7.5823 dB, and the average structural similarity index improvement is greater than 0.2372. At the same time, using the proposed method for high-resolution image scanning leads to a 156.25% speed improvement compared to traditional methods. It opens up possibilities for achieving high-time resolution imaging of dynamic samples in SICM and further promotes the widespread application of SICM in the future.

Remote sensing image super-resolution via cross-scale hierarchical transformer

ABSTRACT Global and local modeling is essential for image super-resolution tasks. However, current efforts often lack explicit consideration of the cross-scale knowledge in large-scale earth observation scenarios, resulting in suboptimal single-scale representations in global and local modeling. The key motivation of this work is inspired by two observations: 1) There exists hierarchical features at the local and global regions in remote sensing images, and 2) they exhibit scale variation of similar ground objects (e.g. cross-scale similarity). In light of these, this paper presents an effective method to grasp the global and local image hierarchies by systematically exploring the cross-scale correlation. Specifically, we developed a Cross-scale Self-Attention (CSA) to model the global features, which introduces an auxiliary token space to calculate cross-scale self-attention matrices, thus exploring global dependency from diverse token scales. To extract the cross-scale localities, a Cross-scale Channel Attention (CCA) is devised, where multi-scale features are explored and progressively incorporated into an enriched feature. Moreover, by hierarchically deploying CSA and CCA into transformer groups, the proposed Cross-scale Hierarchical Transformer (CHT) can effectively explore cross-scale representations in remote sensing images, leading to a favorable reconstruction performance. Comprehensive experiments and analysis on four remote sensing datasets have demonstrated the superiority of CHT in both simulated and real-world remote sensing scenes. In particular, our CHT outperforms the state-of-the-art approach (TransENet) in terms of PSNR by 0.11 dB on average, but only accounts for 54.8% of its parameters.

Underwater Image Super-Resolution via Dual-aware Integrated Network

Underwater scenes are often affected by issues such as blurred details, color distortion, and low contrast, which are primarily caused by wavelength-dependent light scattering; these factors significantly impact human visual perception. Convolutional neural networks (CNNs) have recently displayed very promising performance in underwater super-resolution (SR). However, the nature of CNN-based methods is local operations, making it difficult to reconstruct rich features. To solve these problems, we present an efficient and lightweight dual-aware integrated network (DAIN) comprising a series of dual-aware enhancement modules (DAEMs) for underwater SR tasks. In particular, DAEMs primarily consist of a multi-scale color correction block (MCCB) and a swin transformer layer (STL). These components work together to incorporate both local and global features, thereby enhancing the quality of image reconstruction. MCCBs can use multiple channels to process the different colors of underwater images to restore the uneven underwater light decay-affected real color and details of the images. The STL captures long-range dependencies and global contextual information, enabling the extraction of neglected features in underwater images. Experimental results demonstrate significant enhancements with a DAIN over conventional SR methods.

Ultralight-Weight Three-Prior Convolutional Neural Network for Single Image Super Resolution

The task of image super resolution is crucial in many applications, such as computer vision and medical imaging. Conventionally the task of image super resolution was carried out by formulating it as a constrained optimization problem and then solving it using suitable numerical techniques. However, after the emergence of deep neural networks, the focus of the researchers in this area has been almost entirely on designing deep convolutional neural network architectures that indeed have provided remarkable performance for the task of image super resolution. Even though unified methods of combining the two approaches has a greater potential of providing a superior performance for the task of image super resolution, with the exception of very few works, not much attention has been paid to develop such a unified method for this task. In this paper, we propose a three-prior formulation of the optimization problem for image super resolution and develop an ultralight-weight convolutional neural network for its solution. The effectiveness of the proposed formulation of the optimization problem and ultralight-weight convolution neural network architecture for its solution is demonstrated through extensive experimentations of the proposed scheme on benchmark datasets and comparisons of the results with that of the other state-of-the-art ultralight-weight image super resolution networks.

CTDNet: cartoon-texture decomposition-based gray image super-resolution network with multiple degradations

In the case of multiple degradations, current deep-learning-based gray image super-resolution (SR) methods equally process all components in an image, resulting in missing subtle details. To address this issue, we elaborate a cartoon-texture decomposition-based (CTD) module that can automatically decompose an image into a smooth cartoon component and an oscillatory texture component. The CTD module is a plug-and-play prior module that can be applied in solving imaging inverse problems. Specifically, for the SR task under multiple degradations, we apply CTD as a prior module to build an unfolding SR network termed CTDNet. For the SR task of real terahertz images, the boundary (i.e., the boundary between the object of interest and the carrier table) recovered by CTDNet has artifacts, which limits its realistic applications. To reduce these boundary artifacts, we post-process the SR terahertz images by using a boundary artifact reduction method. Experimental results on the synthetic dataset and real terahertz images demonstrate that the proposed algorithms can maintain subtle details and achieve comparable visual results. The code can be found at https://github.com/shibaoshun/CTDNet.

A Multi-Scale Recursive Attention Feature Fusion Network for Image Super-Resolution Reconstruction Algorithm

In recent years, deep convolutional neural networks (CNNs) have made significant progress in single-image super-resolution (SISR) tasks. Despite their good performance, the single-image super-resolution task remains a challenging one due to problems with underutilization of feature information and loss of feature details. In this paper, a multi-scale recursive attention feature fusion network (MSRAFFN) is proposed for this purpose. The network consists of three parts: a shallow feature extraction module, a multi-scale recursive attention feature fusion module, and a reconstruction module. The shallow features of the image are first extracted by the shallow feature extraction module. Then, the feature information at different scales is extracted by the multi-scale recursive attention feature fusion network block (MSRAFFB) to enhance the channel features of the network through the attention mechanism and fully fuse the feature information at different scales in order to improve the network’s performance. In addition, the image features at different levels are integrated through cross-layer connections using residual connections. Finally, in the reconstruction module, the upsampling capability of the deconvolution module is used to enlarge the image while extracting its high-frequency information in order to obtain a sharper high-resolution image and achieve a better visual effect. Through extensive experiments on a benchmark dataset, the proposed network model is shown to have better performance than other models in terms of both subjective visual effects and objective evaluation metrics.

Remote Sensing Image Super-Resolution via Multi-Scale Texture Transfer Network

As the degradation factors of remote sensing images become increasingly complex, it becomes challenging to infer the high-frequency details of remote sensing images compared to ordinary digital photographs. For super-resolution (SR) tasks, existing deep learning-based single remote sensing image SR methods tend to rely on texture information, leading to various limitations. To fill this gap, we propose a remote sensing image SR algorithm based on a multi-scale texture transfer network (MTTN). The proposed MTTN enhances the texture feature information of reconstructed images by adaptively transferring texture information according to the texture similarity of the reference image. The proposed method adopts a multi-scale texture-matching strategy, which promotes the transmission of multi-scale texture information of remote sensing images and obtains finer-texture information from more relevant semantic modules. Experimental results show that the proposed method outperforms state-of-the-art SR techniques on the Kaggle open-source remote sensing dataset from both quantitative and qualitative perspectives.

Multi-branch-feature fusion super-resolution network

Deep network attracts extensive attention in the single image super-resolution field. Most of the deep network-based super-resolution methods usually employ a feature extraction stream to generate the input for the next extraction module during extracting deep features. Whereas, many experiments show that the feature maps yielded by different feature extraction streams generally contain different but complementary detailed information. Based on this observation, we propose a multi-branch feature fusion super-resolution network termed as MBFSR to solve the single image super-resolution task. MBFSR progressively deploys multiple feature extraction modules to extract the deep feature. Specifically, the deployed feature extraction modules first generate different feature maps through three well-designed feature extraction branches, and then fuse them by the developed three-branch fusion module to generate a high-resolution feature map. Finally, the output features of all modules are directly used to generate the desired high-resolution image. Experimental results demonstrate the availability and superiority of MBFSR over other popular methods.

EDSR: Empowering super-resolution algorithms with high-quality DIV2K images

Remarkable strides have been made in Enhanced-resolution image reconstruction in recent times. In this research, we propose EDSR, a novel algorithm leveraging high-quality DIV2K images to enhance super-resolution algorithms’ performance. Our approach addresses challenges associated with capturing and reconstructing fine details and textures in low-resolution images. The training process utilizes a deep neural network fed with the extensive DIV2K dataset, comprising meticulously selected high-resolution images for super-resolution tasks. The network learns from these high-quality images to improve super-resolved outputs’ accuracy and fidelity. Extensive experimentation evaluates the effectiveness of the EDSR algorithm in achieving superior results. Experimental outcomes exhibit the remarkable progress made by EDSR compared to other leading super-resolution algorithms. The mean PSNR values obtained using EDSR on various test datasets indicate substantial improvement in image quality. The SSIM scores show enhanced preservation of fine details and textures. In the Nature category, the EDSR algorithm exhibits impressive performance, achieving a mean Peak Signal-to-Noise Ratio (PSNR) of 35.92 dB and a Structural Similarity Index (SSIM) of 0.9321. When analyzing Portrait images, the algorithm consistently maintains high quality, delivering a mean PSNR of 34.17 dB and an SSIM of 0.9125. For Cityscape images, EDSR showcases excellent capabilities with a mean PSNR of 36.05 dB and an SSIM of 0.9382, highlighting its exceptional handling in this category. Lastly, in the Still Life category, the algorithm demonstrates competence, achieving a mean PSNR of 33.79 dB and an SSIM of 0.9024. In conclusion, the proposed EDSR algorithm empowers super-resolution algorithms by leveraging high-quality DIV2K images. The empirical findings validate that EDSR is highly efficient in enhancing image quality and preserving fine details.

SwinWave-SR: Multi-scale lightweight underwater image super-resolution

The resource-limited nature of underwater vision equipment leads to poor, otherwise low-resolution information affecting the downstream underwater robotics and ocean engineering tasks. Underwater Image Enhancement (UIE) methods have emerged, particularly Super-Resolution (SR), to tackle the aforementioned challenge by restoring the corresponding low-resolution image to a high-quality counterpart. Vision Transformers (ViTs) have recently been employed for SR tasks thanks to their superior performance over mainstream convolution neural networks. The success of ViTs is largely due to their self-attention mechanism; however, they may encounter challenges in dealing with severe and unpredictable degradation in underwater imaging. In contrast, Multi-scale ViTs (MViTs) variants such as the Swin transformers have overcome that challenge by preserving long-range dependencies over multi-scale feature hierarchies through evolving channel capacity. MViTs tend to induce spatial efficiency through classical down-sampling, such as average pooling over key/values, which results in an inevitable loss of high-frequency components. To address this lack, in the current work, we propose a novel algorithm, SwinWave-SR, for efficient and accurate multi-scale SR for underwater images. Our proposed algorithm is based on Swin transformer consisting of a wavelet block to restrict the information drop by downsampling in an invertible fashion. Consequently, the key components are preserved to assist self-attention learning while reducing its computational cost simultaneously. To further complement it, we explore a prominent compression regime, namely the Lottery Ticket Hypothesis (LTH), to discover a lightweight sub-network with competitive performance to its original model by reducing computational costs up to 70.44%. Overall, SwinWave-SR improves peak signal-to-noise ratio (PSNR) by 0.95 dB ∼ 2.23 dB compared to the state-of-the-art SwinIR while reducing the number of parameters by 29.56% and the calculation cost by 18.734%. Experimental results show that the proposed SwinWave-SR method outperforms the state-of-the-art SR methods on four benchmark underwater datasets and significantly improves PSNR and structural similarity index (SSIM).

An Image Arbitrary-Scale Super-Resolution Network Using Frequency-domain Information

Image super-resolution (SR) is a technique to recover lost high-frequency information in low-resolution (LR) images. Since spatial-domain information has been widely exploited, there is a new trend to involve frequency-domain information in SR tasks. Besides, image SR is typically application-oriented and various computer vision tasks call for image arbitrary magnification. Therefore, in this article, we study image features in the frequency domain to design a novel image arbitrary-scale SR network. First, we statistically analyze LR-HR image pairs of several datasets under different scale factors and find that the high-frequency spectra of different images under different scale factors suffer from different degrees of degradation, but the valid low-frequency spectra tend to be retained within a certain distribution range. Then, based on this finding, we devise an adaptive scale-aware feature division mechanism using deep reinforcement learning, which can accurately and adaptively divide the frequency spectrum into the low-frequency part to be retained and the high-frequency one to be recovered. Finally, we design a scale-aware feature recovery module to capture and fuse multi-level features for reconstructing the high-frequency spectrum at arbitrary scale factors. Extensive experiments on public datasets show the superiority of our method compared with state-of-the-art methods.

Cross-scale collaborative network for single image super resolution

Convolution-based networks show impressive performance in Single Image Super-Resolution (SISR) task by making full use of local patterns. However, it requires deeper structure to capture the long-range dependencies which is inefficient. Hence, the Non-Local Attention (NLA) is introduced to search similar patterns globally and effectively exchange information globally. Nevertheless, the naïve NLA only exchanges information in original spatial scale and has quadratic computational complexity with spatial size of input image. Besides, the global fusion of all similar patterns may lead to blurring, which deviates from the goal of SISR to accurately recover image details. Hence, the naïve NLA is not suit for SISR. To solve this problem, we propose a novel Cross-Scale Collaborative Attention (CSCA) which is designed for SISR. Due to similar patterns tend to occur at different locations and scales, we explore self-similarity and cross-scale similarity simultaneously on multi-scale feature pyramid to utilize more rich details for improving the performance of recovery. To guarantee the recovered details are accurate, we aggregate features in each layer of pyramid into groups and only exchange information between the most relevant groups across multi-scale. Hence, CSCA is both efficient and can accurately recover details using the rich information contained in multi-scale. Furthermore, we propose a Cross-Scale Collaborative Network (CSCN) by inserting a few CSCA modules into a simple backbone network. Extensive experiments show the effectivity and efficiency of CSCA, and state-of-the-art performance of CSCN in SISR task.

SIELNet: 3-D Chaotic-Map-Based Secure Image Encryption Using Customized Residual Dense Spatial Network

The continuous development of Industry 5.0 technology has brought great convenience to people’s work and life. However, during digital data transmission and storage, the data may be accessed by unauthorized persons, resulting in privacy disclosure. Therefore, efficient data protection is always a high demand to solve this realistic problem. This work proposes a secure encryption algorithm, SIELNet, for colour images. First, we introduce a new three-dimensional chaotic map to encrypt colour images, obtaining the cipher images with a relationship to the plain images. We provide its excellent chaotic behaviour through standard randomness test. Secondly, we use a customized residual dense spatial network to perform the task of lossy image reconstruction from an encrypted, compressed image, which solves the constrained super-resolution task. Extensive experimental results on four public datasets demonstrate the superior performance of SIELNet against state-of-the-art techniques with excellent reconstruction quality. We believe the secure design of SIELNet can contribute to the favourable data integrity application of Industry 5.0.

CLSR: Cross-Layer Interaction Pyramid Super-Resolution Network

Convolutional neural network (CNN) achieves impressive success in image super-resolution (SR), where global context interaction is critical for reconstructing reliable edge and texture details. However, most CNN-based SR models focus on modeling the global contextual information within a single feature map by using attention mechanisms, and ignore the dependencies among hierarchical features, resulting in blurred or even distorted detail restoration, especially for SR tasks with large scaling factors ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">i.e</i> ., ×4, ×8). To tackle the above issue, we propose a cross-layer interaction pyramid super-resolution (CLSR) network that reconstructs the desired SR images progressively in a coarse-to-fine fashion. Specifically, we propose a novel cross-layer non-local attention (CLNL) for accurate detail restoration. Through explicitly modeling the long-range feature-wise similarities within and between layers, the proposed CLNL is able to discriminatively explore complementary patches from hierarchical features to reconstruct the target LR patches. Then, to further strengthen the information interaction among hierarchical features at different scales, we propose a novel gradient consistency-aware learning framework (GCA) by constructing a closed loop (LR→HR→LR) on the gradient space. The proposed GCA is able to effectively capture the interdependence between LR and HR gradient maps to guide our CLSR for reliable detail restoration. Extensive experiments validate that our CLSR outperforms the state-of-the-art methods in terms of both reconstruction accuracy and visual quality.

Efficient Super-Resolution System With Block-Wise Hybridization and Quantized Winograd on FPGA

Super-resolution (SR) techniques aim to restore a high-resolution image from low-resolution images, which are often used to assist the enhancement of image/video quality under the rapid development of high-resolution and high-framerate media. Recently, neural network (NN)-based methods perform much better image reconstruction quality than classical approaches. However, the unacceptable computation complexity as well as the huge memory footprints of NNs limit the throughputs and scalability of these SR systems. In this work, we analyze several key issues in the design of NN-based SR systems first. Then, we propose a three-level systematic optimization methodology for SR systems to reduce computation overhead and keep image quality. At the algorithm level, we introduce image blocking to SR tasks and develop a block-wise SR algorithm based on the hybrid of NN and interpolation with a consistent image block evaluation metric. The configurable hybrid parameters help the SR algorithm to achieve a flexible trade-off between the computation overhead and image quality. At the operator level, we focus on the transpose convolution operators commonly used for upsampling in SR neural networks. We propose an efficient Winograd-based transposed convolution acceleration method. Through the efficient sub-convolutions conversion and the Winograd specialization, this methods enables unified Winograd transformations and simplified data access patterns. At the data level, we propose a novel quantization method for Winograd-aware SR neural networks to get better quantized accuracy. Comprehensive evaluations demonstrate the effectiveness of these optimizations. Our SR system reduces a large number of multiplications with great scalability and supports 4K@120fps and 8K@30fps outputs with acceptable image quality degradation.

Investigating transformer‐based models for spatial downscaling and correcting biases of near‐surface temperature and wind‐speed forecasts

AbstractHigh‐resolution and accurate prediction of near‐surface weather parameters based on numerical weather prediction (NWP) models is essential for many downstream and real‐world applications. Traditional dynamical or statistical downscaling methods are insufficient to derive high‐resolution data from operational NWP forecasts, making it essential to devise new approaches. In recent years, an increasing number of researchers have explored the implementations of deep learning (DL) based models for spatial downscaling, motivated by the similarity between the super‐resolution (SR) problem in computer vision (CV) and downscaling. Furthermore, while transformer‐based models have become state‐of‐the‐art models for many SR tasks, they are rarely applied for downscaling of weather forecasts or climate projections. This study adapted transformer‐based models such as SwinIR and Uformer to downscale the temperature at 2 m () and wind speed at 10 m () over Eastern Inner Mongolia, encompassing the area from 39.6–46°N latitude and 111.6–118°E longitude. We used high‐resolution forecast (HRES) data from the European Centre for Medium‐range Weather Forecast (ECMWF) with a spatial resolution of 0.1° as the input and gridded observation data from the China Meteorological Administration (CMA) Land Data Assimilation System (CLDAS) at a spatial resolution of 0.01° as the target. Given that the models use observation data rather than a coarse‐grained version of forecast data as the target, they accomplish both bias correction and spatial downscaling. The results demonstrate that the performance of SwinIR and Uformer is superior to that of two convolutional neural network (CNN) based models (UNet and RCAN). Additionally, we introduced a novel module to extract features of varying resolution from the high‐resolution topography data and applied a multiscale feature fusion module to merge features of different scales, contributing to further enhancement of Uformer's performance.

A Prediction-to-Prediction Remote Sensing Image Super-Resolution Network under a Multi-Level Supervision Paradigm

Super-resolution enhances the spatial resolution of remote sensing images, yielding clearer data for diverse satellite applications. However, existing methods often lose true detail and produce pseudo-detail in reconstructed images due to an insufficient number of ground truth images for supervision. To address this issue, a prediction-to-prediction super-resolution (P2P-SR) network under a multi-level supervision paradigm was proposed. First, a multi-level supervision network structure was proposed to increase the number of supervisions by introducing more ground truth images, which made the network always predict the next level based on the super-resolution reconstruction results of the previous level. Second, a super-resolution component combining a convolutional neural network and Transformer was designed with a flexible super-resolution scale factor to facilitate the construction of multi-level supervision networks. Finally, a method of dividing the super-resolution overall scale factor was proposed, enabling an investigation into the impact of diverse numbers of components and different scale factors of components on the performance of the multi-level supervision network. Additionally, a new remote sensing dataset containing worldwide scenes was also constructed for the super-resolution task in this paper. The experiment results on three datasets demonstrated that our P2P-SR network outperformed the state-of-the-art (SOTA) methods.