1157 results about "High resolution image" patented technology

The invention discloses an intelligent defect detection system and a self-repairing method for a flexible base material RFID tag, and belongs to the technical field of Internet of Things electronic device manufacturing. According to the system, a three-dimensional dynamic scanning system is constructed by integrating a high-resolution image acquisition module, a multispectral sensor array and a mechanical arm motion platform, and surface and internal structure characteristics of a flexible substrate are captured in real time. A defect identification algorithm based on deep learning is combined with a multi-scale convolutional neural network and a transfer learning technology, precise classification of 12 types of defects such as microcracks, conductive layer fractures and base material deformation is realized, and the detection precision reaches 99.2%. A dual-mode self-repairing mechanism is put forward, specifically, nano-silver conductive colloid is injected through a microfluid channel for the defects of the conductive layer, and 3D structure reconstruction is achieved through a controllable temperature field; for substrate damage, a photoresponse shape memory polymer patch is adopted, and molecular-level bonding repair is achieved after ultraviolet light activation. According to the scheme, the detection efficiency is improved by more than 5 times, and the radio frequency performance of the tag is recovered to 98.7% of the initial value after self-repairing.

The invention discloses a medical image super-resolution reconstruction method based on multi-level attention guidance, and the method comprises the following steps: S10, constructing a deep learning network model based on a generative adversarial network architecture, which comprises a generator and a discriminator; the generator is based on an improved U-Net architecture, a hierarchical attention module and a dual-path feature processing module are configured in an encoder and a decoder of the generator, the hierarchical attention module adopts different attention strategies according to network levels to consider structure and texture, and the dual-path feature processing module separates and processes low-frequency and high-frequency information; the generator further comprises a multi-level feature fusion module for integrating the multi-scale features of the decoder, and an attention guide up-sampling module for final enhancement and dimension raising. The discriminator adopts a spectrum normalization U-Net architecture and uses multi-scale features for matching; s20, training the network model by adopting a composite loss function comprising pixels, adversarial, perception and total variation loss; and S30, inputting the low-resolution image into the trained model, and outputting a high-resolution image. According to the method, through deep fusion of multi-level attention and multi-scale feature processing, the image restoration quality can be remarkably improved, the texture detail definition can be enhanced, the anatomical structure accuracy can be ensured, and the noise robustness can be improved.

The invention discloses an urban building three-dimensional automatic modeling and visualization method, and belongs to the technical field of building three-dimensional modeling. The method comprises the steps that point cloud data, high-resolution images and geographic information system data of urban buildings are acquired, data cleaning, registration and alignment are carried out, and preliminary building digital representation is formed; accurately segmenting each building, and identifying the contour and main structural features of the building; based on the data integrity and the building complexity, adaptively selecting a proper reconstruction strategy to carry out three-dimensional reconstruction; in the reconstruction process, the geometric structure is analyzed and optimized in real time, and potential topological problems are repaired; automatically generating missing details based on a predefined architectural style library and a component library, and performing material inference and texture mapping; a graph structure is used for representing the relation between the buildings, and the positions and orientations of the buildings are adjusted through a global optimization algorithm; a rendering engine supporting multi-level detail switching is developed, and smooth visualization and interaction of a large-scale city scene are achieved.

The invention provides an image restoration and super-resolution reconstruction system and method based on deep learning, and belongs to the technical field of digital image processing. The invention aims to solve the problems of high calculation complexity and resource consumption, limitation of long sequence processing, high training difficulty and texture scene deficiency when a multi-scale residual network based on a Transform architecture is used for image resolution conversion. The reconstruction system comprises: an image preprocessing module performing window division and video memory optimization on an input low-resolution image; the multi-layer fusion network dynamically adjusts the characteristics of the low-resolution image, captures channel information in different scenes, performs interactive fusion, performs comparison supervision, establishes an information communication channel, dynamically adjusts and optimizes parameters through negative feedback, and obtains a super-resolution image. And the loss function module maximizes the similarity of the super-resolution image and the high-resolution image in the segmentation feature space to obtain a final super-resolution image.

The invention relates to the field of image comparison, and discloses a multi-layer PCB alignment deviation detection system and method based on image comparison, and the method comprises the steps: obtaining high-resolution image data before and after lamination of a multi-layer PCB, carrying out the unified registration preprocessing of an original image through the combination of a multi-mode image fusion algorithm and a geometric distortion correction technology, and obtaining a multi-layer PCB alignment deviation detection result; constructing a standardized image registration input set; key alignment feature extraction is carried out on the image registration input set, and a multilayer structure graph model is constructed based on a graph neural network; in combination with the alignment reference map, dynamically adjusting an image comparison window and a search region by adopting a region attention mechanism and a local adaptive matching algorithm, and constructing an alignment deviation mapping map; constructing a deviation evolution model by using a time sequence behavior recognition network according to the constructed alignment deviation mapping graph and historical process deviation data; and performing comprehensive evaluation on the image registration input set based on the deviation evolution model and the generated early warning information. The method has the advantage of improving the accurate detection level.

The invention discloses an industrial image anomaly detection method based on deep learning, and particularly relates to the technical field of industrial visual detection. The problems of high false alarm rate, fuzzy fine defect positioning, insufficient real-time response capability, difficulty in model increment updating and the like caused by data distribution drift in an industrial scene are solved. According to the method, robust features are extracted through a multi-scale feature fusion auto-encoder, and a dynamic memory bank is constructed to update a normal sample prototype online; a dual-path detection mechanism is adopted to cooperate with a pixel-level reconstruction error and attention weighted feature matching deviation; efficient edge reasoning is realized in combination with block parallel processing and model compiling optimization; and designing an elastic incremental learning framework to prevent disastrous forgetting. And finally, false alarms caused by environmental changes are reduced, accurate positioning of pixel-level defects is realized, millisecond-level detection requirements of high-resolution images are met, safe and efficient model online evolution is supported, and adaptability and reliability of an industrial quality inspection system are comprehensively improved.

The present application relates to the field of computer vision. Provided are a visual encoding method and apparatus, and a visual encoding model training method and apparatus, which are used for using the same visual encoding model to encode images of different resolutions, and are applied to encoding scenarios for images of more sizes. The visual encoding method comprises: first, acquiring an input image, wherein the input image may be a high-resolution image and may also be a low-resolution image; and then inputting the input image into a visual encoding model, so as to output visual encoding data, wherein the visual encoding model is used for dividing the input image into a plurality of image blocks according to positional embedding, extracting features from each image block, and outputting visual encoding data on the basis of the features of each image block and corresponding positional encoding, the positional embedding is obtained by means of adjusting initial positional embedding on the basis of the difference between the input image and a preset resolution, and the positional embedding may specifically comprise a matrix corresponding to the division of the input image

The invention relates to the technical field of metal defect detection, and discloses an aluminum alloy round aluminum rod surface defect image super-resolution method. The method comprises the following steps: acquiring a low-resolution original image sequence of surface defects of the aluminum alloy round aluminum rod, and synchronously acquiring gray value distribution at different illumination angles through a multi-channel optical sensor; constructing a dynamic degradation model according to pixel displacement of adjacent frames in the original image sequence, extracting cross-scale defect features in the original image sequence, and taking output parameters of the dynamic degradation model as spatial constraint conditions of a feature extraction network; and a high-resolution defect image is generated through the multi-stage residual error reconstruction network, the high-resolution image output by the reconstruction network is fed back to the dynamic degradation model, and the frequency domain response coefficient of the spatial fuzzy kernel function is updated to form closed-loop optimization. The identification degree of defect features is improved, and a reliable image data basis is provided for accurate detection of the surface defects of the aluminum alloy round aluminum rod.

The invention belongs to the technical field of space optical remote sensing, and relates to a high-resolution remote sensing image semantic segmentation method based on a diffusion model. The specific process is as follows: first-stage training: labeling the type of each pixel of a high-resolution remote sensing image to generate a label image, and training an auto-encoder comprising an encoder and a decoder by using the label image; in the second stage of training, on the basis of the auto-encoder, a conditional diffusion model is loaded and trained, the conditional diffusion model comprises a noise injection module, a conditional encoding module and a de-noising U-Net, and parameters of the auto-encoder are fixed during training; wherein the noise injection module adds noise to hidden variables output by the encoder, the conditional encoding module is used for performing multi-scale feature extraction on the high-resolution image, and the de-noised U-Net performs image component and noise component prediction and image reconstruction under the guidance of the multi-scale features; the decoder is used for decoding the reconstructed image; and image semantic segmentation: carrying out semantic segmentation on the high-resolution remote sensing image by using the trained network.

The invention belongs to the field of computer vision and industrial defect detection, and discloses a steel coil end face defect detection method and system based on CBAM-BiFPN and multi-loss optimization, and the method comprises the steps: image preprocessing and region extraction: extracting a steel coil end face region through OpenCV and other image processing methods; dividing the high-resolution image into a plurality of small blocks and performing data enhancement; the method comprises the following steps: constructing a YOLOv11 network based on CBAM-BiFPN, introducing a CBAM attention mechanism and BiFPN feature fusion structure, and constructing an improved YOLOv11 detection network; multi-loss function joint optimization training is carried out, and model training is carried out in combination with loss functions such as Focal Loss and WIoU; and fusion of detection results and defect reconstruction output: reconstructing original image defects of all tile image detection results in a space coordinate mapping and redundant region fusion mode, and realizing high-precision overall detection output. Compared with a traditional method, the method still has the high recognition capability in a complex background and low-contrast scene, the detection precision and stability are obviously improved, and higher industrial adaptability and practical value are achieved.

The invention discloses a coal bunker reserve real-time monitoring method integrating a laser radar and a camera. The method comprises the following steps: step 1, carrying out space-time joint calibration and hardware-level synchronization on a laser radar and a camera, and establishing a projection relationship between a point cloud and an image; 2, cooperatively collecting coal bunker data based on the calibration parameters, and obtaining a point cloud and a high-resolution image; step 3, heterogeneous preprocessing is carried out on the collected point cloud and the image, denoising, segmentation and down-sampling are carried out on the point cloud, semantic segmentation is carried out on the image, and coal and foreign matters are identified; step 4, based on image texture and point cloud coordinate coupling mapping, reconstructing a three-dimensional model with a semantic tag, projecting the point cloud to an image plane to perform feature matching so as to endow the texture, and fusing image semantic information to correct the model; and 5, dynamically calculating the volume of the coal pile by using the semantic three-dimensional model to realize real-time monitoring of reserves. The system overcomes the limitation of a single sensor, achieves the real-time and high-precision monitoring of the reserves of the coal bunker, and effectively improves the intelligent level of coal bunker management.

The invention provides a dolomite multi-scale digital core reconstruction method and device, electronic equipment and a medium, and the method comprises the steps: inputting a to-be-processed CT scanning two-dimensional slice image of a dolomite sample into a reconstruction model, and obtaining a multi-view SEM style image and view parameters; inputting the style image and the visual angle parameter into a NeRF model to obtain a three-dimensional high-resolution image; the reconstruction model is obtained based on the following steps: adjusting a CT scanning two-dimensional slice image and an SEM image of a dolomite sample according to a unified standard; inputting a CT scanning two-dimensional slice image and an SEM image which are in a unified standard into a FastGAN network for preprocessing of image enhancement and augmentation to obtain a standard simulation image; and training a generator in the CycleGAN network based on the standard simulation image to obtain a reconstruction model. The method can solve the problem that a traditional digital core technology is limited by image noise and equipment cost, and nanometer and micrometer multi-scale fusion is difficult to achieve.

The invention discloses an image super-resolution method and system based on semantic perception tokens, and relates to the technical field of computer vision, and the method comprises the steps: generating semantic confidence and grouping information through the aggregation of content perception tokens, and decoupling a basic residual error into a texture enhancement and degradation inhibition guidance graph; in combination with a static semantic constraint mask and a sparse matrix multiplication mechanism, progressive focusing of attention is realized; a diffusion time step embedding and cooperative modulator is introduced, semantic guidance information is dynamically injected into a multi-step denoising process, adaptive attention features and diffusion reconstruction features are fused, and finally a high-fidelity and high-resolution image is output. According to the method, content-adaptive high-resolution image reconstruction is realized through collaborative modulation of a sparse attention mechanism guided by semantic grouping and diffusion denoising guided by semantic decoupling.

The invention provides an image super-resolution reconstruction method based on double-domain feature fusion and implicit representation, and relates to the field of image processing and computers, and the method comprises the steps: obtaining a low-resolution remote sensing image, and carrying out the preprocessing of the low-resolution remote sensing image; performing feature extraction on the preprocessed remote sensing image through Haar discrete wavelet transform and a Transform-based pyramid structure to obtain frequency domain features and spatial domain features; performing double-domain cross attention fusion on the frequency domain features and the spatial domain features to obtain local detail features and global structure features; and through an implicit representation network, the fused local detail features and global structure features are mapped to any space coordinates, a final three-channel high-resolution image is obtained, and high-quality reconstruction of a remote sensing image of any scale is realized. According to the technical scheme of the invention, the implicit neural representation is guided to realize higher-precision image reconstruction through the cooperative expression of the frequency domain information and the spatial domain information.

The invention discloses a heterogeneous double-flow fusion method and system for diabetic retinopathy grading. The method comprises the following steps: obtaining an output result of diabetic retinopathy grading by utilizing a heterogeneous double-flow architecture; processing an input fundus image into images with different resolutions; extracting global context features from the low-resolution image by using a lightweight visual Transform model distilled by composite knowledge, and extracting local focus features from the high-resolution image by using a convolutional neural network model; performing interactive fusion on the global context features and the local focus features of the double-branch architecture through a symmetric bidirectional cross attention fusion module to obtain enhanced fusion feature representation; and finally, inputting the fusion features into a classifier, and outputting a severity grading result of the lesion. The method aims at improving the accuracy and robustness of hierarchical diagnosis through deep analysis of global information and local details, and can be applied to the medical fields of clinical computer-aided diagnosis, eye image analysis and the like.

Methods, systems, and apparatuses, including computer programs encoded on computer storage media, for training a denoising neural network and, once the denoising neural network is trained, generating new images using the denoising neural network. In particular, the described techniques include obtaining data specifying a trained initial denoising neural network, obtaining training data, and training, using the training data and on a denoising objective, a target denoising neural network. The target denoising neural network includes the core-subnetwork of the trained initial denoising neural network, but also includes a target encoder and decoder neural networks that are not included in the trained initial denoising neural network. By training a target neural network that includes the core-subnetwork of a trained initial denoising neural network, the system achieves stable training of a large-scale target denoising neural networks that can be used to generate high resolution images.

The invention discloses an image enhancement method and system based on semantic constraint degradation modeling. The method comprises the steps that semantic masks and multi-scale degradation features are extracted based on a low-resolution image used for training; performing deep fusion on the extracted semantic masks and the multi-scale degradation features based on a double-flow parallel architecture to generate semantic-structure fusion features; forming a multi-modal guide condition, taking the multi-modal guide condition and the semantic-structure fusion feature as input together, and reconstructing a high-resolution prediction image through a diffusion generation model; constructing a structure consistency optimization total loss based on the high-resolution prediction image and the corresponding target image, and optimizing a diffusion generation model based on the structure consistency optimization total loss; and inputting a low-resolution image to be predicted into the optimized diffusion generation model to obtain a high-resolution image corresponding to the low-resolution image. According to the scheme of the invention, comprehensive and refined understanding of low-resolution images is realized through multi-module cooperation and deep fusion.

The invention discloses an efficient image super-resolution reconstruction method and system based on degradation region guidance, and the method comprises the following steps: S1, carrying out the region-level degradation type recognition and severity quantification of an input low-resolution image, and generating a global degradation distribution map with spatial consistency; s2, according to the global degradation distribution map and in combination with semantic-texture collaborative features, repairing a region which is judged to be seriously degraded by adopting a high-capacity branch, and repairing a region which is judged to be slightly degraded by adopting a light-weight branch; s3, fusing the output of the high-capacity branch, the output of the lightweight branch and the global detail enhanced image to generate a final high-resolution image; wherein the global detail enhanced image is obtained by enhancing the semantic-texture collaborative features.

The invention discloses a single image super-resolution reconstruction method and system based on wavelet transform and cross-domain feature fusion. According to the method, firstly, a low-resolution RGB image is mapped to a high-dimensional feature space through a shallow feature extraction module; performing up-sampling and discrete wavelet decomposition on the features by using a wavelet feature mixing module to obtain multi-band features; low-frequency and high-frequency depth features are respectively extracted through a double-branch structure, cross-domain fusion is realized by means of a deformable cross attention mechanism, and the feature expression ability is enhanced in combination with residual connection; and finally, reconstructing a high-resolution image through convolution, up-sampling and regularization processing. In the training process, a pixel-level loss function is adopted to optimize network parameters, the multi-frequency-domain feature sensitivity is effectively improved, texture and structure information is balanced, the image contrast, definition and structural integrity are improved, and high-quality real-time super-resolution reconstruction can be achieved.

The invention discloses an image super-resolution reconstruction method based on fusion of a residual pyramid and a frequency spectrum. The method comprises the following steps: 1, cutting a data set to obtain an image block training data set; 2, according to the image block training set, an image super-resolution reconstruction model based on residual pyramid and spectrum fusion is constructed, and a high-resolution image is synthesized; 3, after setting hyper-parameters, a loss function, an optimizer and the number of iterations of the image super-resolution reconstruction model based on residual pyramid and spectrum fusion, training the model to obtain a trained lightweight image super-resolution model; and 4, inputting a low-resolution image to be reconstructed into the trained lightweight image super-resolution model to obtain a high-resolution image. According to the method, the image reconstruction precision is remarkably improved, the multi-scale information modeling capability is enhanced, and the cooperative enhancement of the frequency domain and the space domain is realized, so that the image reconstruction is better carried out while the model parameter quantity is reduced.

The invention belongs to the field of computer vision, and particularly relates to a high-fidelity image style migration method based on a potential diffusion model. According to the migration method, image style migration is carried out by introducing the diffusion model, the detail fidelity and style consistency of style migration can be effectively improved, and meanwhile the common problems of style distortion and detail loss in an existing method are solved. Compared with a traditional method, the method has the following innovation points that the calculation bottleneck of a high-dimensional pixel space is avoided by carrying out style migration in a potential space, and details of the image can be effectively reserved while the style consistency is kept; by means of the gradual denoising process of the diffusion model, the style and details of the image can be gradually optimized in each stage of style migration, and excessive stylization or loss of details is avoided; modeling is carried out in the potential space, the calculation efficiency is remarkably improved, and the method is suitable for a real-time style migration task of a high-resolution image.

The invention discloses a high-resolution image semantic segmentation network for underwater scene design. A high-resolution image semantic segmentation network for an underwater scene is provided based on HRNetV2. The core of the method comprises: a WDCM feature extraction module for enhancing the anti-noise capability by using wavelet transform convolution, inhibiting irrelevant features by dynamic gating, and improving the performance of a complex scene in combination with an RCA module; a multi-scale slice segmentation head is adopted, global and local features are fused, and key information is dynamically selected; and 3) proposing a sliding combination loss function, and optimizing target boundary semantic information on the basis of variable weight focus (Focal) loss and dice (dice) loss. The target boundary segmentation precision is effectively improved, and the segmentation performance in a complex scene is improved.

The invention provides a scene text image super-resolution method based on mixed prior. The method comprises a hybrid prior extraction module (HPE), a degradation perception branch utilizes a constraint enhancement mechanism to capture a structure degradation mode specific to a text image, and a semantic text branch utilizes cross-modal fusion to align semantic and visual features; the feature fusion module (MFM) is used for fusing image features and prior knowledge; according to the knowledge distillation strategy, the teacher network extracts rich structure and semantic features from a high-resolution image, and the student network predicts fine-grained feature representation through hierarchical constraint learning. According to the method, the problem of low utilization efficiency of structure and semantic information in the super-resolution process is solved. Wide experiments on a TextZoom data set, a real world data set and four identification benchmark test data sets show that the super-divided text image has clearer textures and structures, and the objective indexes of the method are superior to those of most existing methods.

The invention discloses a yarn weak twist and hairiness intelligent detection system based on visual stroboscopic synchronization, particularly relates to the field of quality control in the textile industry, is used for solving the problem of accurate detection of weak twist and hairiness defects in the yarn production process, and dynamically adjusts the flash frequency of a stroboscope according to the real-time speed and acceleration data of yarn, so that the detection accuracy is improved. The light source and the yarn are ensured to move synchronously, and a high-resolution image is obtained. In combination with yarn motion spectrum analysis and image quality evaluation, a complexity score and a matching degree score are generated and are used for dynamically regulating and controlling image noise reduction and edge detection parameters, and characteristic extraction requirements under different yarn motion conditions are met. The weak twist characteristic and the hairiness texture of the yarn are accurately extracted through a multi-scale edge detection and wavelet transform algorithm, a twist distribution model is constructed, the boundary range is corrected in combination with hairiness distribution data, characteristic interference is reduced, and the detection precision and reliability are improved.

The invention discloses a vertical rail scanning remote sensing satellite natural multi-coverage image resolution improving method and system, and relates to the field of remote sensing image processing. The method solves the problems that due to the fact that the distance between an existing vertical rail scanning imaging sensor and a ground target is increased, image pixels cover a wider ground range, the actually-measured spatial resolution is reduced, and fine detection and recognition of ships, aircrafts and the ground target cannot be supported. SIFT feature point extraction is carried out, and feature points extracted from different images are matched by using a Euclidean nearest distance matching strategy; taking one registered image as a reference, and constructing an initial high-resolution image through up-sampling; establishing an imaging degradation model from a high-resolution image to a low-resolution observation image; calculating a residual image of the simulation image and the real observation image; and back-projecting the residual error back to the high-resolution image space, and updating high-resolution image estimation.

The invention discloses a die casting burr detection system and method based on machine vision, and relates to the field of machine vision detection.The method comprises the steps that based on a spectral feature vector set, a curved surface self-adaptive optical compensation mechanism is used, a polarization-spectral image set is obtained again through light path optimization, and the optimized polarization-spectral image set is obtained and corrected; generating a high-resolution image set, performing illumination distribution analysis on the surface of the die casting through the high-resolution image set to form a multi-exposure image set, inputting the multi-exposure image set into the constructed U-Net model for semantic segmentation, generating a high-dynamic-range image, and performing shadow elimination on the high-dynamic-range image by applying a gradient Poisson fusion algorithm to obtain a high-dynamic-range image. And after the shadow is eliminated, a pre-trained Mask-R-CNN model is used for detection, and a burr detection result is output. According to the method, the polarization-spectrum image set is optimized through curved surface adaptive optics, and imaging optimization and geometric correction of a complex curved surface area are achieved.

The invention discloses a fan blade surface image acquisition system and acquisition method based on a galvanometer. The wide-angle camera is right opposite to a fan blade, the galvanometer control module is arranged right below the wide-angle camera, the high-magnification camera is arranged on the side of the galvanometer control module in the mode of facing the galvanometer control module, and the optical axis of the high-magnification camera is perpendicular to the optical axis of the wide-angle camera. The wide-angle camera and the high-magnification camera are respectively used for shooting a global surface image and a local surface image of the fan blade, and the wide-angle camera, the high-magnification camera and the galvanometer control module are electrically connected with the image processor. The variable-view camera module is constructed through the two cameras, synchronous acquisition of high-resolution image information of the surface of the fan blade under the large view is realized by combining the two-dimensional galvanometer, the problems of unclear imaging of the blade image, low acquisition efficiency and the like are solved, the health state monitoring and defect repairing of the blade in a wind power project are realized, and the method is suitable for popularization and application. The method has important theoretical significance and application value.

The invention discloses a semi-rigid asphalt pavement crack depth estimation method, equipment and a medium, and relates to the technical field of road detection. The method comprises the steps of collecting a high-resolution image of a road surface through a mobile detection platform, segmenting a crack region in the high-resolution image by adopting an image segmentation model, and obtaining a binary image of a crack; pixel accumulation, edge detection, skeletonization, skeleton trimming and orthogonal projection are carried out on the crack binary image to extract surface parameters of the crack, and the surface parameters comprise the type, the length, the width and the area; inputting the fracture surface parameters into the fracture depth prediction model, and outputting a fracture depth prediction value; and generating a crack depth grade label according to the depth predicted value, and outputting a corresponding maintenance strategy. According to the method, the crack surface parameters and the pavement structure parameters are combined, the prediction result has good accuracy and consistency through the coupling relation with the depth index, and the method adapts to different crack types and working conditions.

The invention belongs to the technical field of image super-resolution, and particularly relates to an image super-resolution reconstruction method based on channel perception aggregation Transform. The method comprises the following steps: performing shallow feature extraction on a low-resolution image to obtain a shallow feature map; the shallow feature map is input into a deep feature extraction module for deep feature extraction to obtain a deep feature map, the deep feature extraction module comprises a plurality of residual groups, and each residual group at least comprises a dual-aggregation interactive attention and a hierarchical slice attention; carrying out convolution operation and sub-pixel recombination on the deep feature map to realize preliminary recovery of a high-resolution image; and carrying out superposition fusion on global residual information extracted after global up-sampling on the preliminarily recovered high-resolution image and the original low-resolution image to generate a high-resolution reconstructed image. According to the invention, through multi-scale and multi-path feature interaction, the image detail reduction capability of the model is enhanced.