892 results about "Image restoration" patented technology

The invention belongs to the technical field of digital restoration of computer vision and cultural heritage, and particularly relates to a traditional picture restoration method fusing low-resolution prior and efficient visual selection, which comprises the following steps: constructing a multi-source image data set, taking images in the multi-source image data set as high-resolution images, preprocessing the high-resolution images to obtain low-resolution images, and carrying out high-resolution priori and high-efficiency visual selection on the low-resolution images. The high-resolution image and the low-resolution image are respectively masked to generate simulated damage mask images, and the simulated damage mask images comprise a regular damage mask image and an irregular damage mask image; taking the multi-source image data set and the preprocessed multi-source image data set as training data, and training a multi-source image model; the dual-stage repair network comprises a coarse repair network and a fine repair network; according to the method, the problems of structural semantic loss, high priori information dependency and insufficient global and local coordination when an existing image restoration method is used for processing a complex scene and a large-range missing region are solved.

The invention discloses a bad weather image restoration method based on a multi-modal state space model, and belongs to the technical field of computer vision. In order to solve the problem that an existing unified bad weather image restoration method has limitations in the aspects of global receptive field and computational efficiency, the unified restoration of various bad weather images is realized by designing a parallel multi-mode encoder and an adapter to generate comprehensive prompts containing degeneration semantics. Through parallel connection of a state space module and a local context sensing module of a double-attention mechanism, simultaneous capture of global long-range dependence and local detailed features is realized. Experiments show that the method is high in generalization ability, high in processing speed and low in calculation complexity, and can show good adaptive capacity on a plurality of bad weather image removal tasks.

The invention discloses an image restoration method, an image restoration device and a storage medium, which are used for improving the structure restoration precision and the detail restoration capability of image restoration. The method comprises the following steps: acquiring multi-dimensional inertial data in real time; performing frequency domain analysis on the multi-dimensional inertial data by adopting sliding window short-time Fourier transform to obtain vibration intensity; if the vibration intensity does not exceed the preset threshold value, acquiring an image; calculating a definition index of the image; determining whether the image is a blurred image according to a preset definition standard and the definition index of the image; if the image is judged to be a blurred image, dividing the blurred image into a motion blurred image and a focusing blurred image; respectively constructing point spread function models of the motion blurred image and the focusing blurred image; performing deconvolution processing or depth reconstruction on the blurred image through a point spread function model to obtain a clear image; and recalculating the definition index of the clear image, and if the definition index does not exceed the definition threshold, triggering reacquisition or switching the repair model to execute secondary repair.

The invention discloses a plateau mountain road disaster identification method and system based on multi-source remote sensing image restoration and super-resolution reconstruction. The method comprises the following steps: acquiring and preprocessing a multi-source remote sensing image of a plateau mountain region, and extracting landform measurement parameters based on a digital elevation model; a super-resolution reconstruction network fusing deformable convolution and Transform is constructed, and a low-resolution image is reconstructed by using constraint training of a composite loss function containing geomorphic measurement parameters; performing feature extraction and adaptive weighted fusion on the preprocessed image and the reconstructed high-resolution image; based on the fused image, utilizing a multi-task deep learning model to identify landslide, debris flow and roadbed subsidence disasters along the highway; and carrying out morphological optimization and boundary refinement under GIS constraint on an identification result, and outputting a disaster thematic map. According to the invention, the precision and reliability of road disaster identification in a complex terrain environment are effectively improved.

The invention discloses a bronze ware ornamentation and pattern digital restoration method based on an image enhancement technology, and relates to the technical field of image restoration, and the method comprises the steps: building a space mapping matrix; extracting multi-modal data features by using the surface state of the topological insulator, and registering a joint data volume; forming a super-resolution image through super-resolution reconstruction; obtaining a material degradation coefficient by using a wavelet finite element method and a graph neural network; generating an adversarial network by utilizing physical constraints, and generating an embarrassment repairing result; a material sensing three-dimensional model is constructed by adopting a wavelet packet decomposition and neural radiation field fusion technology, texture mapping is dynamically adjusted based on a graphene Moire effect, and virtual-real fusion is performed through holographic waveguide AR; by combining advanced technologies such as a metamaterial lens, micro-distance laser scanning, a topological insulator film, a graphene heterojunction and a nerve radiation field, high-precision three-dimensional digital restoration and repair of bronze cultural relics are realized, and immersive augmented reality display experience is provided.

The invention discloses a lightweight super-resolution reconstruction method based on multi-scale feature extraction and parallel cavity coordinate attention. The lightweight super-resolution reconstruction method comprises the following steps: constructing a shallow feature extraction sub-network for remote sensing image super-resolution reconstruction; constructing a deep feature extraction sub-network for remote sensing image super-resolution reconstruction; constructing an image restoration and reconstruction self-sub-network for remote sensing image super-resolution reconstruction; constructing a remote sensing image super-resolution reconstruction network; generating a training set, a verification set and a test set; training a remote sensing image super-resolution reconstruction network; reconstructing remote sensing image resolution; according to the method, multi-scale feature extraction, a parallel cavity coordinate attention mechanism and depth separable convolution are combined, so that the effect and the quality of super-resolution reconstruction are improved while relatively low calculation cost is kept; the problems of detail loss, high calculation complexity, insufficient utilization of multi-scale features and the like when complex textures and high-frequency details are processed in an existing reconstruction technology are solved.

The present invention relates to the technical field of image restoration, and in particular to a remote-sensing hyperspectral image super-resolution reconstruction method based on a hypergraph neural network, comprising: S1, acquiring a hyperspectral image, and preprocessing the hyperspectral image to obtain a training set and a verification set; S2, constructing a hypergraph neural network; S3, using training images in the training set to construct a three-layer hypergraph, and on the basis of the three-layer hypergraph, constructing hypergraph operators corresponding to the training images; S4, using the training images and the hypergraph operators corresponding to the training images to train the hypergraph neural network, and using a loss function to iterate network parameters of the hypergraph neural network, to obtain a trained hypergraph neural network; and S5, inputting, to the trained hypergraph neural network, low-resolution hyperspectral images to be reconstructed for reconstruction to obtain a high-resolution hyperspectral image. The present invention has an excellent reconstruction result.

The invention relates to the technical field of computer vision and artificial intelligence, in particular to an image restoration method based on automatic evaluation and dynamic optimization and related equipment. The method comprises the following steps: acquiring a to-be-restored image and a corresponding restoration area; performing restoration processing on the to-be-restored image to generate an initial restoration result; performing automatic quality evaluation on the initial repair result by using a multi-modal large model in combination with an anomaly detection rule base to obtain an evaluation result; based on the evaluation result, if it is judged that the repair quality does not reach the standard, an intelligent adjustment tool chain is called to carry out targeted optimization on the initial repair result, and an optimized repair result is generated; and repeatedly executing the quality evaluation and optimization steps on the optimized repair result until the repair quality reaches the standard, and forming a closed-loop processing flow. The method has the effects of improving the restoration quality in a complex scene in an image restoration technology, improving the image restoration efficiency and increasing an automatic closed-loop processing mechanism.

Disclosed in the present invention is a facial-image restoration method based on a state space model. The method comprises: inputting into a restoration model a facial image to be restored, so as to obtain a restored facial image, wherein the restoration model comprises an encoder and a decoder, the encoder sequentially comprising a first image fusion module, a first multi-scale state space module, a second image fusion module, a second multi-scale state space module, a third image fusion module and a third multi-scale state space module, and the decoder sequentially comprising a fourth multi-scale state space module, a first multi-scale attention fusion module, a fifth multi-scale state space module, a second multi-scale attention fusion module, a sixth multi-scale state space module and a third multi-scale attention fusion module. The method restores details and textures while ensuring the consistency of facial semantic information, and can achieve a better restoration effect particularly for a low-quality facial image in a real degradation scenario.

The invention discloses an ancient textile image restoration system based on artificial intelligence. The system comprises a multi-source image acquisition module, a damaged area detection module, a pattern generation module, a color restoration module, a texture synthesis module and a multi-scale fusion module. The system introduces a wavelet guidance-frequency domain attention mechanism and a rotation invariant Haar wavelet basis function to realize accurate identification and classification of a damaged area; a saliency-guided wavelet decomposition control and self-adaptive threshold denoising method is combined, so that the perception capability of slant textures and edge details is improved; the texture synthesis module constructs a hierarchical modeling strategy fusing Gram style loss, Wasserstein style loss and a total variation regular term, and realizes generation of high-quality textures with unified styles and smooth edges; the system can be widely applied to cultural relic digital repair and display scenes.

The invention provides a coral reef remote sensing image multi-modal feature generation and restoration method and system, and relates to the technical field of remote sensing image restoration, and the method comprises the steps: obtaining coral reef image data based on a multi-source sensor, and carrying out the preprocessing; performing image morphological feature and spectral feature extraction on the preprocessed coral reef image data by using a convolutional neural network, and establishing a feature database; carrying out weighted fusion on the multi-source features based on a feature combination network, generating comprehensive feature expressions, and storing the comprehensive feature expressions into a feature database; the coral reef image to be restored is matched with the feature database, and guidance parameters are generated; and inputting the guidance parameters into the generative adversarial network, and performing pixel-level reconstruction on the missing region of the coral reef image to be restored. According to the method, a complete closed-loop system is constructed, multi-source information scheduling, pixel-level guide reconstruction and semantic feedback verification are covered, image information can be supplemented, ecological information can be reasonably reconstructed, and a high-quality data basis is provided for subsequent classification, monitoring and protection work.

The embodiment of the invention provides an image generation method, an image generation device, electronic equipment and a storage medium, and belongs to the technical field of image processing. The method comprises the following steps: acquiring an image generation prompt word and carrying out style understanding according to the image generation prompt word to obtain a scene style feature; performing scene expansion on the image generation prompt word according to the scene style feature to obtain a scene expansion word; performing scene arrangement according to the scene expansion word to obtain scene features; performing information fusion according to the scene style features, the scene expanding words and the scene features to obtain scene description information; performing image generation according to the scene description information to obtain a preliminary image; and performing image restoration according to the initial image and the scene description information to obtain a target image. The image generation method and device can be applied to business systems needing a large number, such as financial science and technology and medical health care, and the image generation efficiency and precision can be improved.

The invention provides an image restoration and generation method based on a conditional generative adversarial network, and the method comprises the steps: a camera APP obtains contour key point data of a user figure proportion through carrying out the high-resolution feature extraction of an input image, carries out the three-dimensional reconstruction of a waist line and a shoulder breadth size, and obtains a contour key point data of a user figure proportion; generating an initial feature mapping graph containing wrinkle density distribution and local deformation amplitude; according to the initial feature mapping graph, adopting a region segmentation technology to separate a body contour from a clothing region, extracting a texture stretching degree and contact point stress distribution, determining a distribution condition of clothing and body contact points, and generating a segmentation result for dynamic adjustment; and for the to-be-optimized detail area list, performing enhancement processing on the texture stretching degree of the contact points of the clothes and the body and the stress distribution of the contact points, obtaining wrinkle layer depth data of a local area, and generating an optimized image layer.

The invention discloses a three-dimensional scene generation method based on a diffusion model and Gaussian splashing and related equipment, and belongs to the field of computer vision. The method comprises a point cloud construction stage and a three-dimensional Gaussian optimization stage: in the point cloud construction stage, extracting an initial point cloud from an input initial image, and expanding the point cloud through a Stable Diffusion image restoration model, a monocular depth estimation model and a boundary perception depth alignment module to create a scene; in the three-dimensional Gaussian optimization stage, three-dimensional Gaussian is initialized according to the obtained point cloud, the three-dimensional Gaussian is utilized to represent the whole scene, a multi-view image is adopted as a supervision signal to optimize parameters of the three-dimensional Gaussian, and a three-dimensional scene capable of being browsed in an immersive mode is obtained after optimization. According to the method, the high-fidelity three-dimensional scene with accurate geometry and natural appearance can be generated without training any three-dimensional data, the problem of dependence on three-dimensional scene data is solved, the requirement for computing power resources is small, and the manufacturing cost of the three-dimensional scene is reduced.

The invention provides a blind person face image restoration method and apparatus, an electronic device and a storage medium. The method comprises the steps of obtaining a to-be-restored image of a blind person face; inputting the to-be-restored image into the image restoration model to obtain a target restoration image output by the image restoration model; wherein the image restoration model comprises a degradation prediction network, a text prompt module, a visual prompt module and a decoding module; according to the method, a degradation prediction network can effectively evaluate the degradation degree of an input to-be-restored image and provide a corresponding degradation probability weight so as to enhance the prompt generation capability of a subsequent task; moreover, the introduction of the degradation prediction network improves the adaptability of the image restoration model, and enables the model to adjust a prompt strategy according to the degradation degree, thereby optimizing the final image restoration effect of the face of the blind person, and improving the fidelity of image restoration.

The invention discloses an optical imaging system tolerance correction method and device based on a neural network, and the method comprises the steps: building an optical imaging system degradation model under an assembly tolerance condition on the basis of considering a plurality of assembly working conditions; the optical imaging system degradation model is used for simulating the spatial change degradation process of the optical system under different assembly working conditions and generating a data set, each sample is an image pair composed of a clear image and a degraded image of a target, and the degraded image is marked with a working condition label; building a neural network model comprising a working condition estimation module and an image restoration module; and training the neural network model based on the data set and a preset loss function to obtain a trained working condition estimation-image restoration model which is used for restoring a clear image from the degraded image to be detected. The problem of imaging quality nonlinear degradation caused by eccentricity and inclination of the optical element in the assembling process is solved from the imaging end, the influence of assembling tolerance can be restrained, and the imaging quality is effectively improved.

The invention discloses a multi-degraded image recovery method based on frequency domain decomposition, and aims to solve the problems that a single model is difficult to deal with various image degradation and recovery processes of different frequency domains are mutually coupled in the prior art. According to the method, a degraded image is decomposed into a high-frequency space and a low-frequency space through fast Fourier transform, and a double-branch network architecture is adopted for targeted processing: for the high-frequency part, a high-frequency feature adaptive processing module HFPM is designed, and detail texture features are effectively extracted and interference is suppressed through feature enhancement and cross-layer fusion technologies; and for the low-frequency part, constructing a low-frequency feature conversion enhancement module LTEM, and capturing global context information by using cyclic convolution to improve the integrity of the structure contour. According to the method, decoupling processing of frequency domain features is realized, and the image restoration performance of the model in various degradation scenes such as rain removal, noise removal and defogging is remarkably improved through the synergistic effect of high-frequency detail enhancement and low-frequency structure optimization. Experimental results show that the method has excellent recovery effect and robustness when a plurality of image degradation tasks are processed at the same time, and can be effectively applied to visual tasks such as traffic accidents with high image quality requirements.

The invention discloses an infrared-guided image restoration method under interference of a non-uniform scattering medium. The infrared-guided image restoration method comprises the following steps: (1) constructing a progressive guide aggregation module; (2) designing a differential amplification attention module; (3) constructing a structure guide enhancement module; and (4) designing physical coupling loss. Aiming at the problems of non-uniform distribution of interference areas and image feature redundancy, infrared image structure information and visible light texture expression capability are effectively combined, and multi-modal complementary information and physical priori knowledge are combined, so that self-adaptive enhancement and fine structure restoration of the visible light image under the interference of the non-uniform scattering medium are realized. The method provided by the invention is excellent in performance on a non-uniform interference data set, effectively relieves the problems of structure loss, color cast, modal redundancy and the like, provides a high-robustness solution for image enhancement in complex environments such as dust, sand dust, water mist and the like, and provides a new direction for research of an infrared guide image restoration method.

The invention belongs to the field of cultural heritage digital protection, and discloses an ancient building three-dimensional modeling method based on three-dimensional laser scanning, which comprises the steps of extracting feature points of a point cloud data set and texture image data, and performing registration in combination with a flight log of an unmanned aerial vehicle; performing image restoration and feature extraction on the texture image data and the point cloud-image registration result through a convolutional neural network-probability Markov random field (CNN-PMRF) model; performing geometric feature extraction on the point cloud data set, fusing the texture image feature vector to obtain a geometric-texture joint feature vector, and optimizing a rough mesh model generated based on the point cloud data set; mapping the repaired texture image data to the optimized grid model to obtain a preliminary three-dimensional grid model; and processing the preliminary model parameters through a gradient boosting decision tree (GBDT) model to obtain a correction value, and adjusting the preliminary three-dimensional grid model based on the correction value to obtain an optimal three-dimensional model. The precision of three-dimensional modeling of the ancient building can be improved.

The invention discloses an end-to-end defogging network fusing Mama and multi-scale context enhancement, and belongs to the technical field of computer vision and image restoration. The existing defogging technology has the problems of complex global modeling calculation, poor local detail recovery and insufficient feature fusion self-adaption. The problem is solved through the design of four core structures: 1, a Mamba state space model is introduced, and global fog long-range dependence modeling is realized with linear complexity; 2, designing a multi-scale cavity convolution module and a local context enhancement unit, and covering multi-scale local features; 3, constructing an enhanced adaptive fusion module to realize dynamic adaptation of global and local features; and 4, gradually recovering details by adopting a multi-scale input-cross-scale fusion-multi-scale output framework. The network can efficiently process high-resolution fog-containing images, and is suitable for scenes needing real-time high-precision defogging, such as automatic driving, security and protection monitoring, remote sensing imaging and the like.

The invention discloses a super-lens image restoration method based on fuzzy prior and semantic segmentation. The method comprises the following steps: eliminating an image visual angle displacement error by adopting a feature point automatic registration algorithm; the method comprises the following steps: designing a parallel multi-scale convolution adapter on the basis of an encoder optimized by a pre-trained visual Transform model, and generating encoding features adaptive to the degradation characteristics of a super lens; splicing the degraded image and the semantic segmentation mask into a joint tensor along a channel dimension, and obtaining a prior feature based on a fuzzy prior extraction network; performing spatial feature enhancement on the semantic segmentation mask based on a semantic segmentation graph convolutional network to obtain graph features aligned with the coding features; splicing the coding features, the prior features and the image features along channel dimensions to generate fusion features, and finally outputting a preliminary recovery image; and optimizing the whole model by adopting a staged training strategy, and finally outputting a high-quality recovery graph. According to the method, the physical rationality and detail fidelity of the recovery quality are improved.

The invention discloses a multi-degraded image restoration method based on semantic guidance. According to the method, for degraded images captured by a vehicle-mounted camera under severe weather conditions, potential features of the images are extracted by adopting a trunk network based on Transform, multi-modal semantic information is extracted in combination with a CLIP visual language model, and semantic guidance is provided for different degradation types through a dynamic text prompt generation mechanism. A self-adaptive feature fusion module is designed, channel attention and space attention mechanisms are combined to realize effective integration of multi-modal features, and a degradation feature extraction and fusion module is introduced to enhance the generalization ability of the model. According to the semantic guidance multi-type image recovery network SGIRN provided by the invention, the global modeling capability of the Transform and the cross-modal representation capability of the CLIP visual language model are combined, so that high-quality recovery of various weather degradation types is realized.

The invention discloses a texture perception state space modeling method for an image restoration task, and the method comprises the steps: 1, constructing a region selection mechanism based on texture complexity, and enabling the region selection mechanism to be used for distinguishing a flat region and a high-texture region in an image; 2, introducing a texture modulation mechanism, and performing explicit adjustment on a state transition matrix in the state space model; 3, enhancing the context modeling capability of the model through a multi-direction sensing module; and 4, by combining position embedding and a sequence modeling structure, the capability of the model in the aspects of image structure understanding and spatial information maintenance is improved. The method can effectively alleviate the problem of information loss when a traditional image restoration method processes texture details, improves the structure restoration capability of a complex region, gives consideration to the restoration quality and the calculation efficiency, is suitable for multiple image restoration scenes such as image super-resolution, image rain removal, low-light image enhancement and the like, and improves the image restoration efficiency. And the method has good engineering adaptability and actual deployment value.

According to an embodiment, an electronic device obtains an input image of a first resolution that includes one or more characters. The electronic device, using the input image, performs training of an image restoration model including a sub model trained to output a text probability map representing the one or more characters associated with the input image, an encoder configured to extract feature information from the input image, a fusion layer configured to combine the text probability map and the feature information, and a decoder connected to the fusion layer and for generating an output image with a second resolution higher than the first resolution. The sub model is trained through one or more masked attention scores obtained by applying a specified masking ratio for a different single character selected among the one or more characters.

The invention discloses a visible light-infrared image restoration fusion method based on a hybrid expert model, and aims at the characteristics that a visible light image is susceptible to noise, haze and blurring, and an infrared image is susceptible to stripe noise, the invention provides an image restoration fusion model based on a hybrid expert mechanism. The model adopts a two-stage cooperative processing architecture: in the first stage, a degradation perception gating mechanism and a multi-expert cooperative module are used for guiding a Transform module to realize high-quality restoration of a bimodal image, and restoration features are extracted; in the second stage, network parameters in the first stage are multiplexed and frozen, and image fusion is realized through a feature pre-fusion technology and a fusion perception gating mechanism. According to the method, the specific degradation problem of the multi-modal image can be effectively solved, the processing tasks are dynamically allocated through the gating multi-expert system, the quality of the fused image is remarkably improved, and an efficient solution is provided for multi-modal image processing in the fields of security and protection, medical treatment and the like.

The invention relates to the technical field of night monitoring, and discloses a night dynamic target tracking and image restoration method, which comprises the following steps of: establishing a heat-motion correlation model of a target through a space alignment algorithm in combination with heat source contour and intensity information acquired by a thermal imaging sensor and motion parameters detected by a millimeter wave radar; outputting an initial position and a motion state; inputting a target initial state and radar point cloud data based on an LSTM network, predicting a future N-frame trajectory, and dynamically correcting a prediction result by using real-time radar data; inputting the position information of the occlusion area and the trajectory prediction value into a GAN network to generate a complemented image, fusing the complemented image with the original heat source image, and recovering the complete contour of the target; and superposing and rendering the complemented image and the trajectory prediction into an AR picture, and when the target distance triggers a preset threshold value, realizing multi-channel safety early warning through vibration feedback, AR highlight warning and voice prompt. According to the invention, high-precision tracking and safety early warning of the night dynamic target can be improved.

The invention provides an image restoration method based on adaptive weighted tensor completion, and relates to the technical field of image processing and application, and the method comprises the steps: obtaining to-be-restored image data, and carrying out the tensor of the to-be-restored image data, and obtaining input tensor data; constructing a tensor completion model based on an adaptive weighted tensor nuclear norm; wherein a weight matrix in the tensor completion model can be adaptively updated along with input tensor data; and based on an alternating direction multiplier method or an approximate singular value decomposition method based on tensor QR decomposition, solving the tensor completion model, and outputting restored tensor data to realize image restoration. According to the scheme, the image restoration quality can be improved.

The application discloses a kind of detection and defense method of counterpatch, respectively based on abnormal positioning and edge detection.The detection method of counterpatch based on abnormal positioning utilizes clean image to train the generator-adversary network of encoder-decoder structure;The output image is obtained by inputting the image to be detected into the generator-adversary network, and the absolute error is obtained by subtracting and taking absolute value;The image region whose absolute error is greater than error threshold is the region where counterpatch is located;The detection method of counterpatch based on edge detection converts the image to be detected into gray scale image and carries out edge detection, and obtains edge image;The edge lines in edge image are connected into a closed area one by one, and the closed area whose area is less than the area of counterpatch region is the region where counterpatch is located.The application can detect counterpatch based on the two schemes of abnormal positioning and edge detection respectively, and blacken the region or use image restoration algorithm to restore the region to defend counterpatch.

The invention provides a method and a system for restoring a bamboo-strip character image based on multi-granularity feature guidance, and innovatively designs a coarse-fine two-stage restoration network and end-to-end multi-task loss joint training aiming at the problems of structure-texture confusion, non-uniform degradation, low contrast ratio and the like of the bamboo-strip image. In the coarse repair stage, a font texture and structure double-reconstruction sub-network is used for separating semantics from a source; in the fine repairing stage, multi-scale dynamic range distribution diagram self-attention (Mdma) is provided, pixels are dynamically classified according to degradation intensity, and long-short range dependence joint modeling is achieved; an adaptive mask is designed to sense pixel shuffling downsampling (Ampd), sampling is guided by mask confidence, damage position information is kept, and artifacts are inhibited. Five mainstream methods are compared on a homemade 313 bamboo strip single word data set, the PSNR, the SSIM and the FID are optimal under 0-60% irregular masks, visual evaluation of real missing samples is natural in texture, the structure is complete, and the readability of the bamboo strip characters and the subsequent recognition accuracy are effectively improved.

The invention provides an image restoration model training method, an image restoration method and related equipment, and relates to the technical field of image processing. The training method is applied to a cloud server, and comprises the following steps: acquiring a training sample set comprising a plurality of high-definition sample images; performing compression processing on the high-definition sample image to obtain a corresponding sample compression image; determining a sample residual image according to the high-definition sample image and the sample compressed image; based on an image restoration model, performing restoration processing on the sample compressed image according to the sample residual image to obtain a prediction restoration image; determining target loss according to the prediction restoration image, the high-definition sample image and the sample residual image; and training an image restoration model according to the target loss to obtain a trained image restoration model. The image restoration model trained through the method can effectively restore the quality degradation problem caused by loss of compression information, so that the restoration precision and the playing image quality can be improved when the terminal equipment deployment model carries out image restoration.