Video processing method and device and related equipment

Abstract

The invention provides a video processing method and device and related equipment, and relates to the technical field of video processing. The method comprises the following steps: acquiring a to-be-processed video frame and processing indication information thereof, wherein the information is used for indicating time steps with correlativity; determining whether a first related time step related to the current time step and before the current time step exists or not according to the processing indication information in each time step processing process of the preset time steps; if the to-be-processed video frame exists, obtaining an image semantic feature of the current time step according to the processing indication information and the cache information, and performing repair processing on the to-be-processed video frame by using the image semantic feature to obtain a repair result of the current time step; and obtaining a target video frame according to a repair result obtained by processing the last time step. According to the method, the correlation between the time steps can be effectively utilized, the unnecessary calculation amount is reduced, the consumption of calculation resources is reduced, the reasoning time is shortened, and the method is suitable for a real-time or quasi-real-time video processing scene.

Description

Technical Field

[0001] The present disclosure relates to the field of video processing technology, and in particular to a video processing method, a video processing device, an electronic device, a computer-readable storage medium, and a computer program product. Background Art

[0002] In the field of video processing, the diffusion model, with its progressive generation characteristics, performs well in tasks such as video restoration, denoising, super-resolution, and image quality enhancement, improving the visual experience. However, the reasoning process of the diffusion model is complex, and clear and high-quality content is gradually restored through multi-step iterative reasoning, which leads to large consumption of computing resources and long reasoning time, making the diffusion model difficult to apply in real-time or quasi-real-time video processing scenarios.

[0003] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0004] The present disclosure provides a video processing method, a video processing device, an electronic device, a computer-readable storage medium, and a computer program product to overcome the above problems or at least partially solve the above problems.

[0005] According to one aspect of an embodiment of the present disclosure, a video processing method is provided, the method comprising: obtaining a video frame to be processed and processing indication information of the video frame to be processed; the processing indication information is used to indicate a time step with a correlation; in the processing of each time step of a preset time step, determining whether there is a first related time step related to the current time step according to the processing indication information; the first related time step is the time step before the current time step; if the first related time step exists, obtaining the image semantic features of the current time step according to the processing indication information and cache information; performing repair processing on the video frame to be processed according to the image semantic features of the current time step to obtain a repair result of the current time step; and obtaining a target video frame of the video frame to be processed according to the repair result obtained by processing the last time step.

[0006] In some embodiments of the present disclosure, the method further includes: if the first relevant time step does not exist, performing feature extraction on the video frame to be processed through a state control branch of a video processing model to obtain image semantic features of the current time step.

[0007] In some embodiments of the present disclosure, the state control branch includes one or more network layers; wherein, obtaining the image semantic features of the current time step according to the processing indication information and the cache information includes: determining the first relevant network layer corresponding to the current time step and the first relevant time step according to the processing indication information; the processing indication information is used to indicate the relevant network layer corresponding to the time step with the relevant relationship; for each network layer, if the network layer is the first relevant network layer, extracting the image semantic features of the network layer during the processing of the first relevant time step from the cache information, and using the extracted results as the image semantic features of the network layer during the processing of the current time step; if the network layer is not the first relevant network layer, performing feature extraction on the video frame to be processed through the network layer to obtain the image semantic features of the network layer during the processing of the current time step.

[0008] In some embodiments of the present disclosure, the method further includes: determining whether there is a second relevant time step related to the current time step based on the processing indication information; the second relevant time step is a time step after the current time step; if the second relevant time step exists, determining the second relevant network layer corresponding to the current time step and the second relevant time step based on the processing indication information; and placing the image semantic features of the second relevant network layer during the processing of the current time step into the cache information.

[0009] In some embodiments of the present disclosure, the video frame to be processed is repaired according to the image semantic features of the current time step to obtain the repair result of the current time step, including: fusing the image semantic features of the current time step and the repair result of the previous time step through the backbone model branch of the video processing model to obtain the repair result of the current time step; wherein, if the current time step is the first time step, the repair result of the previous time step is noise data.

[0010] In some embodiments of the present disclosure, the processing indication information is pre-generated according to the following process: obtaining a sample video frame; the scene information of the sample video frame is the same as the scene information of the video frame to be processed; according to the preset time step, through each network layer in the state control branch included in the video processing model, feature extraction is performed on the sample video frame to obtain sample features of each network layer in each time step processing; for each network layer, based on the obtained sample features, similarity between sample features of the network layer in different time step processing is calculated, and based on the calculated similarity, a time step with a correlation relationship and a related network layer corresponding to the time step with a correlation relationship are determined; based on the time step with a correlation relationship and the related network layer corresponding to the time step with a correlation relationship, the processing indication information is generated.

[0011] In some embodiments of the present disclosure, for each network layer, based on the obtained sample features, the similarity between the sample features of the network layer in different time step processing is calculated, and based on the calculated similarity, the time step where there is a correlation and the relevant network layer corresponding to the time step where there is a correlation are determined, including: for each network layer, the sample features of the network layer in any two time step processing are selected from the obtained sample features, and the similarity between the two selected sample features is calculated; if the calculated similarity is greater than a similarity threshold, the time step corresponding to the two selected sample features is determined to be the time step where there is a correlation, and the network layer is used as the relevant network layer corresponding to the time step where there is a correlation.

[0012] According to another aspect of an embodiment of the present disclosure, a video processing device is provided, the device comprising: an acquisition module, configured to acquire a video frame to be processed and processing indication information of the video frame to be processed; the processing indication information is used to indicate a time step with a correlation relationship; an iteration module, configured to determine whether there is a first related time step related to the current time step according to the processing indication information during processing of each time step of a preset time step; the first related time step is a time step before the current time step; if the first related time step exists, the image semantic features of the current time step are obtained according to the processing indication information and cache information; the video frame to be processed is repaired according to the image semantic features of the current time step to obtain a repair result of the current time step; a processing module, configured to obtain a target video frame of the video frame to be processed according to the repair result obtained by processing the last time step.

[0013] According to another aspect of an embodiment of the present disclosure, an electronic device is provided, including: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute the executable instructions to implement the above-mentioned video processing method.

[0014] According to another aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided. When instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to perform the above-mentioned video processing method.

[0015] According to another aspect of an embodiment of the present disclosure, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the above-mentioned video processing method is implemented.

[0016] The video processing method provided by the embodiment of the present disclosure introduces processing indication information, which can indicate the time steps with correlation. During the processing of each time step of the preset time step, if it is determined according to the processing indication information that there is a first correlated time step that is correlated with the current time step and before the current time step, the image semantic features of the current time step are directly obtained according to the processing indication information and the cache information, and then the image semantic features are used to perform repair processing on the video frame to be processed at the current time step. The correlation between time steps can be effectively utilized in the iterative repair processing, unnecessary calculation amount is reduced, thereby reducing the consumption of computing resources and shortening the inference time. Therefore, the method can generate high-quality videos more quickly, improve the user's visual experience, and is suitable for real-time or quasi-real-time video processing scenarios.

[0017] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the specification are used to explain the principles of the present disclosure. Obviously, the accompanying drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without creative work.

[0019] Figure 1 A schematic diagram showing an exemplary system architecture to which the video processing method according to an embodiment of the present disclosure can be applied;

[0020] Figure 2 A flow chart of a video processing method according to an embodiment of the present disclosure is shown;

[0021] Figure 3 An architectural diagram of a video processing model according to an embodiment of the present disclosure is shown;

[0022] Figure 4 A diagram showing a process of generating processing instruction information in a video processing method according to an embodiment of the present disclosure is shown;

[0023] Figure 5 A process diagram showing the process of obtaining the image semantic features of the current time step according to the processing instruction information and the cache information in the video processing method of the embodiment of the present disclosure;

[0024] Figure 6 A schematic diagram showing video processing according to cache information according to an embodiment of the present disclosure is shown;

[0025] Figure 7 A block diagram of a video processing device according to an embodiment of the present disclosure is shown;

[0026] Figure 8 A schematic structural diagram of an electronic device according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0027] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be comprehensive and complete and will fully convey the concepts of the example embodiments to those skilled in the art. The same reference numerals in the figures represent the same or similar parts, and thus their repeated description will be omitted.

[0028] The features, structures or characteristics described in the present disclosure may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known methods, devices, implementations or operations are not shown or described in detail to avoid blurring the various aspects of the present disclosure.

[0029] The collection, collection, updating, analysis, processing, use, transmission, storage and other aspects of the user personal information involved in this disclosure are in compliance with the relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. Necessary measures are taken for user personal information to prevent illegal access to user personal information data and maintain the security of user personal information, network security and national security.

[0030] The accompanying drawings are only schematic diagrams of the present disclosure, and the same reference numerals in the drawings represent the same or similar parts, so their repeated description will be omitted. Some block diagrams shown in the accompanying drawings do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or implemented in at least one hardware module or integrated circuit, or implemented in different networks and / or processor devices and / or microcontroller devices.

[0031] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and steps, nor must they be executed in the order described. For example, some steps can be decomposed, and some steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0032] In this specification, the terms "a", "an", "the", "said" and "at least one" are used to indicate the presence of at least one element / component / etc.; the term "plurality" refers to two or more; the terms "comprising", "including" and "having" are used to express an open-ended inclusion and mean that additional elements / components / etc. may exist in addition to the listed elements / components / etc.; the terms "first", "second" and "third" etc. are used only as labels and are not intended to limit the quantity of their objects.

[0033] In the field of video processing, the diffusion model has become an important technical direction. However, the complex multi-step iterative reasoning process of the diffusion model leads to high computing resource consumption and long reasoning time, which limits the application of the diffusion model in real-time or quasi-real-time video processing scenarios. In related technologies, acceleration technologies such as quantization and pruning are used to reduce the computational cost of the model. However, for video processing application scenarios that require multiple iterations to generate high-quality images, these acceleration technologies have limited acceleration effects on the diffusion model and are difficult to meet the needs of real-time or quasi-real-time video processing.

[0034] In order to solve the above problems, the embodiments of the present disclosure provide a video processing method, which introduces processing indication information, which can identify the time steps where there are correlations. By using the processing indication information to guide the iterative process, unnecessary calculations are reduced, thereby reducing the consumption of computing resources and shortening the reasoning time. This method can generate high-quality videos more quickly, improve the user's visual experience, and is suitable for real-time or quasi-real-time video processing scenarios.

[0035] Figure 1 The diagram shows an exemplary system architecture to which the video processing method according to the embodiment of the present disclosure can be applied.

[0036] like Figure 1 As shown, the system architecture may include a server 101, a network 102 and a terminal device 103. The network 102 is used to provide a medium for a communication link between the terminal device 103 and the server 101. The network 102 may include various connection types, such as wired, wireless communication links or optical fiber cables.

[0037] In an exemplary embodiment, the terminal device 103 for data transmission with the server 101 may include but is not limited to mobile devices such as smart phones, tablet computers, and laptop computers, as well as terminal devices with specific functions or forms such as smart speakers, digital assistants, AR (Augmented Reality) devices, VR (Virtual Reality) devices, and smart wearable devices. Alternatively, the terminal device 103 may also be a personal computer, such as a laptop computer and a desktop computer. Optionally, the operating system running on the electronic device may include but is not limited to Android, IOS, Linux, Windows, etc.

[0038] Server 101 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. In some practical applications, server 101 can also be a server of a network platform, which can be, for example, a trading platform, a live broadcast platform, a social platform, or an audio platform, etc., which is not limited in the embodiments of the present disclosure. Among them, the server can be a single server or a cluster formed by multiple servers, and the present disclosure does not limit the specific architecture of the server.

[0039] In some embodiments of the present disclosure, the process of video processing by server 101 may be: obtaining a video frame to be processed and processing indication information of the video frame to be processed; the processing indication information is used to indicate a time step with a correlation; in the processing process of each time step of a preset time step, determining whether there is a first related time step related to the current time step according to the processing indication information; the first related time step is the time step before the current time step; if there is a first related time step, obtaining the image semantic features of the current time step according to the processing indication information and the cache information; repairing the video frame to be processed according to the image semantic features of the current time step to obtain a repair result of the current time step; obtaining a target video frame of the video frame to be processed according to the repair result obtained by processing the last time step.

[0040] In addition, it should be noted that Figure 1 What is shown is merely one application environment of the image enhancement model training method or image enhancement method provided by the present disclosure. Figure 1 The number of terminal devices 103, networks 102 and servers 101 is merely illustrative, and any number of terminal devices, networks and servers may be provided according to actual needs.

[0041] Figure 2 A flowchart of a video processing method according to an embodiment of the present disclosure is shown. Figure 2 The execution subject of the method provided in the embodiment may be any electronic device, such as Figure 1 The terminal device 101 in the embodiment is also as follows Figure 1 The terminal device 103 in Figure 1 The server 101 and the terminal device 103 in the embodiment jointly implement the video processing method, but the present disclosure is not limited thereto. Figure 2 The video processing method provided by the embodiment of the present disclosure includes the following steps.

[0042] Step S210, obtaining a video frame to be processed and processing indication information of the video frame to be processed; the processing indication information is used to indicate a time step with a correlation relationship.

[0043] In the embodiment of the present disclosure, the video frame to be processed refers to a video frame that needs to be processed or repaired, and the frame may be used to improve the quality due to low resolution, noise, blur or damage. In the video processing process, the video to be processed is obtained, and the video to be processed includes multiple video frames to be processed. These video frames to be processed can be obtained frame by frame, and each video frame to be processed is subsequently processed.

[0044] The processing instruction information is instruction information associated with the video frame to be processed, which provides specific guidance on how to process or repair the video frame to be processed. In the embodiment of the present disclosure, the processing instruction information is used to indicate the time steps with the correlation relationship, or in other words, the processing instruction information indicates the time steps corresponding to the video frame features with the correlation or similarity.

[0045] Step S220: During the processing of each time step of the preset time step, determine whether there is a first related time step related to the current time step according to the processing instruction information; the first related time step is the time step before the current time step.

[0046] In the embodiment of the present disclosure, the preset time step is used to indicate the number of times the processing of the video frame to be processed is repaired. The preset time step can be set to T, where T is a positive integer, and the video frame to be processed is repaired T times through the video processing model. In the embodiment of the present disclosure, the video frame to be processed is iteratively repaired according to the preset time step. In each time step processing process, that is, in each repair process of the video frame to be processed, it is determined according to the processing indication information whether there is a first related time step related to the current time step, that is, whether there is a time step that is related to the current time step in the time step before the current time step. .

[0047] Step S230: If there is a first relevant time step, the image semantic features of the current time step are obtained according to the processing instruction information and the cache information.

[0048] In the disclosed embodiment, the cache information is used to store the image semantic features of the target time step during the processing, wherein the target time step is the earlier time step in time among the time steps with a correlation. For example, if time step t and time step t+1 are time steps with a correlation, and time step t is the previous time step of time step t+1, then time step t is the target time step.

[0049] In the disclosed embodiment, during the processing of the current time step, if it is determined that the current time step has a first related time step, it means that the similarity between the image semantic features of the current time step and the image semantic features of the first related time step is high, and the first related time step is before the current time step, then the image semantic features of the current time step processing process can be obtained based on the processing indication information and the cache information.

[0050] Taking the current time step t+1 as an example, time step t and time step t+1 are time steps with a correlation relationship, which means that the image semantic features of time step t and the image semantic features of time step t+1 are highly similar, and time step t is earlier than time step t+1. During the processing of time step t, the image semantic features of time step t are stored in the cache information, so that during the processing of time step t+1, the image semantic features of time step t+1 are obtained according to the processing instruction information and the cache information.

[0051] Step S240, performing restoration processing on the video frame to be processed according to the image semantic features of the current time step to obtain a restoration result of the current time step.

[0052] In the disclosed embodiment, after obtaining the image semantic features of the current time step, the image semantic features of the current time step are used to perform restoration processing of the current time step to obtain a restoration result of the current time step.

[0053] Step S250, obtaining a target video frame of the video frame to be processed according to the restoration result obtained by processing at the last time step.

[0054] In the disclosed embodiment, for the video frame to be processed, an iterative repair process is performed according to a preset time step T. In each time step, if it is determined according to the processing indication information that the current time step has a first related time step, the image semantic features of the current time step are directly obtained according to the cache information and the processing indication information, and then the image semantic features of the current time step are used to perform the repair process of the time step at that time to obtain the repair result of the current time step. Finally, at the end of the last time step (i.e., the Tth time step), a repair result after multiple iterative repairs is obtained, and a high-quality target video frame is obtained using the repair result.

[0055] The video processing method provided by the embodiment of the present disclosure introduces processing indication information, which can indicate the time steps with correlation. During the processing of each time step of the preset time step, if it is determined according to the processing indication information that there is a first correlated time step that is correlated with the current time step and before the current time step, the image semantic features of the current time step are directly obtained according to the processing indication information and the cache information, and then the image semantic features are used to perform repair processing on the video frame to be processed at the current time step. The correlation between time steps can be effectively utilized in the iterative repair processing, unnecessary calculation amount is reduced, thereby reducing the consumption of computing resources and shortening the inference time. Therefore, the method can generate high-quality videos more quickly, improve the user's visual experience, and is suitable for real-time or quasi-real-time video processing scenarios.

[0056] In some embodiments of the present disclosure, the video processing method further includes: if the first relevant time step does not exist, performing feature extraction on the video frame to be processed through the state control branch of the video processing model to obtain the image semantic features of the current time step.

[0057] In the disclosed embodiment, the video processing model is a pre-trained diffusion model. The diffusion model is a probability-based generative model that can generate high-quality images or videos by gradually reducing noise. The video processing model uses the diffusion process to learn how to generate clear images or video frames from noise, and in the restoration process, gradually reduces noise and restores high-quality image content.

[0058] For ease of understanding, the video processing model of the embodiment of the present disclosure is first described. Figure 3 FIG. 4 shows an architecture diagram of a video processing model of an embodiment of the present disclosure. Figure 3 As shown, the architecture includes an encoder 310 , a video processing model 320 , and a decoder 330 .

[0059] The encoder 310 is a variational autoencoder (VAE) encoder, and the decoder 330 is a VAE decoder. The encoder 310 is used to encode the video frame to be processed to obtain the encoding features of the video frame to be processed, and the decoder 330 is used to decode the restoration result of the video processing model 320 to finally generate a high-quality video frame.

[0060] The video processing model 320 is the core of the entire architecture and is responsible for performing iterative repair tasks on the video frames to be processed, such as Figure 3 As shown, the video processing model 320 includes a state control branch 321 and a trunk model branch 322. The video processing model 320 performs an iterative repair process according to T time steps, that is, the state control branch 321 and the trunk model branch 322 perform iterative repair in collaboration according to T time steps.

[0061] In the disclosed embodiment, during the processing of the current time step, if it is determined according to the processing indication information that there is a first related time step in the current time step, then the image and speech features of the current time step are obtained according to the processing indication information and the cache information; if it is determined according to the processing indication information that there is no first related time step in the current time step, feature extraction is performed on the encoding features of the video frame to be processed through the state control branch 321 to generate features containing rich image semantic information, that is, the image semantic features of the current time step are obtained.

[0062] In the video processing method provided by the embodiment of the present disclosure, during the processing of each time step, when it is determined that the first related time step does not exist in the current time step, the image semantic features of the current time step are generated through the state control branch of the video processing model, and the generated image semantic features are subsequently used for repair processing, which helps to more accurately restore damaged or missing image parts during the repair process.

[0063] In some embodiments of the present disclosure, the video frame to be processed is repaired according to the image semantic features of the current time step to obtain the repair result of the current time step, including: fusing the image semantic features of the current time step and the repair result of the previous time step through the backbone model branch of the video processing model to obtain the repair result of the current time step; wherein, if the current time step is the first time step, the repair result of the previous time step is noise data.

[0064] In the disclosed embodiment, after obtaining the image semantic features of the current time step, these features are integrated into the backbone model branch 322 as supervisory information to significantly improve the fidelity and authenticity of the generated content; the backbone model branch 322 receives noise (in the first time step of the repair process) or the repair result of the previous time step as input, and performs the repair process in combination with the supervisory information provided by the state control branch 321 (i.e., the image semantic features of the current time step) to obtain the repair result of the current time step.

[0065] from Figure 3 It can be seen that the state control branch 321 can perform feature extraction in combination with the category information C. The category information C refers to the category label to which the video frame or video sequence belongs, such as "animal", "landscape", "sports scene", etc. In the feature extraction process, combining the category information C can help the model capture the features related to the category more accurately, thereby improving the accuracy of subsequent processing.

[0066] In the video processing method provided by the embodiment of the present disclosure, during the processing of the current time step, the repair result of the previous time step is used as a reference, which can enhance the stability of the repair of the current time step, help to more accurately restore the image content, and reduce the amount of calculation and resource consumption required for the processing of the current time step to a certain extent.

[0067] Figure 4 The diagram shows the process of generating processing instruction information in the video processing method of the embodiment of the present disclosure. Figure 4 In the embodiment of the present disclosure, processing instruction information can be pre-generated according to the following steps.

[0068] Step S410, obtaining a sample video frame; the scene information of the sample video frame is the same as the scene information of the video frame to be processed.

[0069] In the disclosed embodiment, the sample video frame refers to a video frame used to generate processing instruction information. The sample video frame has the same scene information as the video frame to be processed, that is, the application scene of the sample video frame is the same as the application scene of the video frame to be processed. For example, if the application scene of the video frame to be processed is a live broadcast scene, then the sample video frame is a video frame in the live broadcast scene. In this way, it can be ensured that the requirements of video processing (such as real-time and quasi-real-time) are met in the same application scenario.

[0070] Step S420, according to the preset time step, through each network layer in the state control branch included in the video processing model, feature extraction is performed on the sample video frame to obtain sample features of each network layer in each time step processing.

[0071] In the embodiment of the present disclosure, the state control branch includes one or more network layers. Figure 3For example, the state control branch 321 includes three network layers.

[0072] In the embodiment of the present disclosure, the preset time step is used to indicate the number of times the repair process is performed on the video frame to be processed, and the preset time step can be set to T, where T is a positive integer. In order to improve the accuracy of the processing instruction information, according to the preset time step T, feature extraction is performed on the sample video frame through each network layer of the state control branch to obtain the sample features of each network layer in each time step processing.

[0073] Step S430, for each network layer, based on the obtained sample features, calculate the similarity between the sample features of the network layer in different time steps, and based on the calculated similarity, determine the time steps with correlation and the relevant network layers corresponding to the time steps with correlation.

[0074] In the embodiment of the present disclosure, for each network layer in the state control branch, the sample features obtained in the processing of different time steps are used to calculate the similarity, so as to evaluate the similarity of the sample features of the same network layer at different time steps through the calculated similarity. Among them, the similarity can be calculated by methods such as cosine similarity and Euclidean distance. Of course, other similarity calculation methods can also be used, and the embodiment of the present disclosure does not limit this.

[0075] Based on the calculated similarity values, it is possible to identify which time steps have significant similarities in sample features, and then determine the time steps with relevant relationships and the relevant network layers corresponding to these time steps.

[0076] In some embodiments of the present disclosure, for each network layer, based on the obtained sample features, the similarity between the sample features of the network layer in different time step processing is calculated, and based on the calculated similarity, the time step with the correlation and the relevant network layer corresponding to the time step with the correlation are determined, including: for each network layer, the sample features of the network layer in any two time step processing are selected from the obtained sample features, and the similarity between the two selected sample features is calculated; if the calculated similarity is greater than a similarity threshold, the time step corresponding to the two selected sample features is determined to be the time step with the correlation, and the network layer is used as the relevant network layer corresponding to the time step with the correlation.

[0077] In the embodiment of the present disclosure, for each network layer in the state control branch, sample features of any two time steps are selected from sample features obtained in processing the network layer at different time steps to perform similarity calculation. The specific calculation formula is as follows:

[0078]

[0079] In formula (1), represents the sample features of the i-th layer in the state control branch at time step t, represents the sample features of the i-th layer in the state control branch at time step t+1, Represents the calculated cosine similarity.

[0080] In the embodiment of the present disclosure, a similarity threshold θ can be preset. This means that the sample features of the i-th layer in the state control branch at time step t are The sample features of the i-th layer in the state control branch at time step t+1 The similarity between them is high. In this case, time step t and time step t+1 are determined to be time steps with a correlation relationship, and network layer i is used as the relevant network layer corresponding to time step t and time step t+1.

[0081] In the disclosed embodiment, the processing efficiency and processing effect can be balanced by controlling the size of the similarity threshold θ. For scenes with high requirements for video processing efficiency, the similarity threshold θ can be set to a smaller value, such as setting the similarity threshold θ to 0.9. For scenes with high requirements for video processing quality, the similarity threshold θ can be set to a larger value, such as setting the similarity threshold θ to 0.95.

[0082] For each network layer in the state control branch, after similarity analysis is performed on sample features of any two time steps among sample features obtained in processing different time steps of the network layer, all relevant time steps corresponding to the network layer are obtained.

[0083] Step S440: Generate processing instruction information according to the time steps with the correlation relationship and the relevant network layers corresponding to the time steps with the correlation relationship.

[0084] In the disclosed embodiment, after comprehensively analyzing the sample features of all network layers at different time steps, all time steps with correlation in the preset time step can be obtained, and the relevant network layers corresponding to the time steps with correlation can also be obtained, and finally the processing indication information is generated. Therefore, the processing indication information is used to indicate the time steps with correlation and the relevant network layers corresponding to the time steps with correlation.

[0085] In the video processing method of the embodiment of the present disclosure, a sample video frame having the same scene information as the video frame to be processed is obtained, and processing instruction information is generated using the sample video frame, thereby ensuring that the processing instruction information matches the scene information of the video frame to be processed; and, by using each network layer in the state control branch of the video processing model to extract features from the sample video frame, subtle changes in the video frame at different time steps and different network layers can be captured, and then by calculating the similarity between the sample features in the processing at different time steps, the time steps with related relationships and the corresponding related network layers can be accurately identified, thereby providing strong support for generating accurate processing instruction information.

[0086] Furthermore, the similarity between the sample features of each network layer in different time step processing is calculated, and a similarity threshold is set to determine the time steps and corresponding related network layers with correlated relationships. This method can accurately identify those time steps and network layers with significant correlations, thereby ensuring the accuracy and reliability of the processing indication information.

[0087] In the disclosed embodiment, during the processing of each time step, feature extraction is performed on the video frame to be processed according to the processing instruction information through the state control branch of the video processing model to obtain the image semantic features of the current time step. Figure 5 The figure shows a process diagram of obtaining the image semantic features of the current time step according to the processing instruction information and the cache information in the video processing method of the embodiment of the present disclosure. Figure 5 , obtaining the image semantic features of the current time step according to the processing instruction information and the cache information may include the following steps.

[0088] Step S510: determining the first relevant network layer corresponding to the current time step and the first relevant time step according to the processing indication information; the processing indication information is used to indicate the relevant network layer corresponding to the time step having a relevant relationship.

[0089] Step S520, for each network layer, if the network layer is the first relevant network layer, the image semantic features of the network layer during the processing of the first relevant time step are extracted from the cache information, and the extracted results are used as the image semantic features of the network layer during the processing of the current time step.

[0090] Step S530, for each network layer, if the network layer is not the first relevant network layer, feature extraction is performed on the video frame to be processed through the network layer to obtain the image semantic features of the network layer during the current time step processing.

[0091] In the embodiment of the present disclosure, the processing indication information is used not only to indicate the time step where the correlation exists, but also to indicate the relevant network layer corresponding to the time step where the correlation exists.

[0092] In the disclosed embodiment, during the processing of the current time step, if there is a first related time step that is correlated with the current time step, it is determined that the image semantic features of the current time step are similar to the image semantic features of the first related time step, but this does not mean that the image semantic features of each network layer are similar. Therefore, the first related network layer is further determined according to the control indication information, that is, it is determined at which specific network layer the image semantic features of the current time step and the first related time step are similar.

[0093] Each network layer is analyzed. If the network layer is the first relevant network layer, it means that the image semantic features of the network layer in the current time step processing process are highly similar to the image semantic features in the first relevant time step processing process, and the first relevant time step is before the current time step, which means that the image semantic features of the network layer in the first relevant time step processing process are stored in the cache information, and the features can be directly obtained and used as the image semantic features of the network layer in the current time step processing process. If the network layer is not the first relevant network layer, the network layer is used to extract features of the video frame to be processed to obtain the image semantic features of the network layer in the current time step processing process.

[0094] Figure 6 A schematic diagram of performing video processing according to cache information in an embodiment of the present disclosure is shown. Figure 6 In the example, the current time step t+1 is used for explanation. Time step t and time step t+1 are time steps with a correlation relationship, that is, time t is the first correlated time step of time step t+1, and the corresponding first correlated network layer is the three network layers of the state control branch. In other words, the similarity between the image semantic features of each network layer in the process of processing time step t and the image semantic features in the process of processing time step t+1 is high. In the process of processing time step t, the image semantic features of each network layer of the state control branch are stored in the cache information, so that in the process of processing time step t+1, the image semantic features of each network layer in the cache information in the process of processing time step t are obtained from the cache information, and these features are used as the image semantic features of the corresponding network layer in the process of processing time step t+1, without the need for feature extraction through the state control branch.

[0095] In the video processing method provided by the embodiment of the present disclosure, during the processing of the current time step, if there is a first relevant time step related to the current time step, further, the first relevant network layer corresponding to the current time step and the first relevant time step can be accurately determined through the indication information, that is, it is possible to accurately determine which network layer features can be reused between the current time step and the first relevant time step, and by using the image semantic features of the first relevant network layer at the first relevant time step in the cache to determine the image semantic features of the first relevant network layer at the current time step, unnecessary calculations are reduced, thereby speeding up the video processing speed, which is particularly important for real-time video processing or application scenarios that require fast response.

[0096] In some embodiments of the present disclosure, the video processing method also includes: determining whether there is a second relevant time step related to the current time step based on processing indication information; the second relevant time step is a time step after the current time step; if there is a second relevant time step, determining the second relevant network layer corresponding to the current time step and the second relevant time step based on the processing indication information; and placing the image semantic features of the second relevant network layer during the processing of the current time step into the cache information.

[0097] In the embodiment of the present disclosure, during the processing of the current time step, it is determined whether there is a second related time step related to the current time step based on the processing indication information, that is, it is determined whether there is a time step that is correlated with the current time step in the time step after the current time step.

[0098] If it is determined that there is a second related time step in the current time step, it means that the image semantic features of the current time step and the image semantic features of the second related time step have a high degree of similarity. Further, the second related network layer corresponding to the current time step and the second related time step is determined, that is, it is determined at which network layer the image semantic features of the current time step and the second related time step are similar. In this way, after obtaining the image semantic features of the second related network layer in the current time processing process, the feature is placed in the cache information, so that in the second related time step processing process, the feature can be directly obtained from the cache information and used as the image semantic features of the second related network layer in the second related time processing process.

[0099] Taking the current time step t+2 as an example, time step t+2 and time step t+3 are time steps with a correlation relationship, and the corresponding second related network layer is network layer 2, which means that the image semantic features of network layer 2 in the process of processing time step t+2 are highly similar to the image semantic features in the process of processing time step t+3. In the process of processing time step t+2, the image semantic features of network layer 2 are stored in the cache information, so that in the process of processing time step t+3, the features are obtained from the cache information and used as the image semantic features of network layer 2 in the process of processing time step t+3. In addition, since network layer 1 and network layer 3 are not the second related network layers corresponding to time step t+2 and time step t+3, in the process of processing time step t+3, network layer 1 and network layer 3 are used to extract features respectively, and the image semantic features of network layer 1 and network layer 3 in the process of processing time step t+3 are obtained.

[0100] In the video processing method provided by the embodiment of the present disclosure, during the processing of the current time step, if there is a second related time step related to the current time step, the second related network layer corresponding to the current time step and the second related time step can be accurately determined through the indication information, that is, it is possible to accurately determine which network layer features can be reused between the current time step and the second related time step, and store the image semantic features of the second related network layer at the current time step in the cache, which reduces the need to recalculate these features in the subsequent second time step processing, reduces unnecessary calculations, and thus significantly improves the efficiency of video processing.

[0101] In summary, the video processing method provided by the embodiment of the present disclosure obtains the video frame to be processed and its processing indication information, and then uses the video processing model to iteratively repair the video frame to be processed according to the preset time step, and updates the repair result in each time step according to the processing indication information and the repair result of the previous time step (the first step is noise data), and finally determines the high-quality target video frame according to the repair result obtained in the last time step. It can be seen that the method introduces processing indication information, which can indicate the time step with a correlation, so that the video processing model can effectively use the correlation between time steps during the iterative repair process, reduce unnecessary calculations, thereby reducing the consumption of computing resources, and shortening the reasoning time. Therefore, the method can generate high-quality videos faster, improve the user's visual experience, and is suitable for real-time or quasi-real-time video processing scenarios.

[0102] It can be understood that the same / similar parts between the various embodiments of the above method in this specification can refer to each other, and each embodiment focuses on the differences from other embodiments. For related points, please refer to the description of other method embodiments.

[0103] Figure 7 FIG. 1 is a block diagram of a video processing device according to an embodiment of the present disclosure. Figure 7 As shown, the video processing device 700 includes: an acquisition module 710 , an iteration module 720 and a processing module 730 .

[0104] Wherein, the acquisition module 710 is configured to: acquire the video frame to be processed and the processing indication information of the video frame to be processed; wherein, the processing indication information is used to indicate the time step with the correlation relationship. The iteration module 720 is configured to: during the processing of each time step of the preset time step, determine whether there is a first related time step related to the current time step according to the processing indication information, wherein the first related time step is the time step before the current time step; if there is a first related time step, obtain the image semantic features of the current time step according to the processing indication information and the cache information; perform repair processing on the video frame to be processed according to the image semantic features of the current time step to obtain the repair result of the current time step. The processing module 730 is configured to: obtain the target video frame of the video frame to be processed according to the repair result obtained by the last time step processing.

[0105] In some embodiments of the present disclosure, the iteration module 720 is further configured to: if there is no first relevant time step, perform feature extraction on the video frame to be processed through the state control branch of the video processing model to obtain the image semantic features of the current time step.

[0106] In some embodiments of the present disclosure, the state control branch includes one or more network layers. The iteration module 720 is further configured to: determine the first relevant network layer corresponding to the current time step and the first relevant time step according to the processing indication information; the processing indication information is used to indicate the relevant network layer corresponding to the time step with the relevant relationship; for each network layer, if the network layer is the first relevant network layer, extract the image semantic features of the network layer in the first relevant time step processing process from the cache information, and use the extracted results as the image semantic features of the network layer in the current time step processing process; if the network layer is not the first relevant network layer, extract features of the video frame to be processed through the network layer to obtain the image semantic features of the network layer in the current time step processing process.

[0107] In some embodiments of the present disclosure, the iteration module 720 is further configured to: determine whether there is a second relevant time step related to the current time step based on the processing indication information; the second relevant time step is the time step after the current time step; if there is a second relevant time step, determine the second relevant network layer corresponding to the current time step and the second relevant time step based on the processing indication information; and put the image semantic features of the second relevant network layer during the processing of the current time step into the cache information.

[0108] In some embodiments of the present disclosure, the iteration module 720 is also configured to: fuse the image semantic features of the current time step and the restoration result of the previous time step through the backbone model branch of the video processing model to obtain the restoration result of the current time step; wherein, if the current time step is the first time step, the restoration result of the previous time step is noise data.

[0109] In some embodiments of the present disclosure, the device 700 also includes an indication generation module 740, which is configured to pre-generate processing indication information according to the following process: obtain a sample video frame, the scene information of the sample video frame is the same as the scene information of the video frame to be processed; according to a preset time step, through each network layer in the state control branch included in the video processing model, feature extraction is performed on the sample video frame to obtain sample features of each network layer in each time step processing; for each network layer, based on the obtained sample features, the similarity between the sample features of the network layer in different time step processing is calculated, and based on the calculated similarity, the time step with a correlation relationship and the related network layer corresponding to the time step with a correlation relationship are determined; based on the time step with a correlation relationship and the related network layer corresponding to the time step with a correlation relationship, processing indication information is generated.

[0110] In some embodiments of the present disclosure, the indication generation module 740 is further configured to: for each network layer, select sample features of the network layer in any two time step processing from the obtained sample features, and calculate the similarity between the two selected sample features; if the calculated similarity is greater than a similarity threshold, determine that the time steps corresponding to the two selected sample features are time steps where a correlation exists, and use the network layer as the relevant network layer corresponding to the time step where a correlation exists.

[0111] Regarding the device in the above embodiment, the specific manner in which each unit performs the operation has been described in detail in the embodiment of the method, and will not be elaborated here.

[0112] Figure 8 FIG. 1 is a schematic diagram showing the structure of an electronic device according to an embodiment of the present disclosure. It should be noted that: Figure 8 The electronic device 800 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0113] like Figure 8 As shown, the electronic device 800 is in the form of a general computing device. The components of the electronic device 800 may include but are not limited to: at least one processing unit 810, at least one storage unit 820, and a bus 830 connecting different system components (including the storage unit 820 and the processing unit 810).

[0114] The storage unit stores program codes, which can be executed by the processing unit 810, so that the processing unit 810 performs the steps according to various exemplary embodiments of the present invention described in the above “Exemplary Method” section of this specification. For example, the processing unit 810 can perform the following steps: Figure 2 Follow the steps shown in .

[0115] The storage unit 820 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 8201 and / or a cache memory unit 8202 , and may further include a read-only memory unit (ROM) 8203 .

[0116] The storage unit 820 may also include a program / utility 8204 having a set (at least one) of program modules 8205, such program modules 8205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0117] Bus 830 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0118] The electronic device 800 may also communicate with one or more external devices 900 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 800, and / or communicate with any device that enables the electronic device 800 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 850. Furthermore, the electronic device 800 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 840. As shown, the network adapter 840 communicates with other modules of the electronic device 800 via a bus 830. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 800, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0119] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the above method of the present specification is stored. In some possible implementations, various aspects of the present invention can also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps according to various exemplary embodiments of the present invention described in the above "Exemplary Method" section of the present specification.

[0120] The program product for implementing the above method according to the embodiment of the present invention may adopt a portable compact disk read-only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto, and in this document, a readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, apparatus, or device.

[0121] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0122] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0123] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0124] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0125] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0126] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0127] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0128] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any modification, use or adaptation of the present disclosure, which follows the general principles of the present disclosure and includes common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are to be considered as exemplary only, and the true scope and spirit of the present disclosure are indicated by the appended claims.

[0129] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A video processing method, characterized in that: The method comprises: Acquire a video frame to be processed and processing indication information of the video frame to be processed; the processing indication information is used to indicate a time step with a correlation relationship; In each time step processing of the preset time step, determining whether there is a first related time step related to the current time step according to the processing instruction information; the first related time step is a time step before the current time step; If the first relevant time step exists, obtaining the image semantic features of the current time step according to the processing instruction information and the cache information; Performing restoration processing on the to-be-processed video frame according to the image semantic features of the current time step to obtain a restoration result of the current time step; According to the restoration result obtained by processing at the last time step, a target video frame of the video frame to be processed is obtained.

2. The method according to claim 1, characterized in that: The method further comprises: If the first relevant time step does not exist, feature extraction is performed on the video frame to be processed through the state control branch of the video processing model to obtain the image semantic features of the current time step.

3. The method according to claim 2, characterized in that The state control branch includes one or more network layers; wherein obtaining the image semantic features of the current time step according to the processing instruction information and the cache information includes: Determine, according to the processing instruction information, a first related network layer corresponding to the current time step and the first related time step; the processing instruction information is used to indicate the related network layer corresponding to the time step having the related relationship; For each network layer, if the network layer is the first relevant network layer, extracting the image semantic features of the network layer in the first relevant time step processing process from the cache information, and using the extracted results as the image semantic features of the network layer in the current time step processing process; If the network layer is not the first relevant network layer, feature extraction is performed on the video frame to be processed through the network layer to obtain image semantic features of the network layer during the current time step processing.

4. The method according to claim 3, characterized in that: The method further comprises: Determine, according to the processing instruction information, whether there is a second related time step related to the current time step; the second related time step is a time step after the current time step; If the second relevant time step exists, determining, according to the processing instruction information, a second relevant network layer corresponding to the current time step and the second relevant time step; The image semantic features of the second relevant network layer during the current time step processing are placed into the cache information.

5. The method according to claim 2, characterized in that: The repairing process is performed on the to-be-processed video frame according to the image semantic features of the current time step to obtain the repair result of the current time step, including: Through the backbone model branch of the video processing model, the image semantic features of the current time step and the restoration result of the previous time step are fused to obtain the restoration result of the current time step; wherein, if the current time step is the first time step, the restoration result of the previous time step is noise data.

6. The method according to any one of claims 1 to 5, characterized in that: The processing instruction information is pre-generated according to the following process: Acquire a sample video frame; the scene information of the sample video frame is the same as the scene information of the video frame to be processed; According to the preset time step, feature extraction is performed on the sample video frame through each network layer in the state control branch included in the video processing model to obtain sample features of each network layer in each time step processing; For each network layer, based on the obtained sample features, the similarity between the sample features of the network layer in different time steps is calculated, and based on the calculated similarity, the time steps with correlation relationship and the relevant network layers corresponding to the time steps with correlation relationship are determined; The processing indication information is generated according to the time steps having the correlation relationship and the relevant network layers corresponding to the time steps having the correlation relationship.

7. The method according to claim 6, characterized in that The method further comprises: calculating, for each network layer, the similarity between the sample features of the network layer in different time steps according to the obtained sample features, and determining, according to the calculated similarity, the time steps with the correlation relationship and the relevant network layers corresponding to the time steps with the correlation relationship, including: For each network layer, sample features of the network layer in any two time step processing are selected from the obtained sample features, and the similarity between the two selected sample features is calculated; If the calculated similarity is greater than the similarity threshold, the time step corresponding to the two selected sample features is determined to be the time step with the correlation relationship, and the network layer is used as the relevant network layer corresponding to the time step with the correlation relationship.

8. A video processing device, characterized in that: The device comprises: An acquisition module is configured to acquire a video frame to be processed and processing indication information of the video frame to be processed; the processing indication information is used to indicate a time step with a correlation relationship; The iteration module is configured to determine, during the processing of each time step of the preset time step, whether there is a first related time step related to the current time step according to the processing indication information; the first related time step is the time step before the current time step; if the first related time step exists, obtain the image semantic features of the current time step according to the processing indication information and the cache information; perform repair processing on the to-be-processed video frame according to the image semantic features of the current time step to obtain the repair result of the current time step; The processing module is configured to obtain a target video frame of the to-be-processed video frame according to a restoration result obtained by processing at the last time step.

9. An electronic device, characterized in that: include: processor; A memory for storing the processor executable instructions; wherein the processor is configured to execute the executable instructions to implement the video processing method according to any one of claims 1 to 7. 10 . A computer-readable storage medium, when instructions in the computer-readable storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the video processing method according to any one of claims 1 to 7.

11. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the video processing method according to any one of claims 1 to 7 is implemented.

Images