Video processing method and device for virtual scene and electronic equipment

Abstract

The invention provides a video processing method and device for a virtual scene, electronic equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: displaying a virtual object and a video acquisition control in a virtual scene; in response to a trigger operation for the video acquisition control, displaying at least one candidate mirror moving template, the mirror moving template being used for representing a movement track of a lens in a video shooting process; in response to a selection operation for the at least one candidate mirror moving template, displaying a lens editing control used for adjusting a target mirror moving template, the target mirror moving template being the selected mirror moving template; a video of the virtual scene is generated, and the video is obtained by shooting the virtual object through the adjusted target mirror moving template. According to the method and the device, the player can be allowed to adjust the mirror moving template to customize the video content, so that the video generation effect and the player experience are improved.

Description

Technical Field

[0001] The present application relates to the field of computer human-computer interaction technology, and in particular to a method, device, electronic device, computer-readable storage medium, and computer program product for processing a video of a virtual scene. Background Art

[0002] Display technology based on graphics processing hardware has expanded the channels for perceiving the environment and obtaining information. In particular, display technology for virtual scenes can achieve diversified interactions between virtual objects controlled by users (or players) or artificial intelligence according to actual application needs. It has various typical application scenarios. For example, in virtual scenes such as games, it can simulate the real battle process between virtual objects.

[0003] Taking Massive Multiplayer Online Role-Playing Game (MMORPG) as an example, in the solutions provided by related technologies, when players want to shoot videos, they can only choose from several sets of camera templates provided by the game platform, and cannot customize them according to the player's needs. As a result, the generated video effect is relatively simple, which in turn leads to a poor player experience. Summary of the Invention

[0004] The embodiments of the present application provide a method, device, electronic device, computer-readable storage medium, and computer program product for processing a virtual scene video, which can allow players to adjust the camera template to customize the video content, thereby improving the video generation effect and player experience.

[0005] The technical solution of the embodiment of the present application is implemented as follows:

[0006] The present invention provides a method for processing a video of a virtual scene, including:

[0007] Display virtual objects and video acquisition controls in a virtual scene;

[0008] In response to a trigger operation on the video acquisition control, displaying at least one candidate camera movement template, wherein the camera movement template is used to represent a movement trajectory of a lens during video shooting;

[0009] In response to a selection operation on the at least one candidate camera movement template, displaying a lens editing control for adjusting a target camera movement template, wherein the target camera movement template is the selected camera movement template;

[0010] A video of the virtual scene is generated, wherein the video is obtained by shooting the virtual object using the adjusted target camera template.

[0011] The embodiment of the present application provides a video processing device for a virtual scene, comprising:

[0012] A display module, used to display virtual objects and video acquisition controls in a virtual scene;

[0013] The display module is further configured to display at least one candidate camera movement template in response to a trigger operation on the video acquisition control, wherein the camera movement template is used to represent a movement trajectory of the lens during video shooting;

[0014] The display module is further configured to display a lens editing control for adjusting a target camera movement template in response to a selection operation on the at least one candidate camera movement template, wherein the target camera movement template is the selected camera movement template;

[0015] A generation module is used to generate a video of the virtual scene, wherein the video is obtained by shooting the virtual object through the adjusted target camera template.

[0016] An embodiment of the present application provides an electronic device, including:

[0017] a memory for storing executable instructions;

[0018] The processor is used to implement the video processing method of the virtual scene provided in the embodiment of the present application when executing the executable instructions stored in the memory.

[0019] An embodiment of the present application provides a computer-readable storage medium storing computer-executable instructions for implementing a video processing method for a virtual scene provided in an embodiment of the present application when executed by a processor.

[0020] An embodiment of the present application provides a computer program product, including a computer program or computer executable instructions, which, when executed by a processor, implements the video processing method of the virtual scene provided in the embodiment of the present application.

[0021] The embodiments of the present application have the following beneficial effects:

[0022] After the player selects the desired target camera template from at least one candidate camera template, a lens editing control is provided for the player to adjust the target camera template. The player can adjust the target camera template through the lens editing control, and then shoot the virtual object through the adjusted target camera template to generate customized video content, thereby improving the video generation effect and player experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 11 is a schematic diagram of the architecture of a video processing system 100 for a virtual scene provided in an embodiment of the present application;

[0024] Figure 2 is a structural diagram of an electronic device 500 provided in an embodiment of the present application;

[0025] Figure 3 1 is a flow chart of a method for processing a video of a virtual scene provided in an embodiment of the present application;

[0026] Figure 4 1 is a flow chart of a method for processing a video of a virtual scene provided in an embodiment of the present application;

[0027] Figure 5 Schematic diagram of an application scenario of the video processing method of a virtual scene provided by an embodiment of the present application;

[0028] Figure 6 Schematic diagram of an application scenario of the video processing method of a virtual scene provided by an embodiment of the present application;

[0029] Figure 7 Schematic diagram of an application scenario of the video processing method of a virtual scene provided by an embodiment of the present application;

[0030] Figure 8 Schematic diagram of an application scenario of the video processing method of a virtual scene provided by an embodiment of the present application;

[0031] Figure 9 Schematic diagram of an application scenario of the video processing method of a virtual scene provided by an embodiment of the present application;

[0032] Figure 10 Schematic diagram of an application scenario of the video processing method of a virtual scene provided by an embodiment of the present application;

[0033] Figure 11 Schematic diagram of an application scenario of the video processing method of a virtual scene provided by an embodiment of the present application;

[0034] Figure 12 This is a schematic diagram of an application scenario of the video processing method for a virtual scene provided in an embodiment of the present application. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical solutions and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limiting this application. All other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0036] In the following description, reference is made to “some embodiments”, which describes a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0037] It is understandable that in the embodiments of the present application, when user information and other related data (such as data of player characters controlled by players) are involved, when the embodiments of the present application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0038] In the following description, the terms "first\second\..." are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It is understandable that "first\second\..." can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0039] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this application pertains. The terms used herein are for the purpose of describing the embodiments of this application only and are not intended to limit this application.

[0040] Before further describing the embodiments of the present application in detail, the nouns and terms involved in the embodiments of the present application are explained. The nouns and terms involved in the embodiments of the present application are subject to the following interpretations.

[0041] 1) In response to: used to indicate the conditions or states on which the executed operations depend. When the dependent conditions or states are met, one or more operations executed can be in real time or with a set delay. Unless otherwise specified, there is no restriction on the order in which the multiple operations executed are executed.

[0042] 2) Virtual scene: It is the scene displayed (or provided) when the application is running on the terminal device. The scene can be a simulation of the real world, a semi-simulation and semi-fictitious virtual environment, or a purely fictitious virtual environment. The virtual scene can be any of a two-dimensional virtual scene, a 2.5-dimensional virtual scene, or a three-dimensional virtual scene. The embodiment of the present application does not limit the dimension of the virtual scene. For example, the virtual scene may include the sky, land, ocean, etc., and the land may include environmental elements such as deserts and cities. The user can control the movement of virtual objects in the virtual scene.

[0043] 3) Virtual objects: images of various people and objects that can interact in a virtual scene, or movable objects in a virtual scene. The movable objects can be virtual characters, virtual animals, cartoon characters, etc., such as people and animals displayed in a virtual scene. For example, a virtual object can be a virtual image in a virtual scene that represents a user. A virtual scene can include multiple virtual objects, each of which has its own shape and volume in the virtual scene and occupies a part of the space in the virtual scene. In addition, the types of virtual objects can include player characters and non-player characters (i.e., NPCs), where player characters refer to game characters controlled by players in the game, and non-player characters refer to game characters controlled by non-players in the game, such as bystanders, opponents, etc.

[0044] 4) Cloud Gaming: Also known as Gaming on Demand, this involves deploying a game program on a server and running an instance of the game program (referred to as a game instance). The game instance then sends the game data generated during operation to the browser page on the user's terminal. The page then calls the browser's media component to decode the game data and renders the real-time game screen based on the decoded results. When the page detects user actions on the game screen, it reports them to the game instance running on the server. Upon receiving the game data generated by the game instance in response to the action, the decoding and rendering process is repeated, presenting the game screen on the page in response to the user's actions.

[0045] In other words, cloud gaming is an online gaming technology based on cloud computing. Cloud gaming technology enables thin clients with relatively limited graphics and data processing capabilities to run high-quality games. In a cloud gaming scenario, the game is not played on the user terminal (e.g., the player's gaming terminal), but rather on a cloud server. The cloud server renders the game scene into an audio and video stream, which is transmitted to the user terminal over the network. This eliminates the need for powerful graphics and data processing capabilities, requiring only basic streaming media playback capabilities and the ability to receive player input and send it to the cloud server.

[0046] 5) Photo function: In the game, players can click the photo button to enter the photo mode and record the characters, scenes, actions and other in-game images or video format.

[0047] The embodiments of the present application provide a method, device, electronic device, computer-readable storage medium, and computer program product for processing a video of a virtual scene, which can allow a player to adjust a selected camera template to generate customized video content. The electronic device provided by the embodiments of the present application is described below. The electronic device provided by the embodiments of the present application can be implemented as a terminal device, or can be implemented in collaboration with a terminal device and a server. The following description takes the video processing method for a virtual scene provided by the embodiments of the present application, in which a server and a terminal device collaborate to implement it, as an example.

[0048] Before introducing the architecture of the video processing system for the virtual scene provided by the embodiment of the present application, the game mode involved in the embodiment of the present application is first introduced. For the solution implemented in collaboration between the terminal device and the server, there are mainly two game modes, namely local game mode and cloud game mode, wherein the local game mode refers to the terminal device and the server collaboratively running the game processing logic, the operation instructions input by the player in the terminal device, part of which is processed by the terminal device running the game logic, and the other part is processed by the server running the game logic, and the game logic processing run by the server is often more complicated and requires more computing power; the cloud game mode refers to the game logic processing run entirely by the server (such as a cloud server), and the cloud server renders the game scene data into an audio and video stream, which is then transmitted to the terminal device via the network for display. In other words, the terminal device only needs to have basic streaming media playback capabilities and the ability to obtain the player's operation instructions and send them to the server.

[0049] The architecture of the video processing system for the virtual scene provided in the embodiment of the present application is described below.

[0050] For example, see Figure 1 , Figure 1 This is a schematic diagram of the architecture of a video processing system 100 for a virtual scene provided by an embodiment of the present application, which is used to support the application of allowing players to adjust the selected camera template to customize the generated video content, such as Figure 1 As shown, the video processing system 100 of the virtual scene includes: a server 200, a network 300 and a terminal device 400, wherein the server 200 is a background server (such as a game background server) of the client 410 running on the terminal device 400, the network 300 can be a local area network or a wide area network, or a combination of the two, the terminal device 400 is a terminal device associated with the player, and a client 410 runs on the terminal device 400. The client 410 can be various types of game clients, such as MMORPG clients, shooting game clients, role-playing game clients, and browsers.

[0051] In some embodiments, a virtual scene may be displayed in the human-computer interaction interface of the client 410. A virtual object (e.g., a game character currently controlled by a player) and a video capture control (e.g., a "one-click video" button) may be displayed in the virtual scene. The client 410 may display at least one candidate camera template in the virtual scene in response to a player's triggering operation (e.g., a click operation, a slide operation, etc.) on the video capture control. The camera template may be used to represent the movement trajectory of the lens during video shooting. Subsequently, the client 410 may display lens editing controls (e.g., including lens push-pull controls and lens offset controls) for adjusting the target camera template (i.e., the selected camera template) in the virtual scene in response to the player's selection operation on at least one candidate camera template. The player may adjust the parameters of the target camera template through the lens editing controls. Finally, the client 410 may generate a video of the virtual scene. The video may be obtained by shooting the virtual object using the adjusted target camera template. For example, the lens may be controlled to shoot the virtual object according to the adjusted target camera template to obtain a video of the virtual scene.

[0052] It should be noted that the virtual scene in the video processing method of the virtual scene provided in the embodiment of the present application can be completely based on the output of the terminal device, or based on the collaborative output of the terminal device and the server. For example, it can completely rely on the computing power of the graphics processing hardware of the terminal device 400 to complete the calculation and output of the relevant data of the virtual scene, wherein the types of graphics processing hardware include central processing units (CPUs) and graphics processing units (GPUs). For example, when forming the visual perception of the virtual scene, the terminal device 400 calculates the data required for display through the graphics computing hardware, and completes the loading, parsing and rendering of the display data, and outputs the video frames that can form a visual perception of the virtual scene in the graphics output hardware, for example, presenting a two-dimensional video frame on the display screen of a smartphone, or projecting a video frame on the lenses of augmented reality / virtual reality glasses to achieve a three-dimensional display effect; in addition, in order to enrich the perception effect, the terminal device 400 can also use different hardware to form one or more of auditory perception, tactile perception, motion perception and taste perception.

[0053] Of course, it is also possible to rely on the computing power of the server 200 to complete the virtual scene calculation and output the virtual scene on the terminal device 400. For example, taking the visual perception of the virtual scene as an example, the server 200 calculates the virtual scene-related display data (such as scene data) and sends it to the terminal device 400 through the network 300. The terminal device 400 relies on the graphics computing hardware to complete the loading, parsing and rendering of the calculated display data, and relies on the graphics output hardware to output the virtual scene to form visual perception. For example, a two-dimensional video frame can be presented on the display screen of a smartphone, or a video frame with a three-dimensional display effect can be projected on the lenses of augmented reality / virtual reality glasses. As for the perception of the form of the virtual scene, it can be understood that the corresponding hardware output of the terminal device 400 can be used, such as using a microphone to form auditory perception, using a vibrator to form tactile perception, and so on.

[0054] In other embodiments, the embodiments of the present application can also be implemented with the help of cloud technology. Cloud technology refers to a hosting technology that unifies a series of resources such as hardware, software, and network within a wide area network or local area network to realize data calculation, storage, processing, and sharing.

[0055] Cloud technology is a general term for network, information, integration, management platform, and application technologies used in the cloud computing business model. It can form a resource pool that can be used flexibly and conveniently on demand. Cloud computing technology will become a key support. The backend services of technical network systems require a large amount of computing and storage resources.

[0056] For example, Figure 1 The server 200 in the embodiment 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, content distribution networks (CDNs), and big data and artificial intelligence platforms. The terminal device 400 can be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, a car terminal, a virtual reality device, an augmented reality device, etc., but is not limited to this. The terminal device 400 and the server 200 can be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiments of the present application.

[0057] In some embodiments, the terminal device or server can also implement the video processing method of the virtual scene provided in the embodiment of the present application by running various computer executable instructions or computer programs. For example, computer executable instructions can be commands, machine instructions or software instructions at the microprogram level. The computer program can be a native program or software module in the operating system; it can be a local (Native) application (APPlication, APP), that is, a program that needs to be installed in the operating system to run, such as a game APP; it can also be a small program that can be embedded in any APP, that is, a program that can be run only by downloading it to a browser environment. In short, the above-mentioned computer executable instructions can be instructions in any form, and the above-mentioned computer program can be an application, module or plug-in in any form.

[0058] The following continues to describe the structure of the electronic device provided by the embodiment of the present application. Take the electronic device as an example, see Figure 2 , Figure 2 is a structural diagram of an electronic device 500 provided in an embodiment of the present application, Figure 2 The electronic device 500 shown includes: at least one processor 510, a memory 550, at least one network interface 520 and a user interface 530. The various components in the electronic device 500 are coupled together via a bus system 540. It is understood that the bus system 540 is used to achieve connection and communication between these components. In addition to including a data bus, the bus system 540 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, the bus system 540 is not shown in FIG. Figure 2 Various buses are labeled as bus system 540 .

[0059] The processor 510 can be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., where the general-purpose processor can be a microprocessor or any conventional processor, etc.

[0060] The user interface 530 includes one or more output devices 531 that enable presentation of media content, including one or more speakers and / or one or more visual display screens. The user interface 530 also includes one or more input devices 532, including user interface components that facilitate user input, such as a keyboard, mouse, microphone, touch screen display, camera, other input buttons and controls.

[0061] The memory 550 may be removable, non-removable, or a combination thereof. Exemplary hardware devices include solid-state memory, hard drives, optical drives, etc. The memory 550 may optionally include one or more storage devices that are physically remote from the processor 510.

[0062] The memory 550 includes volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory may be a read-only memory (ROM), and the volatile memory may be a random access memory (RAM). The memory 550 described in the embodiments of the present application is intended to include any suitable type of memory.

[0063] In some embodiments, the memory 550 can store data to support various operations, examples of which include programs, modules, and data structures, or a subset or superset thereof, as exemplified below.

[0064] Operating system 551, including system programs for processing various basic system services and performing hardware-related tasks, such as the framework layer, core library layer, driver layer, etc., for implementing various basic services and processing hardware-based tasks;

[0065] A network communication module 552 for reaching other computing devices via one or more (wired or wireless) network interfaces 520 , exemplary network interfaces 520 including Bluetooth, WiFi, and USB;

[0066] a presentation module 553 for enabling presentation of information via one or more output devices 531 (e.g., a display screen, a speaker, etc.) associated with the user interface 530 (e.g., a user interface for operating peripheral devices and displaying content and information);

[0067] The input processing module 554 is configured to detect one or more user inputs or interactions from one of the one or more input devices 532 and to translate the detected inputs or interactions.

[0068] In some embodiments, the apparatus provided in the embodiments of the present application may be implemented in software. Figure 2The video processing device 555 of the virtual scene stored in the memory 550 is shown, which can be software in the form of programs and plug-ins, including the following software modules: display module 5551, generation module 5552, prediction module 5553, training module 5554, control module 5555, determination module 5556, acquisition module 5557, storage module 5558 and sharing module 5559. These modules are logical and can be arbitrarily combined or further split according to the functions implemented. It should be pointed out that in Figure 2 For the sake of convenience, all the above modules are shown at once, but it should not be considered that the video processing device 555 in the virtual scene excludes the implementation that can only include the display module 5551 and the generation module 5552. The functions of each module will be explained below.

[0069] The video processing method for the virtual scene provided in the embodiment of the present application will be specifically described below in combination with the exemplary application and implementation of the terminal device provided in the embodiment of the present application.

[0070] For example, see Figure 3 , Figure 3 This is a flow chart of the video processing method of the virtual scene provided by the embodiment of the present application, which will be combined with Figure 3 The steps shown are explained.

[0071] It should be noted that Figure 3 The illustrated methods can be executed by various computer programs running on a terminal device, not limited to a client. For example, they can also be executed by the operating system, software module, script, and applet described above. Therefore, the examples below using a client should not be considered as limiting the embodiments of the present application. In addition, for ease of description, the following description does not specifically distinguish between a terminal device and a client running on the terminal device.

[0072] In step 101, a virtual object and a video acquisition control are displayed in a virtual scene.

[0073] In some embodiments, taking the game character A controlled by player 1 as an example, a client (such as a game APP) can be run on the terminal device associated with player 1, and a virtual scene can be displayed in the human-computer interaction interface of the client, wherein the virtual scene can include game character A and video acquisition controls (such as a "one-click video" button). For example, the "one-click video" button can be displayed in the upper left corner of the virtual scene.

[0074] In other embodiments, the virtual scene may be displayed in the human-computer interaction interface of the client from a first-person perspective (for example, the current player plays the virtual object in the game from his own perspective); or from a third-person perspective (for example, the player chases the virtual object in the game to play the game); or from a bird's-eye view perspective; wherein, the above-mentioned different perspectives can be switched arbitrarily.

[0075] For example, a virtual object can be a game character controlled by the current player in the game. Of course, the virtual scene can also include other virtual objects, such as those controlled by other users or bots. Virtual objects can be assigned to any of multiple teams, and the teams can be in adversarial or collaborative relationships. Teams in the virtual scene can include any or all of these relationships.

[0076] Taking the first-person perspective as an example, the virtual scene displayed in the human-computer interaction interface can include: determining the virtual object's field of view based on the virtual object's viewing position and field of view within the complete virtual scene, and presenting the portion of the virtual scene within the field of view within the complete virtual scene. In other words, the displayed virtual scene can be a portion of the virtual scene relative to the panoramic virtual scene. Because the first-person perspective is the most impactful viewing angle for users, it can achieve an immersive experience for players during operation.

[0077] Taking the bird's-eye view of a virtual scene as an example, the virtual scene displayed in the human-computer interaction interface may include: in response to a zoom operation on a panoramic virtual scene, a portion of the virtual scene corresponding to the zoom operation is presented in the human-computer interaction interface, that is, the displayed virtual scene may be a portion of the virtual scene relative to the panoramic virtual scene. In this way, the operability of the player during the operation can be improved, thereby improving the efficiency of human-computer interaction. In addition, the above-mentioned different perspectives can also be switched. For example, assuming that the virtual scene is currently displayed from a first-person perspective, when a perspective switching operation triggered by the player is received, the first-person perspective can be switched to a bird's-eye view.

[0078] In step 102, in response to a trigger operation on a video acquisition control, at least one candidate camera movement template is displayed.

[0079] Here, the camera movement template can be used to represent the movement trajectory of the lens during video shooting.

[0080] In some embodiments, the above-mentioned display of at least one (i.e., one or more) candidate camera movement templates can be achieved in the following manner: in response to the first tab control (e.g., the "Camera Movement Template" tab control) being selected, at least one candidate camera movement template provided by the server (i.e., the camera movement template provided by the game platform) is displayed in the candidate camera movement template list; in response to the second tab control (e.g., the "My Template" tab control) being selected, at least one candidate camera movement template created by the target object (e.g., player 1) (i.e., the camera movement template created by the player himself) is displayed in the candidate camera movement template list, wherein the virtual object is controlled by the target object. In this way, different types of camera movement templates are classified and displayed through the first tab control and the second tab control, thereby improving the efficiency of players in finding camera movement templates.

[0081] In other embodiments, when there are multiple candidate camera movement templates, the above-mentioned display of at least one candidate camera movement template can also be achieved in the following manner: multiple candidate camera movement templates are displayed in the candidate camera movement template list in one of the following orders: order from most to least times used (that is, the more popular camera movement templates are ranked higher), order from late to early release time (that is, the newer camera movement templates are ranked higher), and order from late to early time of most recent use (that is, the camera movement templates closer to the current moment are ranked higher).

[0082] For example, take 5 candidate camera templates as an example, assuming that they are camera template 1 to camera template 5, among which camera template 1 has been used 100 times in the past month (for example, 100 players have selected camera template 1 in the past month), camera template 2 has been used 50 times in the past month, camera template 3 has been used 60 times in the past month, camera template 4 has been used 20 times in the past month, and camera template 5 has been used 40 times in the past month. The order of arrangement of these 5 camera templates in the candidate camera template list can be: camera template 1, camera template 3, camera template 2, camera template 5, camera template 4. In other words, the more popular camera template is ranked higher in the candidate camera template list, which is convenient for players to choose.

[0083] In some embodiments, when there are multiple candidate camera movement templates, the above-mentioned display of at least one candidate camera movement template can also be achieved in the following way: display some of the multiple camera movement templates in the candidate camera movement template list; in response to a switching operation (for example, a sliding operation on any of the partial camera movement templates), switch to display another part of the multiple camera movement templates (for example, the remaining camera movement templates) in the candidate camera movement template list.

[0084] For example, taking multiple candidate camera templates as 10 candidate camera templates, assuming that they are camera template 1 to camera template 10 respectively, when the candidate camera template list cannot accommodate these 10 camera templates at the same time, some of the 10 camera templates can be displayed in the candidate camera template list first, for example, camera template 1 to camera template 5 can be displayed in the candidate camera template list first, if the player is not satisfied with the currently displayed 5 and camera templates, switching can be performed, for example, when receiving a switching operation triggered by the player, another part of the 10 camera templates can be switched to display in the candidate camera template, for example, camera template 6 to camera template 10 can be switched to display in the candidate camera template list.

[0085] In other embodiments, the above-mentioned display of at least one candidate camera movement template can also be achieved in the following manner: based on the feature data corresponding to the at least one candidate camera movement template (such as video duration, lens effects, etc.), calling the first machine learning model to perform prediction processing to obtain the score corresponding to each camera movement template; for the camera movement template with a score greater than a score threshold in the at least one candidate camera movement template, applying a first display style (such as highlighting or flashing) for display; for the camera movement template with a score less than the score threshold in the at least one candidate camera movement template, applying a second display style for display, wherein the prominence of the first display style is greater than the prominence of the second display style. In other words, the camera movement template with a high score in the at least one candidate camera movement template can be highlighted to recommend it to the player, thereby saving the player the time needed to select the camera movement template.

[0086] In some embodiments, continuing with the above example, before calling the first machine learning model for prediction processing, the first machine learning model can also be trained in the following manner: obtaining a sample camera movement template with a label; based on the feature data of the sample camera movement template, calling the initialized first machine learning model for prediction processing to obtain the score of the sample camera movement template; determining the error between the score and the label, and performing back propagation based on the error, and updating the parameters of the first machine learning model during the back propagation.

[0087] For example, the exemplary structure of the first machine learning model may include: an input layer (i.e., an embedding layer), an encoding layer (e.g., composed of multiple cascaded convolutional layers), a fully connected layer, and an output layer (including an activation function, such as a Softmax function). After obtaining the feature data of the sample camera template, the feature data of the sample camera template can first be input into the input layer for embedding processing, and then the embedded feature vector output by the input layer can be encoded by the encoding layer to obtain a hidden layer feature vector, and then the hidden layer feature vector can be fully connected by the fully connected layer. Finally, the fully connected result output by the fully connected layer can be input into the output layer so that the output layer performs activation processing, thereby obtaining the score of the sample camera template. After obtaining the score of the sample camera template, the predicted score and the label (i.e., the pre-labeled score) can be substituted into the loss function to obtain the corresponding difference, and back propagation can be performed based on the difference, so that the parameters of the first machine learning model can be updated layer by layer during the back propagation process to obtain the trained first machine learning model.

[0088] It should be noted that the above-mentioned first machine learning model can be a neural network model (such as a convolutional neural network, a deep convolutional neural network, or a fully connected neural network), a decision tree model, a gradient boosting tree, a multi-layer perceptron, and a support vector machine, etc. The embodiment of the present application does not specifically limit the type of the first machine learning model.

[0089] In step 103, in response to a selection operation on at least one candidate camera movement template, a shot editing control for adjusting the target camera movement template is displayed.

[0090] Here, the lens editing control may include at least one of a lens push-pull control and a lens offset control, and the target lens movement template is a lens movement template selected from at least one candidate lens movement template.

[0091] In some embodiments, taking the lens editing control as a lens push-pull control as an example, wherein the lens push-pull control can be used to adjust the offset of the lens associated with the target camera template on the first reference axis (for example, the X-axis), then before executing step 104, the following processing can also be performed: in response to a drag operation in a first direction (for example, an upward direction) of the lens push-pull control, the distance between the lens and the virtual object is increased (that is, the lens is zoomed out); in response to a drag operation in a second direction (for example, a downward direction) of the lens push-pull control, the distance between the lens and the virtual object is reduced (that is, the lens is zoomed in).

[0092] In other embodiments, taking the lens editing control as a lens offset control as an example, wherein the lens offset control can be used to adjust the offset of the lens associated with the target camera template on the second reference axis (e.g., Z axis) and the third reference axis (e.g., Y axis), then before executing step 104, the following processing can also be performed: in response to the coordinate adjustment operation based on the lens offset control, the lens is controlled to offset in the direction specified by the coordinate adjustment operation.

[0093] For example, the lens offset control may include multiple directional controls (e.g., an upward directional control, a downward directional control, a left directional control, and a right directional control) and a joystick control. The above-mentioned control of controlling the lens to shift in the direction specified by the coordinate adjustment operation in response to the lens offset control may be implemented in the following manner: in response to a trigger operation on a target directional control (e.g., an upward directional control), controlling the lens to shift in the direction indicated by the target directional control (i.e., the upward direction), wherein the target directional control is a directional control selected from the multiple directional controls, and the distance of the lens shift is positively correlated with the duration of the trigger operation (e.g., the longer the player presses the target directional control, the farther the lens shifts in the direction indicated by the target directional control); and in response to a drag operation on the joystick control, controlling the lens to shift in the direction of the drag operation. That is, the player can control the lens to shift in one direction (e.g., upward) using the directional controls, or can control the lens to shift in two directions simultaneously using the joystick control. For example, if the player drags the joystick control toward the lower right corner, the lens shifts downward and right at the same time.

[0094] In some embodiments, when displaying the lens editing control for adjusting the target camera movement template, the following processing can also be performed: displaying a candidate action list in a virtual scene, wherein the candidate action list includes at least one candidate action; in response to a selection operation for at least one candidate action, the selected candidate action is used as the action performed by the virtual object during the video shooting process.

[0095] For example, taking at least one candidate action as 5 candidate actions, when displaying the lens editing control for adjusting the target camera movement template (such as camera movement template 1), a candidate action list can also be displayed in the virtual scene. Five candidate actions can be displayed in the candidate action list, assuming that they are candidate action 1 to candidate action 5. Then, assuming that the player selects candidate action 2 from these 5 candidate actions, for example, when the player clicks on candidate action 2 displayed in the candidate action list, candidate action 2 can be used as the action that the virtual object needs to perform during the video shooting process. For example, when the video is shot to the 10th second, the virtual object will perform candidate action 2.

[0096] In other embodiments, the candidate action list may further include at least one of the following video setting parameters: whether to enable a slow motion effect, whether to enable lens effects, and whether to loop the action. In this case, one of the following processes may be performed: in response to setting the slow motion effect to be enabled in the candidate action list, the slow motion effect is enabled during the process of video shooting of the virtual object using the adjusted target camera template; in response to setting the lens effects to be enabled in the candidate action list, the lens effects are enabled during the process of video shooting of the virtual object using the adjusted target camera template; in response to setting the loop action in the candidate action list, the virtual object is controlled to loop the selected candidate action during the process of video shooting of the virtual object using the adjusted target camera template. That is, before shooting a video, in addition to setting the action of the virtual object, the player may also set video parameters such as whether to enable a slow motion effect, whether to enable lens effects, and whether to loop the action, thereby further enhancing the player experience.

[0097] In some embodiments, when there are multiple candidate actions, the multiple candidate actions can be arranged in the candidate action list in one of the following orders: the number of times the candidate action is selected from most to least (that is, the more popular the candidate action is, the higher it is ranked), the time when the candidate action was last selected from near to far from the current time (that is, the candidate action closer to the current moment is ranked higher), and the release time of the candidate action from late to early (that is, the later the candidate action is released, the higher it is ranked). In this way, multiple candidate actions are arranged in a certain order to facilitate players' selection and save players' time in selecting candidate actions.

[0098] In some embodiments, the above-mentioned display of the candidate action list in the virtual scene can also be achieved in the following manner: based on the feature data corresponding to at least one candidate action (for example, including the complexity of the action, the type, the degree of matching with the virtual object, etc.), the second machine learning model is called for prediction processing to obtain the score corresponding to each candidate action; for at least one candidate action with a score greater than a score threshold, a third display style (for example, a highlight or flashing manner) is applied to display it in the candidate action list; for at least one candidate action with a score less than a score threshold, a fourth display style is applied to display it in the candidate action list, wherein the prominence of the third display style is greater than the prominence of the fourth display style. In other words, a candidate action with a high score in at least one candidate action can be highlighted to recommend it to the player, thereby saving the player the time needed to spend on selecting a candidate action.

[0099] In some embodiments, when there are multiple candidate actions, the above-mentioned response to the selection operation of at least one candidate action, where the selected candidate action is used as the action performed by the virtual object during the video shooting process, can be achieved in the following manner: in response to multiple candidate actions being selected, the execution order set for the multiple selected candidate actions is obtained; in the process of video shooting of the virtual object through the adjusted target camera template, the virtual object is controlled to execute the multiple selected candidate actions in sequence according to the execution order.

[0100] For example, taking multiple candidate actions as 10 candidate actions, assuming they are candidate actions 1 to candidate actions 10, and assuming that the player simultaneously selects candidate action 2, candidate action 4, candidate action 5 and candidate action 8 from these 10 candidate actions, the player can further set the execution order of the 4 selected candidate actions. For example, assuming that the execution order set by the player is: candidate action 4, candidate action 8, candidate action 2, candidate action 5, then in the process of shooting a video of the virtual object through the adjusted target camera template, the virtual object can be controlled to first execute candidate action 4 (for example, when the shooting time of the video reaches the 4th second, the virtual object is controlled to execute candidate action 4), then execute candidate action 8 (for example, when the shooting time of the video reaches the 7th second, the virtual object is controlled to execute candidate action 8), then execute candidate action 2 (for example, when the shooting time of the video reaches the 10th second, the virtual object can be controlled to execute candidate action 2), and finally execute candidate action 5 (for example, when the shooting time of the video reaches the 13th second, the virtual object can be controlled to execute candidate action 5).

[0101] It should be noted that, when the player does not set an execution order for the selected multiple candidate actions, the order in which the player selects the multiple candidate actions can be used as the execution order of the multiple candidate actions. This embodiment of the present application does not specifically limit this.

[0102] In other embodiments, the above-mentioned response to the selection operation for at least one candidate action, using the selected candidate action as the action performed by the virtual object during the video shooting process can also be achieved in the following way: in response to the selection operation for at least one candidate action, obtaining the time point set for the selected candidate action; in the process of video shooting of the virtual object through the adjusted target camera template, when the shooting time reaches this time point, controlling the virtual object to perform the selected candidate action.

[0103] For example, assuming that at least one candidate action is four candidate actions, assuming they are candidate actions 1 to candidate actions 4, after the player selects the candidate action they want (for example, candidate action 2) from these four candidate actions, they can also set the time point at which the virtual object performs candidate action 2 during the video shooting process. For example, assuming the time point set by the player is the 10th second, then during the video shooting of the virtual object using the adjusted target camera template, when the shooting time reaches the 10th second, the virtual object can be controlled to perform candidate action 2. In other words, the player can not only set the action to be performed by the virtual object, but also the time point at which the virtual object performs the action, further enhancing the player experience.

[0104] In some embodiments, when displaying the lens editing control for adjusting the target camera template, the following processing can also be performed: displaying a clothing editing control (such as a dress editing bar) in a virtual scene, wherein the clothing editing control includes at least one time node control, and each time node control is used to edit the clothing (or outfit) of the virtual object at a corresponding time point during the video shooting process.

[0105] For example, taking the target camera template as camera template 1, when the player selects camera template 1 from the candidate camera template list, in addition to displaying the lens editing control for adjusting the parameters of camera template 1 in the virtual scene, the clothing editing control can also be displayed, wherein the clothing editing control can include 3 time node controls, for example, assuming that they are time node control 1, time node control 2 and time node control 3, wherein the time point corresponding to time node control 1 can be the 5th second (that is, time node control 1 can be used to edit the clothing of the virtual object when the video is shot to the 5th second), the time point corresponding to time node control 2 can be the 10th second (that is, time node control 2 can be used to edit the clothing of the virtual object when the video is shot to the 10th second), and the time point corresponding to time node control 3 can be the 15th second (that is, time node control 3 can be used to edit the clothing of the virtual object when the video is shot to the 15th second).

[0106] In some embodiments, the length of the clothing editing control can be positively correlated with the duration of the video, and the number of at least one time node control can be positively correlated with the duration of the video. In other words, the longer the video shot associated with the target camera template, the longer the clothing editing control. In other words, the clothing editing control can include more time node controls, making it easier for players to edit at different time points.

[0107] In other embodiments, continuing with the above example, after displaying the clothing editing control in the virtual scene, the following processing can also be performed: in response to a trigger operation on a target time node control, a candidate clothing list is displayed, wherein the target time node control is a time node control selected from at least one time node control, and the candidate clothing list includes at least one candidate clothing; in response to a selection operation on at least one candidate clothing, during the video shooting of the virtual object through the adjusted target camera template, when the shooting time reaches the time point corresponding to the target time node control, the clothing of the virtual object is replaced with the selected candidate clothing.

[0108] For example, taking at least one time node control as 3 time node controls, assuming they are time node control 1, time node control 2 and time node control 3, wherein the time point corresponding to time node control 1 is the 5th second, the time point corresponding to time node control 2 is the 10th second, and the time point corresponding to time node control 3 is the 15th second, assuming that the player selects time node control 2 from the clothing editing control, a candidate clothing list can be displayed, wherein 4 candidate clothing items can be displayed in the candidate clothing list, for example, assuming they are candidate clothing 1, candidate clothing 2, candidate clothing 3 and candidate clothing 4, assuming that the player selects candidate clothing 2 from the candidate clothing list, then in the process of shooting a video of the virtual object through the adjusted target camera template, when the shooting time reaches the time point corresponding to time node control 2 (i.e., the 10th second), the clothing of the virtual object can be replaced with candidate clothing 2, thereby further improving the video effect.

[0109] In step 104 , a video of the virtual scene is generated.

[0110] Here, the video may be obtained by shooting the virtual object using the adjusted target camera template, for example, the video may be obtained by controlling the lens to shoot the virtual object according to the adjusted target camera template.

[0111] In some embodiments, a video generation control may also be displayed in the virtual scene. Figure 3 Step 104 shown may be performed by Figure 4 Steps 1041 and 1042 shown are implemented by combining Figure 4 The steps shown are explained.

[0112] In step 1041 , in response to a trigger operation for generating a video control, a transition animation is played.

[0113] In some embodiments, upon receiving a trigger operation (e.g., a click operation) from a player on a control for generating a video, a transition animation may be played, and while the transition animation is playing, the camera is controlled to shoot the virtual object according to the adjusted target camera template to obtain a video of the virtual scene. In other words, in order to prevent players from waiting in vain, embodiments of the present application play transition animations while the video is being generated to reduce boredom for the player.

[0114] In step 1042 , in response to the completion of the transition animation, a video obtained by shooting the virtual object using the adjusted target camera template is played.

[0115] In some embodiments, when it is detected that the transition animation has finished playing, a video obtained by shooting the virtual object through the adjusted target camera template can be played, and the video is generated during the transition animation playing.

[0116] In other embodiments, at least one of a save video control and a save template control may be displayed in the video playback interface, and the following processing may also be performed: in response to a trigger operation for the save video control, the video is stored in a terminal device (i.e., local storage) or a server; in response to a trigger operation for the save template control, a template name edit box is displayed; the input template name is received through the template name edit box; the adjusted target camera movement template is saved as a camera movement template created by the target object (i.e., "My Template"), wherein the name of the camera movement template is the input template name.

[0117] For example, a save video control can be displayed in the video playback interface, for example, the save video control can be displayed in the lower left corner of the video playback interface. When a player triggers an operation (such as a click operation) to save the video control, the generated video can be stored locally on the terminal device, or the generated video can be sent to a server (such as a game background server) via the network for storage on the server.

[0118] For example, a save template control can also be displayed in the video playback interface. For example, the save template control can be displayed in the lower left corner of the video playback interface. For example, the save video control and the save template control can be displayed side by side. When the player's trigger operation for the save template control (such as a click operation) is received, the template name edit box can be displayed in a pop-up window, and the player can enter the template name in the template name edit box. For example, after receiving the template name entered by the player in the template name edit box, the adjusted target camera template can be saved as a camera template created by the player (ie "My Template"), and the name of the camera template is the template name entered by the player in the template name edit box.

[0119] In other embodiments, sharing controls corresponding to at least one social platform may also be displayed in the video playback interface, and the following processing may also be performed: in response to a trigger operation on a target sharing control, the video is shared to the social platform corresponding to the target sharing control, wherein the target sharing control is the sharing control selected from the sharing controls corresponding to at least one social platform.

[0120] For example, taking the case where there are three sharing controls corresponding to at least one social platform, assuming that they are sharing control 1 corresponding to social platform 1, sharing control 2 corresponding to social platform 2, and sharing control 3 corresponding to social platform 3, players can share the generated video to the corresponding social platform by clicking the sharing control corresponding to any social platform. For example, when the player clicks on sharing control 2, the generated video can be shared to social platform 2.

[0121] The video processing method for a virtual scene provided in an embodiment of the present application provides a lens editing control for adjusting the target camera template after the player selects the desired target camera template from at least one candidate camera template. The player can adjust the target camera template through the lens editing control, and then shoot the virtual object through the adjusted target camera template to generate customized video content, thereby improving the video generation effect and player experience.

[0122] Below, an MMORPG game is taken as an example to illustrate an exemplary application of the embodiment of the present application in an actual application scenario.

[0123] An embodiment of the present application provides a video processing method for a virtual scene, and adds a "one-click video" function to the in-game camera system. Players can click the "one-click video" button to open the camera template selection interface, adjust some parameters of the selected camera template, customize the video content, and generate a video with one click. The generated video can then be saved locally or shared to an external platform.

[0124] The technical solution provided by the embodiment of the present application is simple to operate and does not require players to manually move the camera. It can easily and easily customize (DIY, Do It Yourself) the movements, camera positions, clothing, and special effects of virtual objects (such as game characters) in the video, and the generated video has excellent effects and good dissemination effects.

[0125] The following is a detailed description of the video processing method for the virtual scene provided in the embodiment of the present application.

[0126] In some embodiments, players can first select a camera template from the camera template selection interface on the left to determine the camera's movement trajectory during video capture. Players can then adjust some parameters of the selected camera template, such as fine-tuning the camera's front-to-back, up-down, left-to-right, and left-to-right offsets, to adjust the overall camera curve. Players can then select an action from the action selection interface displayed on the right. During the camera movement, the game character will begin performing the action. Players can select a one-time action or loop the action until the end of the video. Furthermore, at the recommended time points configured within the template, players can click to switch between character outfits. For example, in the game's wardrobe system, there are 10 outfit combinations that players can create. Players can quickly select one and fill it in. At that point in the video, the character's outfit will automatically change, creating a seamless cross-dressing video effect without editing. Finally, players can click the "Generate Video" button to execute the shot, action, and outfit combination to generate a short video that can be previewed and saved locally or shared to external platforms. Players can also save their edited plans for easy reuse next time.

[0127] That is to say, in the technical solution provided in the embodiment of the present application, the camera movement parameters can be customized according to the needs of the players. At the same time, in addition to the lens and action, there are also custom settings for dressing and changing clothes, which facilitates the production of more dimensional video effects and improves the player's operational freedom and repeatability when using the one-click video function.

[0128] In some embodiments, see Figure 5 , Figure 5 Schematic diagram of an application scenario of the video processing method of a virtual scene provided in an embodiment of the present application. Figure 5As shown, a virtual scene 600 displays a "one-click video" control 601 and a game character 602 controlled by the current player. When the player clicks on the "one-click video" control 601, several camera templates provided by the gaming platform, such as camera template 603, camera template 604, and camera template 605, are displayed on the left side of the virtual scene 600 for the player to select. When the player selects camera template 605 from the several camera templates provided by the gaming platform, the camera can be fixed to the first frame of the selected camera template (i.e., camera template 605). At the same time, lens editing controls for adjusting the parameters of camera template 605, such as a lens push-pull control 606 and a lens offset control 607, are displayed in the virtual scene 600. The player can fine-tune the front-back offset of the camera using the lens push-pull control 606, and the up-down, left-right, and right-side offsets of the camera using the lens offset control 607, thereby adjusting the entire camera curve trajectory. In addition, multiple candidate actions can be displayed on the right side of the virtual scene 600 for the player to select. If the player selects action 608 from the multiple candidate actions, the game character 602 will perform the selected action 608 during the camera movement. The player can also select whether to enable slow motion effects 609, whether to enable camera effects 610, and whether to loop the action 611.

[0129] Continue to see Figure 5 After selecting the camera template 605, the player can also display the dress editing bar 612 in the virtual scene 600. The dress editing bar 612 can include at least one time node control for recommending a dress-up. The player can click on any time node control to switch the character's dress-up plan. For example, in the game's wardrobe system, there are 10 sets of outerwear matching plans that the player has matched themselves. The player can quickly switch and select a set to fill in. At this time point in the video, the appearance of the game character 602 will be automatically switched, thereby achieving a dress-up video effect without editing. Finally, the player can click on the "Generate Video" control 613. When the player clicks on the "Generate Video" control 613, the lens + action + outfit can be executed to generate a short video. The player can preview and save it locally, or share it to an external platform.

[0130] It should be noted that the camera movement template can contain the position information of the lens in the entire timeline (for example, including curved movement or point lens switching position) as well as some lens special effects, lens slow motion and other lens performances. After selecting any camera movement template, the player can switch the template, and the lens will display the lens effect of the template's initial point. In addition, the player can also check whether to turn on special effects and slow motion through the settings.

[0131] In other embodiments, see Figure 6 , Figure 6Schematic diagram of an application scenario of the video processing method of a virtual scene provided in an embodiment of the present application. Figure 6 As shown, the lens offset controls 607 can be used to offset the entire lens coordinates along the Z and Y axes. These controls include an upward direction control 6071 (corresponding to the positive Z direction), a rightward direction control 6072 (corresponding to the positive Y direction), a downward direction control 6073 (corresponding to the negative Z direction), a leftward direction control 6074 (corresponding to the negative Y direction), and a joystick control 6075. Each direction control supports click or long-press operations. For example, each click of the upward direction control 6071 shifts the lens one unit toward the positive Z direction, where the distance per unit is configurable. When the player long-presses the upward direction control 6071, the distance the lens shifts toward the positive Z direction can be positively correlated with the duration of the press; that is, the longer the press, the greater the lens shift. Furthermore, the player can use the joystick control 6075 to shift the lens in both directions simultaneously. For example, if the player drags the joystick control 6075 to the upper right corner, the camera can be shifted in the positive direction of the Z axis while also being shifted in the positive direction of the Y axis. The player can fine-tune the vertical and horizontal offsets of the camera using the lens offset control 607, that is, the camera will be shifted in the Z and Y axis coordinates. Figure 7 shown.

[0132] In some embodiments, see Figure 8 , Figure 8 Schematic diagram of an application scenario of the video processing method of a virtual scene provided in an embodiment of the present application. Figure 8 As shown, the lens can be offset in the X-axis coordinate through the lens push-pull control 606, wherein the lens push-pull control 606 can include an upward direction control 6061, a downward direction control 6062 and a joystick control 6063. When a click operation is received from the player for the upward direction control 6061, the lens can be controlled to be offset in the positive direction of the X-axis (i.e., the distance between the lens and the game character 602 is pulled closer); when a click operation is received from the player for the downward direction control 6062, the lens can be controlled to be offset in the negative direction of the X-axis (i.e., the distance between the lens and the game character 602 is pushed farther). In addition, the joystick control 6063 can only control the offset of the lens in the X-axis, and the effect is the same as the long press operation on the direction control. When the player fine-tunes the offset of the lens before and after through the lens push-pull control 606, that is, after the lens coordinate is offset in the X-axis (for example, the distance between the lens and the game character 602 is pushed closer), the effect is as follows. Figure 9 shown.

[0133] That is, in the technical solution provided in the embodiments of the present application, players can adjust some parameters of the selected camera template, such as fine-tuning the front-back, up-down, left-right, and up-down offsets of the lens, thereby adjusting the entire camera curve trajectory, thereby achieving the effect of adjusting the height, left-right, and distance of the camera. For example, players can fine-tune the front-back offset of the lens using the lens push-pull control, and fine-tune the up-down, left-right, and up-down offsets of the lens using the lens offset control. In addition, each camera template can also be configured with multiple recommended actions to complement the camera performance. Players can choose not to perform an action, perform a certain action once, or perform a certain action in a loop, etc. This embodiment of the present application does not specifically limit this.

[0134] In other embodiments, see Figure 10 , Figure 10 Schematic diagram of an application scenario of the video processing method of a virtual scene provided in an embodiment of the present application. Figure 10 As shown, the dress editing bar 612 can include several time node controls, which can be used to change the dressing scheme of the game character 602 between any two time nodes. For example, taking the time node control 6121 as an example, the time node control 6121 includes a dressing scheme number 61211, a dressing scheme picture 61212 and a node time point 61213 (for example, the 5th second). When the player clicks on the time node control 6121 displayed in the dress editing bar 612, the time node control 6121 can be switched to a selected state, and the dress selection bar 614 is displayed at the same time. In the dress selection bar 614, the corresponding numbers of the multiple coat matching schemes that the player has matched in the wardrobe system are displayed for the player to choose. For example, assuming that the player has selected number 6141 in the dress selection bar 614, when the video is shot to the 5th second, the appearance of the game character 602 can be automatically switched to the outerwear matching scheme corresponding to number 6141.

[0135] It should be noted that the number of time node controls corresponding to each camera movement template can be different, for example, it can be related to the duration of the video. The longer the video is, the more corresponding time node controls there are, and accordingly, the length of the dress editing bar is also longer. In addition, when the number of time node controls is greater than or equal to a quantity threshold (for example, 5), 3 of the time node controls can be displayed first, while supporting horizontal sliding. For example, when a sliding operation triggered by a player is received, another 2 time node controls can be switched to display in the dress editing bar. In addition, it should also be noted that the dress selection bar can be horizontal and fixed in position, and the length of the dress selection bar can be adaptively changed according to the number of coat matching schemes that the player matches in the wardrobe system. In addition, when the dress selection bar is called out, if the player performs other operations, the dress selection bar will be retracted and the selected state of the time node control will be cancelled.

[0136] In some embodiments, see Figure 11 , Figure 11 Schematic diagram of an application scenario of the video processing method of a virtual scene provided in an embodiment of the present application. Figure 11 As shown, after the player has edited the lens parameters, dressing scheme and action, he can click on the "Generate Video" control 613. When the player clicks on the "Generate Video" control 613, the transition animation 615 can be played first. After the transition animation 615 is played, the video 616 obtained by shooting the game character 602 can be played in full screen (i.e., a preview video effect is generated). When the video 616 is played or the player clicks on the skip control 617, a video browsing pop-up window 618 can be displayed. In the video browsing pop-up window 618, a "Save Video" control 619, a "Save Template" control 620, a "Save Local" control 621 and sharing controls corresponding to multiple social platforms can be displayed, for example, a sharing control 622 corresponding to social platform 1, a sharing control 623 corresponding to social platform 2 and a sharing control 624 corresponding to social platform 3. When a player clicks on the "Save Video" control 619, the video 616 can be saved locally. In other words, the function of the "Save Video" control 619 is the same as that of the "Save Local" control 621. When a player clicks on the "Save Template" control 620, a pop-up window 626 can be displayed, and the player can name the template in the pop-up window 626. If the player does not enter a name in the template name edit box included in the pop-up window 626, the original name of the template is used by default. In addition, the number of templates currently saved by the player and the upper limit of the number of templates that can be saved (for example, 10 / 40) can also be displayed in the pop-up window 626. When the number of templates saved by the player reaches the upper limit, the player can display a prompt message when clicking the "Save Template" control 620, such as "My number of templates has reached the upper limit!"

[0137] Continue to see Figure 11 When the player wants to share the video 616 to the social platform 1, the player can click the share control 622 corresponding to the social platform 1. When the player clicks the share control 622, the video 616 can be shared to the social platform 1. In addition, a return control 625 can be displayed in the video browsing pop-up window 618. When the player clicks the return control 625, the player can return to the one-click video interface. Before returning, the player needs to retain all changes to the currently selected template.

[0138] In other embodiments, see Figure 12 , Figure 12 Schematic diagram of an application scenario of the video processing method of a virtual scene provided in an embodiment of the present application. Figure 12As shown, players can also edit saved camera templates (i.e., "My Templates"). For example, when the "My Templates" tab control 627 is selected, several camera templates saved by the player can be displayed. Taking camera template 628 as an example, an edit control 629 can be displayed on the tab where camera template 628 is located. When the player clicks on the edit control 629, a "Modify Name" option 630 and a "Delete Template" option 631 can be displayed. When the player clicks on the "Modify Name" option 630, a pop-up window 632 can be displayed, in which the player can modify the name of camera template 628. When the player clicks on the "Delete Template" option 631, a pop-up window 633 can be displayed. When the player clicks on the confirmation control displayed in the pop-up window 633, the camera template 628 can be deleted.

[0139] The following continues to describe the video processing method for the virtual scene provided in the embodiment of the present application.

[0140] The video processing method for the virtual scene provided in the embodiment of the present application mainly includes five parts: camera template configuration, modification of camera lens parameters, selection of camera action, selection of dressing function, and saving of custom template data, which are explained below respectively.

[0141] 1. Camera template configuration

[0142] In some embodiments, the in-game skill editor can be used to edit the lens curve position in the timeline (i.e., record the coordinate position of the lens in each frame) to achieve the effect of camera movement. In addition, the in-game skill editor can also be used to edit the time period for special effects display or slow motion effects in the timeline. In addition, the in-game skill editor can also be used to edit the timeline, switching outfit 1 from frame x to frame y, switching outfit 2 from frame y to frame z, and so on, until the end of the video.

[0143] 2. Modify the lens parameters

[0144] In some embodiments, based on the camera template selected by the player and according to the player's movement of the wheel, the player can perform downward, upward, left, right, and depth offsets (i.e., the coordinate offsets of the lens on the X, Y, and Z axes), modify the lens coordinates of the camera template, and the client lens offsets the coordinate axis when moving the camera.

[0145] 3. Choose the camera movement

[0146] In some embodiments, after each camera movement template is configured, a configuration identifier (e.g., an ID) may be generated. Each camera movement template may be configured with a recommended action, and the player may select a recommended action or an action other than the recommended action. Furthermore, the player may also select to play the action once or in a loop by checking an option. When generating a video, the client may execute the operation of playing the action and, based on the checked option, determine whether to play it once and then stop or to loop the action until the camera movement ends.

[0147] 4. Select the cross-dressing function

[0148] In some embodiments, several dressing nodes can be configured in the camera template, that is, several configurable time node controls are displayed. The server can pull multiple dressing plans configured in the player's wardrobe system and fill in the dressing plan selected by the player. The client can switch the clothing appearance of the game character at the dressing time node according to the dressing plan, thereby achieving a video dressing effect.

[0149] 5. Save custom template data

[0150] In some embodiments, after the player clicks to save the template control, the client can save various parameter information, such as the initial camera template ID, the camera coordinate offset, the ID of the selected action, whether to loop the action, the outfit ID of outfit slot 1 (such as time node control 1), the outfit ID of outfit slot 2 (such as time node control 2), etc., and upload it to the server, and store the plan in my template.

[0151] To sum up, the video processing method of the virtual scene provided by the embodiment of the present application has the following beneficial effects: by generating user-generated content (UGC) video content templates with one click, and providing a simple and easy-to-operate custom adjustment function, the arrangement and combination of camera movement + action + dressing + special effects can produce diverse, rich and beautiful video effects, and can conveniently produce video content showing game characters in the game, satisfying the players' desire to create, share and social needs. At the same time, players can also share videos to external platforms, bringing about the effect of attracting traffic, thereby forming a good social communication effect.

[0152] The following continues to describe the exemplary structure of the virtual scene video processing device 555 provided in the embodiment of the present application implemented as a software module. In some embodiments, such as Figure 2 As shown, the software modules in the video processing device 555 of the virtual scene stored in the memory 550 may include: a display module 5551 and a generation module 5552.

[0153] Display module 5551 is used to display virtual objects and video acquisition controls in a virtual scene; display module 5551 is also used to display at least one candidate camera movement template in response to a trigger operation on the video acquisition control, wherein the camera movement template is used to represent the movement trajectory of the lens during the video shooting process; display module 5551 is also used to display a lens editing control for adjusting a target camera movement template in response to a selection operation on at least one candidate camera movement template, wherein the target camera movement template is the selected camera movement template; generation module 5552 is used to generate a video of a virtual scene, wherein the video is obtained by shooting the virtual object with the adjusted target camera movement template.

[0154] In some embodiments, the display module 5551 is also used to display at least one candidate camera template provided by the server in the candidate camera template list in response to the first tab control being in a selected state; and to display at least one candidate camera template created by the target object in the candidate camera template list in response to the second tab control being in a selected state, wherein the virtual object is controlled by the target object.

[0155] In some embodiments, when there are multiple candidate camera movement templates, the display module 5551 is also used to display multiple camera movement templates in the candidate camera movement template list in one of the following orders: the order of the number of times used from most to least, the order of the release time from late to early, and the order of the time of the most recent use from late to early.

[0156] In some embodiments, when there are multiple candidate camera movement templates, the display module 5551 is also used to display some of the multiple camera movement templates in the candidate camera movement template list; in response to a switching operation, another part of the multiple camera movement templates in the candidate camera movement template list is switched to display.

[0157] In some embodiments, the video processing device 555 of the virtual scene also includes a prediction module 5553, which is used to call the first machine learning model for prediction processing based on the feature data corresponding to at least one candidate camera movement template, and obtain the score corresponding to each camera movement template; the display module 5551 is also used to apply the first display style to display the camera movement template with a score greater than the score threshold in at least one candidate camera movement template; and apply the second display style to display the camera movement template with a score less than the score threshold in at least one candidate camera movement template, wherein the prominence of the first display style is greater than the prominence of the second display style.

[0158] In some embodiments, the video processing device 555 of the virtual scene also includes a training module 5554, which is used to train the first machine learning model in the following manner: obtaining a sample camera movement template with a label; based on the feature data of the sample camera movement template, calling the initialized first machine learning model to perform prediction processing to obtain the score of the sample camera movement template; determining the error between the score and the label, and performing backpropagation based on the error to update the parameters of the first machine learning model.

[0159] In some embodiments, the lens editing control includes a lens push-pull control, wherein the lens push-pull control is used to adjust the offset of the lens associated with the target camera template on the first reference axis; the video processing device 555 of the virtual scene also includes a control module 5555, which is used to increase the distance between the lens and the virtual object in response to a drag operation in a first direction of the lens push-pull control; and is used to reduce the distance between the lens and the virtual object in response to a drag operation in a second direction of the lens push-pull control.

[0160] In some embodiments, the lens editing control includes a lens offset control, wherein the lens offset control is used to adjust the offset of the lens associated with the target camera template on the second reference axis and the third reference axis; the control module 5555 is also used to control the lens to offset in the direction specified by the coordinate adjustment operation in response to the coordinate adjustment operation based on the lens offset control.

[0161] In some embodiments, the lens offset control includes multiple direction controls and a joystick control; the control module 5555 is also used to control the lens to offset in the direction indicated by the target direction control in response to a trigger operation on the target direction control, wherein the target direction control is the direction control selected from the multiple direction controls, and the distance of the lens offset is positively correlated with the duration of the trigger operation; and is used to control the lens to offset in the dragging direction of the dragging operation in response to a drag operation on the joystick control.

[0162] In some embodiments, when displaying the lens editing controls for adjusting the target camera movement template, the display module 5551 is also used to display a list of candidate actions in the virtual scene, wherein the list of candidate actions includes at least one candidate action; the video processing device 555 of the virtual scene also includes a determination module 5556, which is used to respond to a selection operation for at least one candidate action and use the selected candidate action as the action performed by the virtual object during the video shooting process.

[0163] In some embodiments, the control module 5555 is also used to perform at least one of the following processing: in response to setting the enable slow motion effect in the candidate action list, enabling the slow motion effect during the video shooting of the virtual object through the adjusted target camera template; in response to setting the enable lens special effects in the candidate action list, enabling the lens special effects during the video shooting of the virtual object through the adjusted target camera template; in response to setting the loop play action in the candidate action list, controlling the virtual object to loop the selected candidate action during the video shooting of the virtual object through the adjusted target camera template.

[0164] In some embodiments, when there are multiple candidate actions, the multiple candidate actions are arranged in the candidate action list in one of the following orders: the number of times the candidate action is selected from most to least, the time when the candidate action was last selected from the current time from near to far, and the release time of the candidate action from late to early.

[0165] In some embodiments, the prediction module 5554 is further used to call the second machine learning model for prediction processing based on the feature data corresponding to at least one candidate action to obtain a score for each candidate action; the display module 5551 is further used to apply the third display style to display in the candidate action list for at least one candidate action whose score is greater than the score threshold; and apply the fourth display style to display in the candidate action list for at least one candidate action whose score is less than the score threshold, wherein the prominence of the third display style is greater than the prominence of the fourth display style.

[0166] In some embodiments, when the number of at least one candidate action is multiple, the video processing device 555 of the virtual scene also includes an acquisition module 5557 for acquiring the execution order set for the multiple candidate actions selected in response to multiple candidate actions being selected; the control module 5555 is also used to control the virtual object to execute multiple candidate actions in sequence according to the execution order during the process of video shooting of the virtual object through the adjusted target camera template.

[0167] In some embodiments, the acquisition module 5557 is also used to obtain the time point set for the selected candidate action in response to a selection operation for at least one candidate action; the control module 5555 is also used to control the virtual object to perform the selected candidate action when the shooting time reaches the time point during the process of video shooting of the virtual object through the adjusted target camera template.

[0168] In some embodiments, when displaying the lens editing controls for adjusting the target camera template, the display module 5551 is also used to display clothing editing controls in a virtual scene, wherein the clothing editing controls include at least one time node control, and each time node control is used to edit the clothing of the virtual object at a corresponding time point during the video shooting process.

[0169] In some embodiments, the display module 5551 is also used to display a list of candidate clothing in response to a trigger operation on a target time node control, wherein the target time node control is a selected time node control among at least one time node control, and the candidate clothing list includes at least one candidate clothing; the control module 5555 is also used to respond to a selection operation on at least one candidate clothing, and in the process of video shooting of the virtual object through the adjusted target camera template, when the shooting time reaches the time point corresponding to the target time node control, the clothing of the virtual object is replaced with the selected candidate clothing.

[0170] In some embodiments, the length of the clothing editing control is positively correlated with the duration of the video, and the number of at least one time node control is positively correlated with the duration of the video.

[0171] In some embodiments, the virtual scene also includes generating a video control; the generating module 5552 is also used to play a transition animation in response to a triggering operation for generating a video control; in response to the completion of the transition animation, a video obtained by shooting the virtual object through the adjusted target camera template is played.

[0172] In some embodiments, at least one of a save video control and a save template control is displayed in the video playback interface; the video processing device 555 of the virtual scene also includes a save module 5558, which is used to store the video in a terminal device or server in response to a trigger operation for the save video control; the display module 5551 is also used to display a template name edit box in response to a trigger operation for the save template control; the save module 5558 is also used to receive an input template name through the template name edit box; the adjusted target camera template is saved as a camera template created by the target object, and the name of the camera template is the input template name.

[0173] In some embodiments, sharing controls corresponding to at least one social platform are displayed in the video playback interface; the video processing device 555 of the virtual scene also includes a sharing module 5559, which is used to share the video to the social platform corresponding to the target sharing control in response to a trigger operation on the target sharing control, wherein the target sharing control is the sharing control selected from the sharing controls corresponding to at least one social platform.

[0174] It should be noted that the description of the device of the embodiment of the present application is similar to the description of the method embodiment above, and has similar beneficial effects as the method embodiment, so it will not be repeated here. Figure 3 ,or Figure 4 The present invention should be understood by referring to the description of any one of the accompanying drawings.

[0175] The present invention provides a computer program product comprising a computer program or computer-executable instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer-executable instructions from the computer-readable storage medium and executes the computer-executable instructions, causing the computer device to perform the virtual scene video processing method described in the present invention.

[0176] The embodiment of the present application provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, the processor will execute the video processing method of the virtual scene provided by the embodiment of the present application, for example, Figure 3 ,or Figure 4 The video processing method of the virtual scene is shown.

[0177] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface storage, optical disk, or CD-ROM; or various devices including one or any combination of the above memories.

[0178] In some embodiments, executable instructions may be in the form of a program, software, software module, script, or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a stand-alone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.

[0179] As an example, executable instructions may be deployed to be executed on one electronic device, or on multiple electronic devices located at one site, or on multiple electronic devices distributed across multiple sites and interconnected by a communication network.

[0180] The above description is merely an embodiment of the present application and is not intended to limit the scope of protection of the present application. Any modifications, equivalent replacements, and improvements made within the spirit and scope of the present application are included in the scope of protection of the present application.

Claims

1. A video processing method for a virtual scene, characterized in that: The method comprises: Display virtual objects and video acquisition controls in a virtual scene; In response to a trigger operation on the video acquisition control, displaying at least one candidate camera movement template, wherein the camera movement template is used to represent a movement trajectory of a lens during video shooting; In response to a selection operation on the at least one candidate camera movement template, displaying a lens editing control for adjusting a target camera movement template, wherein the target camera movement template is the selected camera movement template; A video of the virtual scene is generated, wherein the video is obtained by shooting the virtual object using the adjusted target camera template.

2. The method according to claim 1, characterized in that The displaying of at least one candidate camera movement template includes: In response to the first tab control being in a selected state, displaying at least one candidate camera template provided by the server in the candidate camera template list; In response to the second tab control being in a selected state, at least one candidate camera template created by the target object is displayed in the candidate camera template list, wherein the virtual object is controlled by the target object.

3. The method according to claim 1, characterized in that When there are multiple at least one candidate camera movement templates, displaying at least one candidate camera movement template includes: In the candidate camera template list, multiple camera templates are displayed in one of the following orders: the order of the number of times used from most to least, the order of the release time from late to early, and the order of the time of the most recent use from late to early.

4. The method according to claim 1, wherein When there are multiple at least one candidate camera movement templates, displaying at least one candidate camera movement template includes: Displaying some of the camera movement templates in a candidate camera movement template list; In response to a switching operation, another portion of the camera movement templates among the plurality of camera movement templates is switched and displayed in the candidate camera movement template list.

5. The method according to claim 1, characterized in that The displaying of at least one candidate camera movement template includes: Based on the feature data corresponding to at least one candidate camera movement template, calling a first machine learning model to perform prediction processing to obtain a score corresponding to each of the camera movement templates; For the camera movement template with a score greater than a score threshold among the at least one candidate camera movement template, display it in a first display style; For the camera movement template with a score less than the score threshold in the at least one candidate camera movement template, a second display style is applied for display, wherein the prominence of the first display style is greater than the prominence of the second display style.

6. The method according to claim 5, characterized in that Before calling the first machine learning model to perform prediction processing, the method further includes: The first machine learning model is trained by: Obtain a sample camera template with a label; Based on the feature data of the sample camera movement template, calling the initialized first machine learning model to perform prediction processing to obtain a score for the sample camera movement template; Determine an error between the score and the label, and perform backpropagation based on the error to update parameters of the first machine learning model.

7. The method according to claim 1, characterized in that The lens editing control includes a lens push-pull control, wherein the lens push-pull control is used to adjust the offset of the lens associated with the target lens movement template on the first reference axis; Before generating the video of the virtual scene, the method further includes: In response to a drag operation in a first direction of the lens push-pull control, increasing the distance between the lens and the virtual object; In response to a drag operation in a second direction of the lens zoom control, the distance between the lens and the virtual object is reduced.

8. The method according to claim 1, characterized in that The lens editing control includes a lens offset control, wherein the lens offset control is used to adjust the offset of the lens associated with the target lens movement template on the second reference axis and the third reference axis; Before generating the video of the virtual scene, the method further includes: In response to a coordinate adjustment operation based on the lens offset control, the lens is controlled to shift toward a direction specified by the coordinate adjustment operation.

9. The method according to claim 8, characterized in that The lens shift control includes multiple direction controls and a joystick control; In response to the coordinate adjustment operation based on the lens offset control, controlling the lens to shift toward a direction specified by the coordinate adjustment operation includes: In response to a trigger operation on a target direction control, controlling the lens to shift toward a direction indicated by the target direction control, wherein the target direction control is a direction control selected from the plurality of direction controls, and a distance of the lens shift is positively correlated with a duration of the trigger operation; In response to a drag operation on the joystick control, the lens is controlled to shift toward a drag direction of the drag operation.

10. The method according to claim 1, characterized in that When displaying a lens editing control for adjusting the target lens movement template, the method further includes: Displaying a candidate action list in the virtual scene, wherein the candidate action list includes at least one candidate action; In response to a selection operation on the at least one candidate action, the selected candidate action is used as the action performed by the virtual object during video shooting.

11. The method according to claim 10, characterized in that The method further comprises: Perform at least one of the following: In response to setting the slow motion effect to be enabled in the candidate action list, enabling the slow motion effect during the process of shooting a video of the virtual object using the adjusted target camera template; In response to setting the lens effect to be enabled in the candidate action list, enabling the lens effect during the process of shooting a video of the virtual object using the adjusted target camera template; In response to setting a loop play action in the candidate action list, during the process of shooting a video of the virtual object using the adjusted target camera template, the virtual object is controlled to loop execute the selected candidate action.

12. The method according to claim 10, characterized in that When there are multiple candidate actions, the multiple candidate actions are arranged in the candidate action list in one of the following orders: the order of the number of times the candidate action is selected from most to least, the order of the time when the candidate action was most recently selected from the current time from near to far, and the order of the release time of the candidate action from late to early.

13. The method according to claim 10, characterized in that The displaying of the candidate action list in the virtual scene includes: Based on the feature data corresponding to the at least one candidate action, calling the second machine learning model to perform prediction processing to obtain a score for each candidate action; For the candidate action with a score greater than the score threshold among the at least one candidate action, display it in the candidate action list using a third display style; For the candidate action with a score less than the score threshold in the at least one candidate action, a fourth display style is applied to display the candidate action list, wherein the prominence of the third display style is greater than the prominence of the fourth display style.

14. The method according to claim 10, characterized in that When there are multiple candidate actions, in response to a selection operation on the at least one candidate action, selecting the selected candidate action as the action performed by the virtual object during the video capture process includes: In response to a plurality of the candidate actions being selected, obtaining an execution order set for the plurality of the selected candidate actions; During the process of shooting a video of the virtual object using the adjusted target camera template, the virtual object is controlled to sequentially execute the plurality of candidate actions in the execution order.

15. The method according to claim 10, characterized in that In response to the selection operation for the at least one candidate action, selecting the selected candidate action as the action performed by the virtual object during the video shooting process includes: In response to a selection operation on the at least one candidate action, obtaining a time point set for the selected candidate action; During the process of shooting a video of the virtual object using the adjusted target camera template, when the shooting time reaches the time point, the virtual object is controlled to execute the selected candidate action.

16. The method according to claim 1, wherein When displaying a lens editing control for adjusting the target lens movement template, the method further includes: Displaying a clothing editing control in the virtual scene, wherein the clothing editing control includes at least one time node control, and each time node control is used to edit the clothing of the virtual object at a corresponding time point during video shooting.

17. The method according to claim 16, characterized in that The method further comprises: In response to a trigger operation on a target time node control, displaying a candidate clothing list, wherein the target time node control is a time node control selected from the at least one time node control, and the candidate clothing list includes at least one candidate clothing; In response to the selection operation for at least one candidate clothing, during the process of shooting a video of the virtual object through the adjusted target camera template, when the shooting time reaches the time point corresponding to the target time node control, the clothing of the virtual object is replaced with the selected candidate clothing.

18. The method according to claim 16, characterized in that The length of the clothing editing control is positively correlated with the duration of the video, and the number of the at least one time node control is positively correlated with the duration of the video.

19. The method according to claim 1, wherein The virtual scene also includes generating a video control; The generating of the video of the virtual scene comprises: In response to a triggering operation on the generated video control, playing a transition animation; In response to the completion of playing the transition animation, a video obtained by shooting the virtual object using the adjusted target camera template is played.

20. The method according to claim 19, characterized in that Displaying at least one of a save video control and a save template control in the video playback interface; The method further comprises: In response to a triggering operation on the save video control, storing the video in a terminal device or a server; In response to the trigger operation for the save template control, a template name edit box is displayed; the input template name is received through the template name edit box; the adjusted target camera movement template is saved as a camera movement template created by the target object, and the name of the camera movement template is the input template name.

21. The method according to claim 19, wherein Displaying sharing controls corresponding to at least one social platform in the video playback interface; The method further comprises: In response to a triggering operation on a target sharing control, the video is shared to a social platform corresponding to the target sharing control, wherein the target sharing control is a selected sharing control from among the sharing controls corresponding to the at least one social platform.

22. A video processing device for a virtual scene, characterized in that: The device comprises: A display module, used to display virtual objects and video acquisition controls in a virtual scene; The display module is further configured to display at least one candidate camera movement template in response to a trigger operation on the video acquisition control, wherein the camera movement template is used to represent a movement trajectory of the lens during video shooting; The display module is further configured to display a lens editing control for adjusting a target camera movement template in response to a selection operation on the at least one candidate camera movement template, wherein the target camera movement template is the selected camera movement template; A generation module is used to generate a video of the virtual scene, wherein the video is obtained by shooting the virtual object through the adjusted target camera template.

23. An electronic device, characterized in that: include: a memory for storing executable instructions; The processor is configured to implement the video processing method of the virtual scene according to any one of claims 1 to 21 when executing the executable instructions stored in the memory.

24. A computer-readable storage medium storing computer-executable instructions, characterized in that: When the computer executable instructions are executed by a processor, the video processing method of the virtual scene according to any one of claims 1 to 21 is implemented.

25. A computer program product comprising a computer program or computer executable instructions, characterized in that When the computer program or computer executable instructions are executed by a processor, the video processing method of the virtual scene according to any one of claims 1 to 21 is implemented.

Images