Video generation method and apparatus, device, and storage medium

Abstract

A video generation method and apparatus, a device, and a storage medium, relating to the technical fields of computers and Internet. The method comprises: displaying a picture of a virtual scene (210); in response to a viewfinding operation for the virtual scene, displaying n viewfinding pictures obtained by capturing the virtual scene from n viewfinding viewing angles, different viewfinding pictures being obtained by capturing the virtual scene from different viewfinding viewing angles, and n being a positive integer (220); and in response to an operation for generating a video, displaying a scene display video corresponding to the virtual scene (230). The method, apparatus, device, and medium achieve automatic generation of a scene display video, simplify operation steps of users, greatly shorten the manufacturing time of the scene display video, and improve the generation efficiency of the scene display video.

Description

Video generation method, device, equipment and storage medium

[0001] This application claims priority to Chinese patent application number 202311212527.6, filed on September 18, 2023, entitled “Video Generation Method, Device, Equipment and Storage Medium,” the entire contents of which are incorporated herein by reference. Technical Field

[0002] The embodiments of the present application relate to the field of computer and Internet technologies, and in particular to a video generation method, apparatus, device, and storage medium. Background Art

[0003] Massively Multiplayer Online Game (MMO game for short) is a type of game that allows a large number of game users to interact simultaneously in a virtual world.

[0004] Massively Multiplayer Online Role-Playing Games (MMO RPGs) are a type of MMO game that allows users to explore the game world through activities such as completing quests, fighting, building homes, and interacting with others. In related technologies, after decorating their homes, users enable screen recording, use joysticks to control the camera, and then edit the video using video editing software to create the final presentation video.

[0005] Summary of the Invention

[0006] The embodiments of the present application provide a video generation method, apparatus, device, and storage medium. The technical solutions provided by the embodiments of the present application are as follows:

[0007] According to one aspect of an embodiment of the present application, a video generation method is provided, the method being executed by a computer device, the method comprising:

[0008] Displaying a picture of a virtual scene;

[0009] In response to a framing operation on the virtual scene, displaying n framing pictures obtained by photographing the virtual scene from n framing perspectives, where different framing pictures are obtained by photographing the virtual scene from different framing perspectives, and n is a positive integer;

[0010] In response to an operation for generating a video, a scene display video corresponding to the virtual scene is displayed, where the scene display video is generated based on m framing pictures among the n framing pictures, where m is a positive integer less than or equal to n.

[0011] According to one aspect of an embodiment of the present application, a video generation method is provided, the method being executed by a computer device, the method comprising:

[0012] Obtain m framing pictures obtained by shooting a virtual scene, where different framing pictures are obtained by shooting the virtual scene from different framing perspectives, and m is a positive integer;

[0013] Based on the m framed pictures, a scene display video corresponding to the virtual scene is generated.

[0014] According to one aspect of an embodiment of the present application, a video generation device is provided, the device comprising:

[0015] A display module, used for displaying images of virtual scenes;

[0016] a framing module, configured to, in response to a framing operation on the virtual scene, display n framing pictures obtained by photographing the virtual scene from n framing perspectives, wherein different framing pictures are obtained by photographing the virtual scene from different framing perspectives, and n is a positive integer;

[0017] A display module is used to display a scene display video corresponding to the virtual scene in response to an operation for generating a video, wherein the scene display video is generated based on m framing pictures among the n framing pictures, where m is a positive integer less than or equal to n.

[0018] According to one aspect of an embodiment of the present application, a video generation device is provided, the device comprising:

[0019] an acquisition module, configured to acquire m framing pictures obtained by photographing a virtual scene, wherein different framing pictures are obtained by photographing the virtual scene from different framing perspectives, and m is a positive integer;

[0020] A generation module is used to generate a scene display video corresponding to the virtual scene based on the m framing pictures.

[0021] According to one aspect of an embodiment of the present application, a computer device is provided, comprising a processor and a memory, wherein a computer program is stored in the memory, and the computer program is loaded and executed by the processor so that the computer device implements the above method.

[0022] According to one aspect of an embodiment of the present application, a non-volatile computer-readable storage medium is provided, in which a computer program is stored. The computer program is loaded and executed by a processor to enable a computer to implement the above method.

[0023] According to one aspect of an embodiment of the present application, a computer program product is provided, comprising a computer program stored in a non-volatile computer-readable storage medium. A processor of a computer device reads the computer program from the non-volatile computer-readable storage medium and executes the computer program, causing the computer device to perform the above-described method.

[0024] According to one aspect of an embodiment of the present application, a computer program is provided. The computer program is loaded and executed by a processor to enable a computer to implement the above method.

[0025] By taking multiple framing pictures in a virtual scene, which are obtained by shooting the virtual scene from different framing perspectives, a scene display video can be directly generated based on the framing pictures, thereby realizing the automation of scene display video generation. Users only need to take different framing pictures in the virtual scene, and the scene display video can be automatically generated by the device, which simplifies the user operation steps and significantly reduces the production time of the scene display video, thereby improving the generation efficiency of the scene display video, allowing users to see the scene display video as soon as possible, improving the user's interactive experience, and thus improving the human-computer interaction rate. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] FIG1 is a schematic diagram of an implementation environment of a solution provided by an embodiment of the present application;

[0027] FIG2 is a flow chart of a video generation method provided by one embodiment of the present application;

[0028] FIG3 is a schematic diagram of a virtual scene provided by an embodiment of the present application;

[0029] FIG4 is a schematic diagram of a user interface provided by one embodiment of the present application;

[0030] FIG5 is a schematic diagram of a user interface provided by another embodiment of the present application;

[0031] FIG6 is a flowchart of a video generation method provided by another embodiment of the present application;

[0032] FIG7 is a schematic diagram of a zoomed-out lens according to an embodiment of the present application;

[0033] FIG8 is a schematic diagram of a zoomed-in lens according to an embodiment of the present application;

[0034] FIG9 is a schematic diagram of lens rotation provided by one embodiment of the present application;

[0035] FIG10 is a schematic diagram of a close-up of a lens provided in one embodiment of the present application;

[0036] FIG11 is a schematic diagram of a camera movement method for an outdoor viewing point provided by one embodiment of the present application;

[0037] FIG12 is a schematic diagram of a camera movement method for indoor viewing angles provided by one embodiment of the present application;

[0038] FIG13 is a schematic diagram of virtual item scoring provided by one embodiment of the present application;

[0039] FIG14 is a schematic diagram of a virtual item viewing angle provided by one embodiment of the present application;

[0040] FIG15 is a schematic diagram of a close-up of a lens provided by another embodiment of the present application;

[0041] FIG16 is a schematic diagram of a preview interface of a scene display video provided by one embodiment of the present application;

[0042] FIG17 is a flowchart of a video generation method according to an embodiment of the present application;

[0043] FIG18 is a block diagram of a video generating apparatus provided by one embodiment of the present application;

[0044] FIG19 is a block diagram of a video generating apparatus provided by another embodiment of the present application;

[0045] FIG20 is a structural block diagram of a terminal device provided by an embodiment of the present application;

[0046] Figure 21 is a structural block diagram of a server provided by an embodiment of the present application. DETAILED DESCRIPTION

[0047] In order to make the objectives, technical solutions and advantages of this application clearer, the implementation methods of this application will be further described in detail below with reference to the accompanying drawings.

[0048] In related art, after decorating their home, users activate the screen recording function, use a joystick to control the camera, and finally edit the video using video editing software to create a final home display video. However, recording home display videos in this way has the problem of numerous steps and a significant time consumption, resulting in low efficiency in generating home display videos. Users take a long time to view home display videos, resulting in a poor interactive experience and a low human-computer interaction rate. In some embodiments, a home can refer to a virtual building in a virtual scene, and a home display video can also be referred to as a scene display video.

[0049] Please refer to FIG1 , which shows a schematic diagram of an implementation environment of a solution provided by an embodiment of the present application. The implementation environment of the solution may include: a terminal device 10 and a server 20 .

[0050] The terminal device 10 includes, but is not limited to, mobile phones, tablet computers, intelligent voice interaction devices, game consoles, wearable devices, multimedia playback devices, PCs (Personal Computers), vehicle-mounted terminals, smart home appliances, AR (Augmented Reality) devices, VR (Virtual Reality) devices, and other electronic devices. The terminal device 10 can run a client for a target application (such as a game application). Optionally, the target application can be an application that needs to be downloaded and installed, or it can be in the form of a web page or a mini-program, which is not limited in this embodiment of the present application.

[0051] A mini-program is an application developed in a programming language and dependent on a host program to run. Mini-programs do not require downloading and installation; they can be dynamically loaded into the host program to run. Users can find the mini-program they need through search, scanning, and other methods, click to open it, and close it after use, without occupying the terminal device's memory, making it very convenient. Mini-programs can be easily accessed and distributed within the host program, while providing an excellent user experience. In some embodiments, mini-programs can also be referred to as embedded programs.

[0052] In the embodiment of the present application, the target application may be, but is not limited to, a city construction and management simulation game application, an action-adventure game application, a turn-based strategy game application, a medieval architecture and strategy game application, a war strategy game application, a business strategy game application, a strategy game (Simulation Game, SLG for short) application, a massively multiplayer online game (Massively Multiplayer Online Game, MMO game for short) application, a massively multiplayer online role-playing game (Massively Multiplayer Online Role-Playing Game, MMO RPG for short) application, a social application, an interactive entertainment application, a simulation program, a VR application, an AR application, a three-dimensional map application, a virtual reality game application, an augmented reality game application, etc.

[0053] In some embodiments, the target application is an MMO game application. MMO games are a type of game that allows a large number of users to interact simultaneously in a virtual world. MMO games provide users with a vibrant and socially interactive virtual environment, where users explore the game world by completing quests, fighting, interacting, and other activities. In MMO games, users can build and manage virtual homes, cities, or bases in the home system, which gives them a sense of accomplishment.

[0054] In an embodiment of the present application, a virtual scene is a scene displayed (or provided) when the client of a target application (such as a game application) is running on a terminal device. The virtual scene refers to an environment created for virtual objects to carry out activities (such as house construction and interior decoration). For example, a virtual scene may include a virtual building, which may be a virtual house, a virtual living room, a virtual bedroom, etc. The virtual scene may be a simulation of the real world, a semi-simulated and semi-fictitious three-dimensional world, or a purely fictitious three-dimensional world. The virtual scene may be any one of a two-dimensional virtual scene, a 2.5-dimensional virtual scene, and a three-dimensional virtual scene. In some embodiments, the virtual scene may also be referred to as a virtual environment.

[0055] The above-mentioned virtual building refers to a virtual element of the architectural form built by the user in the target application. In this application, the display form of the virtual building is not limited. For example, the display form of the virtual building may include but is not limited to the forms of houses, sports centers, farms, greenhouses, etc. The virtual building can be displayed in three-dimensional form or in two-dimensional form, and the embodiments of this application do not limit this. Optionally, when the virtual scene is a three-dimensional virtual scene, the virtual building is a three-dimensional stereo model. Each virtual building has its own shape and volume in the three-dimensional virtual scene and occupies a part of the space in the three-dimensional environment. In some embodiments, the virtual building can also be implemented as a 2.5-dimensional or 2-dimensional model, and this application does not limit this.

[0056] A virtual object refers to an interactive element within a target application. For example, if the target application is a game application, a virtual object refers to a virtual character controlled by a user or server within the game application. A virtual object can be in the form of a human, animal, cartoon, or other form, although this embodiment of the present application does not limit this. A virtual object can be displayed in either three-dimensional or two-dimensional form, although this embodiment of the present application does not limit this. Optionally, when the virtual environment is a three-dimensional virtual environment, the virtual object is a three-dimensional model, such as one created using animation skeletal technology. Each virtual object has its own shape and volume within the three-dimensional virtual environment and occupies a portion of the space within the three-dimensional virtual environment. Virtual object activities include, but are not limited to, at least one of adjusting body posture, crawling, walking, running, riding, flying, jumping, driving, picking up, shooting, attacking, and throwing. Illustratively, a virtual object is a virtual character, such as a humanoid or anime character. In some implementations, a virtual object can also be implemented as a 2.5D or 2D model, although this embodiment of the present application does not limit this. A virtual object can be controlled by a server or by a user through a client, although this embodiment of the present application does not limit this.

[0057] The server 20 is used to provide background services for the client of the target application in the terminal device 10. For example, the server 20 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms, but is not limited thereto.

[0058] The terminal device 10 and the server 20 can communicate with each other via a network, which can be a wired network or a wireless network.

[0059] Please refer to Figure 2, which shows a flow chart of a video generation method provided by an embodiment of the present application. The execution subject of each step of the method can be a computer device. For example, the computer device can be the terminal device 10 in the implementation environment of the solution shown in Figure 1, and the execution subject of each step can be the client of the target application running in the terminal device 10. In the following embodiments, for the sake of convenience of description, only the execution subject of each step is introduced as the "client". The method can include at least one of the following steps (210-230):

[0060] Step 210: Display the image of the virtual scene.

[0061] In some embodiments, the virtual scene may be constructed or decorated by the user, or may be a scene initialized in the target application.

[0062] In some embodiments, the above-mentioned target application provides users with different types of virtual elements. The virtual elements may include but are not limited to: virtual houses, virtual swimming pools, virtual farms, virtual plants, virtual furniture, virtual decorations, etc. Users can decorate virtual scenes or perform other activities by placing virtual elements. The types of virtual elements are not limited in this application.

[0063] For example, as shown in Figure 3, it shows a schematic diagram of a virtual scene provided by an embodiment of the present application. The virtual scene includes a virtual house 310, virtual floor tiles 320, a virtual wall 330 and a virtual rockery 340. The virtual wall 330 and the virtual rockery 340 are preset scenes, that is, the scenes initialized by the above-mentioned target application. The user places the virtual house 310 in the center of the screen of the virtual scene, and places a circle of virtual floor tiles 320 around the virtual house 310 to form a path.

[0064] Optionally, virtual elements in the virtual scene can be observed and adjusted by using a zoom control.

[0065] In some embodiments, the user interface displayed by the client may include a screen layer and a control layer, wherein the control layer is located above the screen layer. The screen layer is used to display the screen of the virtual scene. The control layer is used to display user interface (UI) controls, such as the zoom control mentioned above and other controls mentioned below.

[0066] In the above manner, the user places different virtual elements in the virtual scene to beautify the picture of the virtual scene, and prepares for the subsequent user's framing operation by displaying the picture of the virtual scene.

[0067] Step 220 , in response to a framing operation on the virtual scene, displaying n framing pictures obtained by photographing the virtual scene from n framing perspectives, where different framing pictures are obtained by photographing the virtual scene from different framing perspectives, and n is a positive integer.

[0068] A framing operation for a virtual scene refers to an operation performed by a user to capture a framing picture. For example, a user may capture n framing pictures by performing n framing operations for a virtual scene, with each framing operation capturing one framing picture. Of course, a framing operation can capture one framing picture, or multiple framing pictures. For example, a framing operation may refer to a single click on a capture control, in which case one framing picture may be captured; another example may refer to a long press and click on a capture control, in which case multiple framing pictures may be captured.

[0069] In some embodiments, the user can shoot by clicking a control for responding to a framing operation on a virtual scene, or can shoot through a gesture.

[0070] For example, there is a shooting control in the user interface. After clicking the shooting control, a shooting of the current framing angle can be completed, and a framing picture corresponding to the current framing angle can be obtained.

[0071] For example, the user taps the screen of the terminal device twice with the tip of his finger to complete a shot of the current viewing angle and obtain a viewing picture corresponding to the current viewing angle.

[0072] Optionally, the picture of the virtual scene is in a picture layer of the user interface, and the control layer of the user interface may include a switching control, a zoom control, and a shooting control, and the control layer is above the picture layer.

[0073] In some embodiments, the toggle control is used to control the display state and hidden state of all controls in the user interface. When all controls are in the hidden state, the image of the virtual scene is not blocked by other controls; when all controls are in the displayed state, framing operations for the virtual scene can be performed.

[0074] In some embodiments, a zoom control is used to adjust the zoom level of virtual elements in a virtual scene. The zoom level is a measure of the degree to which a virtual element in the virtual scene is enlarged or reduced, indicating the size ratio of the virtual element. The virtual elements include, but are not limited to, virtual houses, virtual trees, and virtual fences.

[0075] In some embodiments, a user can use different viewing angles to control the movement of virtual objects in a virtual scene. The virtual scene observed by the user varies under different viewing angles, including but not limited to the following: first-person perspective, third-person perspective, high-angle perspective, low-angle perspective, bird's-eye perspective, side-view perspective, etc. For example, when a user moves in a virtual scene from a first-person perspective, the image of the virtual scene is the image seen from the perspective of the virtual object, i.e., the user is inside the current virtual scene; when the current virtual scene is from a third-person perspective, the image of the virtual scene includes the virtual object, and the user can observe the image of the virtual object moving in the virtual scene, i.e., the user is outside the current virtual scene.

[0076] In some embodiments, in response to adjusting the viewing angle, a view of the virtual scene from the adjusted viewing angle is displayed. The user can flexibly adjust the content of the virtual scene by adjusting the viewing angle, which improves the visual effect, encourages the user to capture the view more quickly, and improves the efficiency of generating scene display videos.

[0077] When a user performs a framing operation, the framing perspective refers to the position and angle at which the user frames the virtual scene.

[0078] Optionally, the user can continuously adjust the current framing angle by controlling the virtual joystick to determine the position of the framing angle; or can adjust the current framing angle by controlling the virtual direction keys to determine the position of the framing angle. The virtual joystick can be a visual control or an invisible control, which is not limited in this application. For example, the virtual joystick is a visual control in the shape of a disc. By dragging the virtual joystick, the direction of movement of the virtual scene screen can be controlled, and the direction of movement of the screen is consistent with the direction of dragging the virtual joystick. For example, the virtual joystick is an invisible control. By dragging it within the specified range of the user interface, the direction of movement of the virtual scene screen can be controlled. The starting point of the drag is the position of the virtual joystick, and the direction of movement of the screen is consistent with the direction of dragging.

[0079] Optionally, the user can drag a position in the virtual scene where there is no control to adjust the angle of the viewing angle. For example, dragging upward in a position where there is no control in the virtual scene will cause the current viewing angle to change upward, and the same applies to other directions.

[0080] For example, the framing angle is used to determine how to shoot the virtual scene. The framing angle includes the framing position and the framing angle. For example, the framing position may refer to the position of the virtual object controlled by the user in the virtual scene when shooting the virtual scene, and the framing angle may refer to the orientation of the virtual object controlled by the user when shooting the virtual scene.

[0081] Exemplarily, the framing image is obtained by capturing a virtual scene from a framing perspective with a virtual camera. The framing perspective is used to determine how the virtual camera captures the virtual scene. Exemplarily, the framing position within the framing perspective is used to determine the shooting position of the virtual camera when capturing the virtual scene, and the framing angle within the framing perspective is used to determine the shooting angle of the virtual camera when capturing the virtual scene.

[0082] Optionally, the user can adjust the zoom level of the current virtual scene by controlling the zoom control, or by using gestures to adjust the zoom level of the current virtual scene, thereby changing the size and field of view of the virtual scene. For example, the user can adjust the zoom level of the current virtual scene by controlling the zoom control, which is a slider control that is dragged to zoom in or out. For example, the user can adjust the zoom level of the current virtual scene by using gestures, such as pinching on the screen to zoom out, or spreading fingers on the screen to zoom in.

[0083] It should be noted that there are many ways to adjust the current viewing angle and picture size. In actual applications, it can be the method in this embodiment or other methods, which are not limited in this application.

[0084] In some embodiments, n framing pictures obtained by photographing the virtual scene from n framing perspectives are displayed in the picture display bar; wherein the picture display bar is displayed on the upper layer of the picture of the virtual scene.

[0085] The picture display bar is a visual tool for displaying captured framing pictures. Optionally, the picture display bar includes n framing picture frames on the user interface, with each framing picture frame being used to display a framing picture. For example, the order of the framing pictures can be adjusted by clicking and dragging the framing picture frames, or by clicking on two different framing picture frames to change their positions. For example, the framing picture displayed in the framing picture frame can be deleted by dragging the framing picture frame to a recycling control position or by clicking on a delete control in the framing picture frame.

[0086] Through the above method, the user previews the currently framed picture in the picture display bar, which helps the user quickly determine the picture to be framed next by viewing the picture display bar, thereby improving the efficiency of obtaining the framed pictures and the efficiency of generating the scene display video, so that the user can see the scene display video as soon as possible, improving the user's interactive experience, and thus improving the human-computer interaction rate.

[0087] In some embodiments, a video generation control is also displayed in the picture display bar.

[0088] In some embodiments, the video generation control may also be located anywhere in the control layer.

[0089] In response to an operation for generating a video, displaying a scene display video corresponding to the virtual scene includes: displaying a scene display video corresponding to the virtual scene in response to an operation on a video generation control. Optionally, the operation on the video generation control may refer to a click operation on the video generation control, such as a single click operation, a double click operation, etc.

[0090] The operation of the video generation control is very convenient. By generating operations on the video generation control to trigger the generation and display of the video, it is beneficial to improve the efficiency of video generation and display, so that users can see the scene display video as soon as possible, improve the user's interactive experience, and thus improve the human-computer interaction rate.

[0091] In some embodiments, a user can perform the video generation operation by clicking the video generation control, or by performing a gesture. For example, a user can perform the video generation operation by tapping the screen of a terminal device three times with a finger joint. The specific method used to implement the video generation operation is determined by relevant technical personnel and is not limited by this application.

[0092] In some embodiments, the picture display bar has a corresponding display or hide control, and the display or hide control is used to switch the picture display bar between a display state and a hidden state. The method provided in the embodiment of the present application also includes: when the picture display bar is in a hidden state, in response to an operation on the display or hide control, switching the picture display bar from a hidden state to a display state, that is, displaying the picture display bar; or, when the picture display bar is in a displayed state, in response to an operation on the display or hide control, switching the picture display bar from a displayed state to a hidden state, that is, canceling the display of the picture display bar.

[0093] The operation for showing or hiding the control may refer to a click operation for showing or hiding the control, such as a single-click operation, a double-click operation, etc. The showing or hiding control is a control with different functions in different situations. When the picture display bar is in a hidden state, the showing or hiding control is a control with a display function. If an operation for showing or hiding the control is obtained, the picture display bar is switched from a hidden state to a displayed state so that the picture display bar is displayed; when the picture display bar is in a displayed state, the showing or hiding control is a control with a hidden function. If an operation for showing or hiding the control is obtained, the picture display bar is switched from a displayed state to a hidden state so that the picture display bar is hidden, that is, the picture display bar is canceled. The showing or hiding control can be displayed at any position in the user interface, and the embodiments of the present application are not limited to this.

[0094] In some embodiments, the display or hide control displays the number of captured viewfinder images. In this way, even when the image display bar is in a hidden state, the user can still know the number of captured viewfinder images.

[0095] The above method switches the image display bar from a visible state to a hidden state, hiding the controls within the bar and providing the user with a complete virtual scene, helping the user better complete the framing operation. Switching the image display bar from a hidden state to a visible state provides a preview of the framing image, helping the user determine the next framing image. Users can flexibly display or hide controls as needed, improving operational flexibility during the framing image capture process, thereby enhancing the user's interactive experience and increasing the human-computer interaction rate.

[0096] The display state of the image display bar refers to the current visible state of the image display bar. The image display bar is displayed in a specific area of ​​the user interface, and the user can interact with the controls in the image display bar.

[0097] The hidden state of the image display bar means that the image display bar is currently in an invisible state. The image display bar is neither visible nor occupies space in the user interface. At this time, the user cannot interact with the controls in the image display bar.

[0098] Optionally, when the image display bar switches from a visible state to a hidden state, other controls within the same interface as the image display bar also enter a hidden state. Similarly, when the image display bar switches from a hidden state to a visible state, other controls within the same interface as the image display bar also enter a visible state. These other controls include the zoom controls mentioned above. Switching all controls within the same interface to a hidden state can provide users with a more comprehensive view of the virtual scene.

[0099] In some embodiments, a shooting control is displayed above the virtual scene screen, and framing operations are operations performed on the shooting control. For example, as shown in FIG4 , clicking shooting control 440 captures a framing image at the current framing angle. Operations performed on the shooting control are highly convenient. By triggering framing operations by operating the shooting control, the efficiency of capturing framing images is improved, thereby improving the efficiency of generating and displaying scene presentation videos, enabling users to view the scene presentation videos as quickly as possible, enhancing their interactive experience, and ultimately increasing the human-computer interaction rate.

[0100] In some embodiments, after the pth shooting, a framing picture frame is added after the last framing picture frame in the picture display column to display the framing picture corresponding to the pth framing operation, where p is less than or equal to n and is a positive integer.

[0101] For example, as shown in Figure 4, it shows a schematic diagram of a user interface provided by an embodiment of the present application. The user interface 400 is located on the screen of the virtual scene, and includes a visible virtual joystick 410, a display or hide control 420, a switch control 430, a shooting control 440, a zoom control 450 and a virtual drone control 460. After clicking the display or hide control 420, as shown in Figure 5, it shows a schematic diagram of a user interface provided by another embodiment of the present application. The user interface 400 includes a visible virtual joystick 410, a display or hide control 420, a switch control 430, a shooting control 440, a zoom control 450 and a virtual drone control 460, which correspond one-to-one to the controls in Figure 4. Compared with Figure 4, Figure 5 has a viewfinder picture frame 470, a video generation control 480 and a picture display bar 490. That is, after clicking the display or hide control 420, the picture display bar 490 switches from a hidden state to a displayed state, and the viewfinder picture frame 470, the video generation control 480 and the picture display bar 490 also switch from an invisible state to a visible state.

[0102] Through the above method, the user adjusts the viewing angle of the current virtual scene, determines at least one framing perspective, and takes at least one framing picture to provide material for the subsequent generation of a scene display video.

[0103] In some embodiments, after step 220, the process further includes the following steps: in response to the operation of selecting a framing picture, marking and displaying the selected framing picture from the n framing pictures; wherein the m framing pictures include the selected framing picture. By marking and displaying the selected framing picture, the user can intuitively distinguish the selected framing picture from the unselected framing pictures, thereby improving the user's visual experience and thereby increasing the human-computer interaction rate.

[0104] The user selects m framing pictures in the picture display bar. There are many ways to mark and display the selected framing pictures, including but not limited to at least one of the following ways: highlight mark, transparent area, icon, symbol, text prompt, color mark, etc. Optionally, the way to mark and display the selected framing pictures may include at least one of the following: highlighting the selected framing picture, setting the background of the selected framing picture to transparent, displaying a selection icon on the selected framing picture, displaying a selection symbol on the selected framing picture, displaying selected text on the selected framing picture, and setting the framing picture frame where the selected framing picture is located to a target color. The selection icon is any icon that can prompt that the framing picture is selected, the selection symbol is any symbol that can prompt that the framing picture is selected, and the selection text is any text that can prompt that the framing picture is selected. The target color is different from the color of the framing picture frame where the unselected framing pictures are located.

[0105] If the user does not select a framing picture, then all n framing pictures will be used to generate the scene display video, that is, m is equal to n.

[0106] Optionally, when the mark displays the selected framed picture, the mark also displays the order in which the framed pictures were selected.

[0107] By using the above method, the framing picture that is ultimately used to generate the scene display video is selected, which is conducive to subsequently generating the corresponding scene display video around the above framing picture.

[0108] Step 230 , in response to the operation for generating a video, displaying a scene display video corresponding to the virtual scene, where the scene display video is generated based on m framing pictures out of n framing pictures, where m is a positive integer less than or equal to n.

[0109] In some embodiments, m is equal to n. In this case, the scene display video is generated based on all the framing pictures in the n framing pictures. Generating the scene display video by considering all the captured framing pictures is conducive to improving the reliability of the scene display video.

[0110] In some embodiments, m is less than n. In this case, the scene display video is generated based on a portion of the n framing pictures. Generating the scene display video by considering a portion of the captured framing pictures is conducive to improving the efficiency of generating the scene display video.

[0111] In some embodiments, when m is less than n, the m framed pictures may be pictures selected by the user from the n framed pictures, or may be pictures selected by the client from the n framed pictures.

[0112] For example, taking the example of a client selecting m framing pictures from n framing pictures, the client can randomly select m framing pictures from the n framing pictures, or the client can select m framing pictures from the n framing pictures according to a selection rule. The selection rule can be set based on experience or flexibly adjusted according to the application scenario, and this embodiment of the application does not limit this. For example, the selection rule can be to select the m framing pictures with the most recent shooting time.

[0113] Optionally, the scene display video can be generated according to the order in which the m framing pictures are selected; the scene display video can also be generated according to the order in which the m selected framing pictures are taken; or the m framing pictures can be classified according to different viewing angles, and the scene display video can be generated based on the classified framing pictures.

[0114] Through the above method, by previewing the corresponding scene display video, the user is helped to adjust the framing picture to obtain a scene display video that is more satisfactory to the user.

[0115] To sum up, the technical solution provided by the embodiment of the present application, by shooting multiple framing pictures in a virtual scene, the framing pictures are obtained by shooting the virtual scene from different framing perspectives, and a scene display video can be directly generated based on the framing pictures, thereby realizing the automation of scene display video generation. The user only needs to shoot different framing pictures in the virtual scene, and the scene display video can be automatically generated by the device, which simplifies the user operation steps and significantly reduces the production time of the scene display video, thereby improving the generation efficiency of the scene display video, allowing the user to see the scene display video as soon as possible, improving the user's interactive experience, and thereby improving the human-computer interaction rate.

[0116] Please refer to Figure 6, which shows a flow chart of a video generation method provided by another embodiment of the present application. The execution subject of each step of the method can be a computer device. For example, the computer device can be the terminal device 10 in the implementation environment of the solution shown in Figure 1, or it can be the server 20 in the implementation environment of the solution shown in Figure 1. For example, the execution subject of each step can be the client or server of the target application running in the terminal device 10. In the following embodiments, for the sake of convenience of description, only the execution subject of each step is introduced as "server". The method may include at least one of the following steps (610-620):

[0117] Step 610 , obtaining m framing pictures obtained by photographing the virtual scene, where different framing pictures are obtained by photographing the virtual scene from different framing perspectives, and m is a positive integer.

[0118] The m framing images are obtained from the client, and after responding to the operation for generating a video, the client sends the m framing images to the server. For example, the m framing images can be framing images selected by the user from n framing images taken, or can be framing images selected by the client from n framing images taken, or can be the n framing images taken by the user themselves, and this embodiment of the application is not limited to this.

[0119] Through the above method, m framing pictures are obtained from the client to provide materials for the subsequent generation of scene display videos.

[0120] Step 620: Generate a scene display video corresponding to the virtual scene based on the m framed images.

[0121] In some embodiments, camera movement modes corresponding to m framing pictures are determined, and the camera movement modes are used to indicate the moving path and shooting angle of the virtual camera; based on the camera movement modes corresponding to the m framing pictures, scene display clips corresponding to the m framing pictures are generated; wherein, the scene display clip corresponding to the i-th framing picture among the m framing pictures is a video clip obtained by controlling the virtual camera to shoot the virtual scene based on the moving path and shooting angle of the virtual camera indicated by the camera movement mode corresponding to the i-th framing picture, and i is a positive integer less than or equal to m; based on the scene display clips corresponding to the m framing pictures, a scene display video is generated.

[0122] The camera movement method refers to the movement of the virtual camera to change the distance and height of the virtual scene, so that the video footage can show more details. It should be noted that the virtual camera here and the virtual camera used to capture the viewfinder can be the same virtual camera or different virtual cameras, and this embodiment of the application is not limited to this.

[0123] There are many different camera movement methods, including but not limited to: zooming out, zooming in, rotating, and following. All camera movement methods can indicate the virtual camera's movement path and shooting angle. The shooting angle indicates the virtual camera's direction as it moves along the movement path.

[0124] Zooming out refers to moving the virtual camera a certain distance away from the subject, with the virtual camera's movement path being a straight line passing through the virtual camera's current position and extending along the virtual camera's current shooting angle. The subject is the primary subject or focal point in the framed image, the compositional core of the framed image. For a zoomed-out camera movement, while the virtual camera moves along the movement path indicated by the zoom-out lens, the virtual camera's shooting angle remains unchanged. That is, while the virtual camera moves along the movement path indicated by the zoom-out lens, the virtual camera's lens orientation remains unchanged, i.e., the virtual camera's lens always faces the subject.

[0125] For example, as shown in Figure 7, it shows a schematic diagram of zooming out provided by an embodiment of the present application. Before zooming out, the position of the virtual camera 710 is S0. When the virtual camera moves a distance L1 away from the shooting subject 720 along the straight line where S0 and the current angle of the virtual camera are located, the shooting angle of the virtual camera 710 remains unchanged, and the position of the virtual camera 710 becomes S1. That is, the movement of the virtual camera 710 from S0 to S1 is the process of zooming out.

[0126] A zoom-in movement involves moving the virtual camera a certain distance toward the subject, along a straight line that passes through the virtual camera's current position and extends along its current shooting angle. For a zoom-in movement, the virtual camera's shooting angle remains unchanged while it moves along the indicated zoom-in path. This means that the virtual camera's lens orientation remains unchanged, i.e., it always faces the subject.

[0127] For example, as shown in Figure 8, it shows a schematic diagram of a zoom-in provided by an embodiment of the present application. Before the zoom-in is performed, the position of the virtual camera 810 is S0. After the virtual camera moves a distance L2 along the straight line between S0 and the current angle of the virtual camera and approaches the subject 820, the shooting angle of the virtual camera 810 remains unchanged, and the position of the virtual camera 810 becomes S1. That is, the movement of the virtual camera 810 from S0 to S1 is the process of zooming in.

[0128] Lens rotation refers to the virtual camera rotating a certain angle with the subject as the center. The movement path of the virtual camera is the arc formed by horizontally rotating the line connecting the current position of the virtual camera and the center of the subject clockwise or counterclockwise by the above angle. For example, for the lens rotation movement method, the shooting angle of the virtual camera can remain unchanged during the process of the virtual camera moving according to the movement path indicated by the lens rotation. That is, the direction of the lens of the virtual camera remains unchanged during the process of the virtual camera moving according to the movement path indicated by the lens rotation. For example, for the lens rotation movement method, the shooting angle of the virtual camera can also be continuously adjusted during the process of the movement, so that the lens of the virtual camera is always facing the subject.

[0129] For example, as shown in Figure 9, it shows a schematic diagram of lens rotation provided by an embodiment of the present application. The position of the virtual camera 910 before the lens rotation is S0. After the virtual camera 910 rotates horizontally a degrees counterclockwise around the Z axis, the distance between the virtual camera 910 and the shooting subject 920 remains unchanged, the shooting angle of the virtual camera 910 remains unchanged, and the position becomes S1. That is, the movement of the virtual camera 910 from S0 to S1 is the process of lens rotation.

[0130] A close-up shot refers to the virtual camera approaching the subject and adjusting the virtual camera's shooting angle to the optimal shooting angle. The movement path of the virtual camera is the path of the virtual camera moving toward the optimal shooting point of the subject. Regarding the close-up shot movement method, as the virtual camera moves along the movement path indicated by the close-up shot, the virtual camera's shooting angle gradually adjusts to the optimal shooting angle of the subject. The optimal shooting point and optimal shooting angle of the subject can be set based on experience or flexibly adjusted as needed, and this is not limited in the embodiments of the present application.

[0131] For example, as shown in Figure 10, it shows a schematic diagram of a close-up shot provided by an embodiment of the present application. Before the close-up shot is taken, the position of the virtual camera 1010 is S0, and the optimal photographic point of the shooting subject 1020 is S1. As shown in the enlarged view 1030, the virtual camera 1010 moves along the line connecting S0 and S1. During the movement, the shooting angle of the virtual camera 1010 is gradually adjusted to the optimal shooting angle, and the position of the virtual camera 1010 becomes S1. That is, the movement of the virtual camera 1010 from S0 to S1 is the process of the close-up shot.

[0132] In some embodiments, different combinations of camera movements may be used for different framing pictures.

[0133] Through the above method, by determining the appropriate camera movement method for each framing picture, a corresponding scene display clip can be generated for each framing picture, which helps to smoothly display the details in the corresponding framing picture through the scene display clip, thereby improving the effect of the final generated scene display video, improving the user's visual experience of watching the scene display video, and improving the human-computer interaction rate.

[0134] Exemplarily, based on the movement path and shooting angle of the virtual camera indicated by the camera movement method corresponding to the i-th framing picture, the process of controlling the virtual camera to shoot the virtual scene and obtaining the scene display segment corresponding to the i-th framing picture can be: controlling the virtual camera to move according to the movement path indicated by the camera movement method corresponding to the i-th framing picture, and controlling the lens direction of the virtual camera according to the shooting angle indicated by the camera movement method corresponding to the i-th framing picture during the movement; and using the video segment shot by the virtual camera during the movement as the scene display segment corresponding to the i-th framing picture.

[0135] In some embodiments, for the i-th framing picture, the framing point category corresponding to the i-th framing picture is determined based on the framing point position of the i-th framing picture, and the framing point category is an outdoor framing point or an indoor framing point; if the framing point category of the i-th framing picture is an outdoor framing point, the camera movement mode corresponding to the i-th framing picture is determined to be a first camera movement mode; if the framing point category of the i-th framing picture is an indoor framing point, the camera movement mode corresponding to the i-th framing picture is determined to be a second camera movement mode; wherein, the first camera movement mode and the second camera movement mode are different.

[0136] A framing point refers to the position and angle of the virtual camera when capturing the corresponding framing image. Each framing image corresponds to one framing point. Because indoor and outdoor framing points differ in subject size, detail, and other factors, the shooting methods for indoor and outdoor framing points differ.

[0137] By determining different camera movements based on different viewpoint types, the generated scene display clips can include more details required to be displayed in the framing images. This helps to improve the matching between the generated scene display clips and the viewpoint types of the framing images, thereby improving the quality of the scene display videos generated from the scene display clips, enhancing the user's visual experience when watching the scene display videos, and improving the human-computer interaction rate.

[0138] In some embodiments, the first camera movement mode includes: zooming in and rotating the lens; based on the camera movement modes corresponding to the m framing pictures, scene display clips corresponding to the m framing pictures are generated, including: when the camera movement mode corresponding to the i-th framing picture is the first camera movement mode, controlling the virtual camera to zoom in and move from a first position to a second position along a first direction; wherein the second position is the framing point position of the i-th framing picture, the distance between the first position and the second position is the first distance, and the first direction is the direction of the lens when taking the i-th framing picture; controlling the virtual camera to rotate the lens and rotate from the second position to a third position around a first straight line in a horizontal plane by a first angle; wherein the first straight line is perpendicular to the horizontal plane; during the movement of the virtual camera, controlling the virtual camera to shoot the virtual scene based on a determined shooting angle to obtain a scene display clip corresponding to the i-th framing picture.

[0139] The first camera movement is used for shooting outdoor locations. When shooting outdoors, the subject is a large object such as a virtual building. Close-ups are suitable for capturing details of small objects, so they are not used here. Since details of the subject need to be captured, zooming out is also not suitable. Using a zoom-in camera movement can capture details of the subject's current direction. Combined with lens rotation, details of other sides of the subject can be obtained. For example, virtual buildings can include virtual houses, virtual swimming pools, and virtual farms.

[0140] In some embodiments, a method for obtaining a scene display segment corresponding to the i-th framing image includes: when the camera movement mode corresponding to the i-th framing image is a first camera movement mode, controlling a virtual camera to capture a virtual scene based on a first movement path and a first shooting angle to obtain a scene display segment corresponding to the i-th framing image. The first camera movement mode includes a zoom-in and a pan. The first movement path includes a first sub-path indicated by the zoom-in, which moves from a first position along a first direction to a second position, and a second sub-path indicated by the pan, which rotates from the second position about a first straight line within a horizontal plane at a first angle to a third position. The second position is the framing point position of the i-th framing image, the distance between the first position and the second position is a first distance, the first direction is the lens orientation when capturing the i-th framing image, and the first straight line is perpendicular to the horizontal plane. The first shooting angle includes a first shooting sub-angle of the virtual camera during movement according to the first sub-path, as indicated by the zoom-in, and a second shooting sub-angle of the virtual camera during movement according to the second sub-path, as indicated by the pan.

[0141] Exemplarily, the first shooting sub-angle and the second shooting sub-angle are both used to make the lens of the virtual camera always face the first direction, that is, the shooting angle of the virtual camera always remains unchanged regardless of whether it is moving along the first sub-path or moving along the second sub-path.

[0142] Exemplarily, the first shooting sub-angle is used to ensure that the lens of the virtual camera is always facing the first direction when it moves along the first sub-path, that is, the shooting angle of the virtual camera remains unchanged during the movement along the first sub-path; the second shooting sub-angle is used to ensure that the lens of the virtual camera is always facing the subject in the i-th framed picture when it moves along the second sub-path. Since the second sub-path is a path that rotates the virtual camera and the position of the subject remains unchanged, the shooting angle of the virtual camera is gradually adjusted during the movement along the second sub-path.

[0143] Exemplarily, based on the first moving path and the first shooting angle, the virtual camera is controlled to shoot the virtual scene to obtain the scene display segment corresponding to the i-th framing picture. The process can be: controlling the virtual camera to move according to the first sub-path, and controlling the lens direction of the virtual camera according to the first shooting sub-angle during the movement; after the virtual camera moves to the second position, controlling the virtual camera to move according to the second sub-path, and controlling the lens direction of the virtual camera according to the second shooting sub-angle during the movement; splicing the video segment shot by the virtual camera during the movement according to the first sub-path and the video segment shot by the virtual camera during the movement according to the second sub-path to obtain the scene display segment corresponding to the i-th framing picture.

[0144] Exemplarily, as shown in Figure 11, it shows a schematic diagram of the camera movement method of an outdoor viewing angle provided by an embodiment of the present application. The viewing angle position of the framing picture corresponds to the position S0 (corresponding to the second position) in the preview image. The current viewing angle is an outdoor viewing angle, and the shooting subject of the virtual scene is the virtual house 1110. The first camera movement method is used for camera shooting, that is, the combination of lens zooming in and lens rotation is used for shooting. The virtual camera retreats a first distance along the shooting angle of the viewing angle to the S1 position (corresponding to the first position), moves from S1 to S0 to realize the lens zooming in movement, and then rotates counterclockwise from S0 around the center point of the virtual house 1110 by a first angle to the S2 position (corresponding to the third position) to realize the lens rotation movement.

[0145] Through the above method, based on the characteristics of outdoor filming locations: the subject is large and many details need to be captured, the first camera movement method is determined for it, which is conducive to capturing smooth and reasonable scene display clips. Generating scene display clips corresponding to the framing images taken at outdoor filming locations based on the camera movement methods of lens zooming in and lens rotation can ensure that the scene display clips include details of the current direction of the subject as well as details of other sides of the subject, allowing the scene display clips to display details of more sides of the subject, thereby improving the display effect of the scene display clips.

[0146] In some embodiments, the second camera movement mode includes: zooming in and close-up; based on the camera movement modes corresponding to the m framing pictures, generating scene display clips corresponding to the m framing pictures, including: when the camera movement mode corresponding to the i-th framing picture is the second camera movement mode, controlling the virtual camera to zoom in and move from a fourth position to a second position along a first direction; wherein the second position is the viewing angle position of the i-th framing picture, the distance between the fourth position and the second position is the second distance, and the first direction is the lens direction when shooting the i-th framing picture; controlling the virtual camera to close-up and move from the second position to a fifth position, and controlling the lens direction of the virtual camera to adjust from the first direction to the second direction during the movement; wherein the fifth position is the set viewing angle position corresponding to the first virtual object contained in the i-th framing picture, and the second direction is the set lens direction corresponding to the first virtual object; during the movement of the virtual camera, controlling the virtual camera to shoot the virtual scene based on a determined shooting angle to obtain a scene display clip corresponding to the i-th framing picture.

[0147] The second camera movement method is used for shooting indoor shooting locations. When shooting indoors, the subject is a small object such as virtual furniture and virtual decorations, so it is suitable to use a close-up lens for shooting. In addition to shooting the subject, it is also necessary to shoot a panoramic view of the interior. If the lens is zoomed out for shooting, it will be not smooth compared to the close-up lens shooting. Therefore, a combination of zooming in and close-up lens is used as the second camera movement method.

[0148] In some embodiments, a method for obtaining a scene display segment corresponding to the i-th framing picture includes: when the camera movement mode corresponding to the i-th framing picture is the second camera movement mode, controlling a virtual camera to shoot a virtual scene based on a second movement path and a second shooting angle to obtain a scene display segment corresponding to the i-th framing picture. The second camera movement mode includes: zooming in and close-up; the second movement path includes a third sub-path indicated by a zoom-in, moving from a fourth position to a second position along a first direction, and a fourth sub-path indicated by a close-up, moving from the second position to a fifth position; the second position is the viewing angle position of the i-th framing picture, the distance between the fourth position and the second position is the second distance, the first direction is the camera direction when shooting the i-th framing picture, and the fifth position is the set viewing angle position corresponding to the first virtual object contained in the i-th framing picture. The second shooting angle includes a third shooting sub-angle of the virtual camera indicated by a zoom-in lens while moving along the third sub-path, and a fourth shooting sub-angle of the virtual camera indicated by a close-up lens while moving along the fourth sub-path. The fourth shooting sub-angle is used to control the lens direction of the virtual camera from the first direction to the second direction, where the second direction is the set lens direction corresponding to the first virtual object.

[0149] Exemplarily, the third shooting sub-angle is used to ensure that the lens of the virtual camera always faces the first direction during the movement along the third sub-path. That is, the shooting angle of the virtual camera always remains unchanged during the movement along the third sub-path.

[0150] Exemplarily, based on the second moving path and the second shooting angle, the virtual camera is controlled to shoot the virtual scene to obtain the scene display segment corresponding to the i-th framing picture. The process can be: controlling the virtual camera to move according to the third sub-path, and controlling the lens direction of the virtual camera according to the third shooting sub-angle during the movement; after the virtual camera moves to the second position, controlling the virtual camera to move according to the fourth sub-path, and controlling the lens direction of the virtual camera according to the fourth shooting sub-angle during the movement; splicing the video segment shot by the virtual camera in the process of moving according to the third sub-path and the video segment shot by the virtual camera in the process of moving according to the fourth sub-path to obtain the scene display segment corresponding to the i-th framing picture.

[0151] Exemplarily, as shown in Figure 12, it shows a schematic diagram of the camera movement method of an indoor shooting point provided by an embodiment of the present application. The shooting point position of the shooting point picture corresponds to the position S0 (corresponding to the second position) in the preview picture. The current shooting point is an indoor shooting point, and the shooting subject of the virtual scene is the virtual Trojan horse 1210, which is also the first virtual object that needs a close-up. The second camera movement method is used for shooting, that is, a combination of lens zoom-in and lens close-up is used for shooting. The virtual camera retreats a second distance along the shooting angle of the shooting point to position S1 (corresponding to the fourth position), moves from S1 to S0 to achieve the lens zoom-in movement, and moves from S0 to S2 (corresponding to the fifth position). During the movement, the lens direction of the virtual camera is gradually adjusted to the second direction to achieve a close-up camera movement of the virtual Trojan horse 1210.

[0152] Through the above method, based on the characteristics of indoor filming locations: the subject is small and requires a close-up, determining the second camera movement method for it facilitates the capture of smooth and reasonable scene display clips. Generating scene display clips corresponding to the framing images taken at indoor filming locations based on the camera movement methods of zooming in and close-up allows the scene display clips to capture close-ups of small subjects while ensuring smooth shooting and improving the presentation effect of the scene display clips.

[0153] In some embodiments, a value score corresponding to at least one virtual item included in the i-th framed image is determined, where the value score is used to represent the shooting value of the virtual item; and the virtual item with the highest value score is determined as the first virtual item.

[0154] Optionally, virtual items in the framed image can be comprehensively scored based on factors such as their aesthetics and rarity. A virtual item with a higher value score indicates a higher value for photographing and a higher priority for photographing. For example, as shown in FIG13 , which illustrates a schematic diagram of virtual item scoring provided by an embodiment of the present application, the current virtual scene includes six virtual items: a virtual sofa 1310 (score: 400), a virtual potted plant 1320 (score: 200), a virtual window 1330 (score: 200), a virtual picture frame 1340 (score: 800), a virtual bed 1350 (score: 400), and a virtual photo frame 1360 (score: 900). Assuming that each framed image features at most two virtual items, the two virtual items with the highest value scores are selected for close-up, i.e., the two virtual items are determined to be the first virtual items. Therefore, virtual picture frame 1340 and virtual photo frame 1360 are determined to be the first virtual items.

[0155] In some embodiments, when the first virtual item includes multiple virtual items, a close-up order is generated based on the distance between the virtual items and the viewing angle positions. The close-up order is the order in which the virtual items are viewed in close-up. When the multiple virtual items are viewed in close-up order, the fifth position refers to the set viewing angle position corresponding to the virtual item with the last position in the close-up order. The fourth sub-path includes sub-paths corresponding to each of the multiple virtual items. The sub-path corresponding to the virtual item with the first position in the close-up order moves from the second position to the set viewing angle position corresponding to the virtual item with the first position in the close-up order; the sub-path corresponding to the virtual item with the kth position in the close-up order moves from the set viewing angle position corresponding to the virtual item with the k-1th position in the close-up order to the set viewing angle position corresponding to the virtual item with the kth position in the close-up order, where k is an integer greater than 1 and not greater than n, and n is the number of the multiple virtual items.

[0156] Through the above method, when the framed image includes multiple virtual items, the shooting value of the virtual items can be obtained through value scoring. Selecting virtual items with high value scores for close-ups is conducive to generating scene display clips with high user satisfaction, thereby improving the human-computer interaction rate.

[0157] In some embodiments, when the first virtual object corresponds to multiple set viewing locations, a set shooting order for the multiple set viewing locations is obtained; and the virtual camera is controlled to perform a close-up shot, starting from the second position and moving to each set viewing location in sequence according to the set shooting order. In other words, the fourth sub-path is a path that starts from the second position and moves to each set viewing location in sequence according to the set shooting order for the multiple set viewing locations corresponding to the first virtual object.

[0158] Close-up shots are suitable for capturing details of small objects, but there are also large virtual objects that cannot be fully captured in full view or detail by a single close-up shot. Therefore, multiple framing positions need to be set for shooting.

[0159] For example, as shown in FIG14 , which shows a schematic diagram of virtual object viewing angles provided by an embodiment of the present application, the first virtual object 1410 in sub-graph (a) of FIG14 is a smaller virtual object, so only one viewing angle is required to complete a close-up shot, and the virtual object 1420 in sub-graph (b) of FIG14 is a larger virtual object, so two viewing angles are required to complete a close-up shot.

[0160] For example, as shown in Figure 15, it shows a schematic diagram of a close-up shot provided by another embodiment of the present application. Figure 15 is the process of completing the close-up shot in sub-figure (b) of Figure 14. The virtual object 1420 corresponds to the viewing angles S1 and S2. The virtual camera 1510 first moves from the current position to the viewing angle S1. During the movement, the shooting angle of the virtual camera is gradually adjusted to the shooting angle corresponding to the viewing angle S1. Then, it moves from the viewing angle S1 to the viewing angle S2, and the shooting angle of the virtual camera is gradually adjusted to the shooting angle corresponding to the viewing angle S2.

[0161] By using the above method, multiple viewing angles are set for large virtual objects in the framing picture for close-up shooting, thereby ensuring the integrity of the shooting details of the virtual object in the scene display segment generated by the framing picture, improving user satisfaction with the scene display segment, and increasing the human-computer interaction rate.

[0162] In some embodiments, determining the viewing point category corresponding to the i-th framing picture based on the viewing point location of the i-th framing picture includes: obtaining the construction area of ​​the virtual building corresponding to the i-th framing picture; if the viewing point location of the i-th framing picture is outside the construction area, determining the viewing point category corresponding to the i-th framing picture as an outdoor viewing point; if the viewing point location of the i-th framing picture is within the construction area, determining the viewing point category corresponding to the i-th framing picture as an indoor viewing point. Determining whether the viewing point category is outdoor or indoor based on whether the viewing point location is outside or within the construction area is conducive to improving the accuracy of determining the viewing point category, thereby improving the reliability of generating the scene display segment corresponding to the framing picture.

[0163] There are many ways to determine the category of the viewing point, including but not limited to one of the following methods: environmental rendering and mapping method, collision detection method, skybox and environmental special effects method, design element method, map data and area marking method, etc. Exemplarily, using the map data and area marking method, based on the coordinates of the construction area of ​​the virtual building and the coordinates of the viewing point position, the relative distances between the viewing point position and the center point of the virtual building in the horizontal direction, vertical direction and depth direction can be calculated respectively. If the horizontal relative distance is less than half of the width of the virtual building, the vertical relative distance is less than half of the length of the virtual building, and the depth relative distance is less than half of the height of the virtual building, the viewing point can be determined to be an indoor viewing point. In other cases, it is an outdoor viewing point.

[0164] It should be noted that the virtual camera has a height limit during the framing and video shooting process. This height limit is used to ensure that the virtual camera frames and shoots within the normal framing area. The normal framing area may refer to other areas except the normal framing area. The abnormal framing area may be below the ground. The height limit is set by relevant technical personnel and is not limited in this application.

[0165] In some embodiments, the scene display segments corresponding to the m framed images are spliced ​​together to generate a scene display video. The scene display video is generated by splicing multiple scene display segments, which makes the scene display video more fluid, improves user satisfaction with the scene display video, and thus improves the human-computer interaction rate.

[0166] In some embodiments, the m frame pictures are spliced ​​together according to the framing time sequence to generate a scene display video.

[0167] Exemplarily, according to the framing time sequence of the above-mentioned m framing pictures, the m scene display segments corresponding to the m framing pictures are spliced ​​together to generate a complete scene display video.

[0168] In some embodiments, m frame pictures are spliced ​​together according to a first order to generate a scene display video; wherein the first order is determined by a user.

[0169] Exemplarily, before responding to the operation for generating a video, the user sorts the above-mentioned m framing pictures in the picture display column to determine the splicing order of the m scene display fragments, that is, determines the first order, and splices the above-mentioned m scene display fragments according to the first order to generate a complete scene display video.

[0170] In some embodiments, m framing pictures are spliced ​​together according to the framing view category to generate a scene display video.

[0171] For example, the scene display segments corresponding to the m framing pictures are first divided into outdoor scene display segments and indoor scene display segments according to the category of the viewing angle, and then the m scene display segments are spliced ​​together according to the distance of the viewing angle to generate a complete scene display video.

[0172] In some embodiments, after the scene display video is generated, a video preview interface is displayed on the upper layer of the screen of the current virtual scene, and the video preview interface is used to display the scene display video. Exemplarily, as shown in Figure 16, it shows a schematic diagram of a preview interface of a scene display video provided by an embodiment of the present application, the video preview interface 1600 includes a scene display video frame 1610, a regeneration control 1620, a video progress bar control 1630, a download control 1640, a release control 1650 and a video preview interface close control 1660, the scene display video frame 1610 is used to play the scene display video, and the scene display video frame 1610 includes a video progress bar control 1630, the video progress bar control 1630 is used to view the video playback progress, the regeneration control 1620 is used to fall back to the framing step, the download control 1640 is used to download the scene display video to the local, the release control 1650 is used to publish the scene display video to the social platform, and the video preview interface close control 1660 is used to close the video preview interface 1600.

[0173] Exemplarily, as shown in Figure 17, it shows a program flow chart of the video generation method provided by an embodiment of the present application. After obtaining m framing pictures selected by the user, each framing picture is analyzed, and the category of the framing point is determined according to the second position corresponding to the framing picture, that is, the position and angle of the virtual camera when shooting the framing picture. The corresponding camera movement method is determined according to the category of the framing point. If it is an outdoor framing point, the corresponding camera movement method is lens zoom-in and lens rotation. If it is an indoor framing point, the camera movement method is lens zoom-in and lens close-up. After recording based on the above-mentioned camera movement method, the scene display clip corresponding to the framing picture is obtained. The processing logic of each framing picture is the same. After all framing pictures are processed, m scene display clips are obtained. By splicing them together, a complete scene display video can be obtained.

[0174] To sum up, the technical solution provided in the embodiment of the present application can generate a scene display video directly based on the content of a plurality of framing pictures taken in a virtual scene, thereby realizing the automation of scene display video generation, streamlining the user operation steps, and significantly reducing the production time of the scene display video, thereby improving the generation efficiency of the scene display video, enabling users to see the scene display video as soon as possible, improving the user's interactive experience, and thereby improving the human-computer interaction rate.

[0175] The following are device embodiments of the present application, which can be used to implement the method embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the method embodiments of the present application.

[0176] Please refer to Figure 18, which shows a block diagram of a video generation device provided by one embodiment of the present application. This device has the functions of implementing the above-mentioned method examples. These functions can be implemented by hardware or by hardware executing corresponding software. This device can be the terminal device described above, or it can be provided in a terminal device. As shown in Figure 18, the device 1800 can include a display module 1810, a framing module 1820, and a presentation module 1830.

[0177] The display module 1810 is used to display the image of the virtual scene.

[0178] The framing module 1820 is configured to, in response to a framing operation on the virtual scene, display n framing pictures obtained by photographing the virtual scene from n framing perspectives, where different framing pictures are obtained by photographing the virtual scene from different framing perspectives, and n is a positive integer.

[0179] The display module 1830 is used to display a scene display video corresponding to the virtual scene in response to an operation for generating a video, where the scene display video is generated based on m framing pictures among the n framing pictures, where m is a positive integer less than or equal to n.

[0180] In some embodiments, the framing module 1820 is used to display the n framing pictures obtained by shooting the virtual scene from the n framing perspectives in a picture display bar; wherein the picture display bar is displayed on the upper layer of the screen of the virtual scene.

[0181] In some embodiments, the image display bar further displays a video generation control. The display module 1830 is configured to display the scene display video corresponding to the virtual scene in response to an operation on the video generation control.

[0182] In some embodiments, the image display bar has a corresponding display or hide control, and the display or hide control is used to switch the image display bar between a display state and a hidden state. The framing module 1820 is further configured to, when the image display bar is in the hidden state, switch the image display bar from the hidden state to the display state in response to an operation on the display or hide control; or, when the image display bar is in the display state, switch the image display bar from the display state to the hidden state in response to an operation on the display or hide control.

[0183] In some embodiments, a shooting control is also displayed on the upper layer of the image of the virtual scene, and the framing operation is an operation on the shooting control.

[0184] In some embodiments, the display module 1810 is further configured to, in response to an operation of adjusting the viewing angle, display a picture obtained by observing the virtual scene from the adjusted viewing angle.

[0185] In some embodiments, the apparatus 1800 further includes a marking module (not shown in FIG. 18 ).

[0186] The marking module is configured to mark and display a selected framing picture from the n framing pictures in response to an operation of selecting the framing picture; wherein the m framing pictures include the selected framing picture.

[0187] To sum up, the technical solution provided by the embodiment of the present application, by shooting multiple framing pictures in a virtual scene, the framing pictures are obtained by shooting the virtual scene from different framing perspectives, and a scene display video can be directly generated based on the framing pictures, thereby realizing the automation of scene display video generation. The user only needs to shoot different framing pictures in the virtual scene, and the scene display video can be automatically generated by the device, which simplifies the user operation steps and significantly reduces the production time of the scene display video, thereby improving the generation efficiency of the scene display video, allowing the user to see the scene display video as soon as possible, improving the user's interactive experience, and thereby improving the human-computer interaction rate.

[0188] Please refer to Figure 19, which shows a block diagram of a video generation device provided by another embodiment of the present application. The device has the functions of implementing the above-mentioned method examples, and the functions can be implemented by hardware or by hardware executing corresponding software. The device can be the terminal device described above, or it can be set in the terminal device; alternatively, the device can be the server described above, or it can be set in the server. As shown in Figure 19, the device 1900 may include: an acquisition module 1910 and a generation module 1920.

[0189] The acquisition module 1910 is configured to acquire m framing pictures obtained by photographing a virtual scene, where different framing pictures are obtained by photographing the virtual scene from different framing perspectives, and m is a positive integer.

[0190] The generating module 1920 is configured to generate a scene display video corresponding to the virtual scene based on the m framed images.

[0191] In some embodiments, the generation module 1920 includes: a camera movement determination unit, a segment generation unit, and a video generation unit (not shown in FIG. 19 ).

[0192] The camera movement determination unit is used to determine the camera movement modes corresponding to the m framing pictures respectively, and the camera movement modes are used to indicate the moving path and shooting angle of the virtual camera.

[0193] A segment generating unit is configured to generate scene display segments corresponding to the m framing pictures respectively based on the camera movement modes corresponding to the m framing pictures respectively; wherein the scene display segment corresponding to the i-th framing picture among the m framing pictures is a video segment obtained by controlling the virtual camera to shoot the virtual scene based on the moving path and shooting angle of the virtual camera indicated by the camera movement mode corresponding to the i-th framing picture, where i is a positive integer less than or equal to m.

[0194] The video generation unit generates the scene display video according to the scene display segments corresponding to the m framed images.

[0195] In some embodiments, the mirror movement determination unit includes: a category determination subunit, a first mirror movement unit, and a second mirror movement unit.

[0196] The category determination subunit is used to determine the viewing point category corresponding to the i-th viewing point picture according to the viewing point position of the i-th viewing point picture, where the viewing point category is an outdoor viewing point or an indoor viewing point.

[0197] The first mirror movement unit is used to determine that the mirror movement mode corresponding to the i-th framing picture is the first mirror movement mode if the viewing angle category of the i-th framing picture is the outdoor viewing angle.

[0198] The second mirror movement unit is used to determine that the mirror movement mode corresponding to the i-th framing picture is the second mirror movement mode if the viewing angle category of the i-th framing picture is the indoor viewing angle.

[0199] The first camera movement mode and the second camera movement mode are different.

[0200] In some embodiments, the segment generation unit is configured to, when the camera movement mode corresponding to the i-th framing picture is a first camera movement mode, control the virtual camera to capture the virtual scene based on a first movement path and a first shooting angle, thereby obtaining a scene display segment corresponding to the i-th framing picture; wherein the first camera movement mode includes: a zoom-in and a rotation; the first movement path includes a first sub-path indicated by the zoom-in, moving from a first position to a second position along a first direction, and a second sub-path indicated by the rotation, rotating from the second position to a third position around a first straight line within a horizontal plane at a first angle; the second position is a framing point position of the i-th framing picture, the distance between the first position and the second position is a first distance, the first direction is a lens orientation when capturing the i-th framing picture, and the first straight line is perpendicular to the horizontal plane; the first shooting angle includes a first shooting sub-angle indicated by the zoom-in, which is the virtual camera's movement along the first sub-path, and a second shooting sub-angle indicated by the rotation, which is the virtual camera's movement along the second sub-path.

[0201] In some embodiments, the fragment generation unit is used to control the virtual camera to shoot the virtual scene based on the second movement path and the second shooting angle when the camera movement mode corresponding to the i-th framing picture is the second camera movement mode, so as to obtain the scene display fragment corresponding to the i-th framing picture; wherein the second camera movement mode includes: lens zoom-in and lens close-up; the second movement path includes a third sub-path indicated by the lens zoom-in, which moves from the fourth position to the second position along the first direction, and a fourth sub-path indicated by the lens close-up, which moves from the second position to the fifth position; the second position is the viewing point position of the i-th framing picture, and the fourth position and the i-th framing picture are the same. The distance between the two positions is the second distance, the first direction is the lens direction when taking the i-th framing picture, and the fifth position is the set framing view position corresponding to the first virtual object contained in the i-th framing picture; the second shooting angle includes the third shooting sub-angle indicated by the lens zoom-in, which is the process of the virtual camera moving along the third sub-path, and the fourth shooting sub-angle indicated by the lens close-up, which is the process of the virtual camera moving along the fourth sub-path, the fourth shooting sub-angle is used to control the lens direction of the virtual camera to adjust from the first direction to the second direction, and the second direction is the set lens direction corresponding to the first virtual object.

[0202] In some embodiments, the segment generation unit further includes: a value scoring subunit and an item determination subunit.

[0203] The value scoring subunit is configured to determine a value score corresponding to at least one virtual item included in the i-th framed image, wherein the value score is used to represent the shooting value of the virtual item.

[0204] The item determination subunit is configured to determine the virtual item with the highest value score as the first virtual item.

[0205] In some embodiments, the fourth sub-path is a path starting from the second position and moving to each of the set viewing angle positions in sequence according to the set shooting order of the plurality of set viewing angle positions corresponding to the first virtual object.

[0206] In some embodiments, the category determination subunit is used to: obtain the construction area of ​​the virtual building corresponding to the i-th framing picture; if the viewing point position of the i-th framing picture is outside the construction area, then determine that the viewing point category corresponding to the i-th framing picture is an outdoor viewing point; if the viewing point position of the i-th framing picture is within the construction area, then determine that the viewing point category corresponding to the i-th framing picture is an indoor viewing point.

[0207] In some embodiments, the video generation unit is further configured to splice the scene display segments corresponding to the m framing pictures to generate the scene display video.

[0208] To sum up, the technical solution provided in the embodiment of the present application can generate a scene display video directly based on the content of a plurality of framing pictures taken in a virtual scene, thereby realizing the automation of scene display video generation, streamlining the user operation steps, and significantly reducing the production time of the scene display video, thereby improving the generation efficiency of the scene display video, enabling users to see the scene display video as soon as possible, improving the user's interactive experience, and thereby improving the human-computer interaction rate.

[0209] It should be noted that the apparatus provided in the above embodiments, when implementing its functions, is only illustrated by the division of the above functional modules. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above embodiments are based on the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0210] Please refer to Figure 20, which shows a block diagram of a terminal device 2000 provided in one embodiment of the present application. The terminal device 2000 may be the terminal device 10 in the implementation environment shown in Figure 1, and is used to implement the video generation method provided in the above embodiment. Specifically:

[0211] Typically, the terminal device 2000 includes: a processor 2010 and a memory 2020 .

[0212] The processor 2010 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 2010 may be implemented in at least one hardware form of digital signal processing (DSP), field programmable gate array (FPGA), and programmable logic array (PLA). The processor 2010 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a central processing unit (CPU); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 2010 may be integrated with a graphics processing unit (GPU), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 2010 may also include an AI processor for processing computing operations related to machine learning.

[0213] Memory 2020 may include one or more computer-readable storage media, which may be non-transitory. Memory 2020 may also include high-speed random access memory and non-volatile memory, such as one or more magnetic disk storage devices or flash memory storage devices. In some embodiments, the non-transitory computer-readable storage media in memory 2020 is used to store a computer program, which is configured to be executed by one or more processors to implement the above-described video generation method.

[0214] In some embodiments, terminal device 2000 may optionally include a peripheral device interface 2030 and at least one peripheral device. The processor 2010, memory 2020, and peripheral device interface 2030 may be connected via a bus or signal lines. Each peripheral device may be connected to peripheral device interface 2030 via a bus, signal lines, or circuit boards. Specifically, the peripheral device may include at least one of a radio frequency circuit 2040, a display screen 2050, an audio circuit 2060, and a power supply 2070.

[0215] Those skilled in the art will understand that the structure shown in FIG20 does not constitute a limitation on the terminal device 2000 , and may include more or fewer components than shown in the figure, or combine certain components, or adopt a different component arrangement.

[0216] Please refer to Figure 21, which shows a block diagram of a server 2100 provided in another embodiment of the present application. The server can be used to implement the functions of the above-mentioned video generation method. The server 2100 can be the server 20 in the implementation environment shown in Figure 1, which is used to implement the video generation method provided in the above-mentioned embodiment. Specifically:

[0217] The server 2100 includes a central processing unit (CPU) 2101, a system memory 2104 including a random access memory (RAM) 2102 and a read-only memory (ROM) 2103, and a system bus 2105 connecting the system memory 2104 and the CPU 2101. The server 2100 also includes a basic input / output (I / O) system 2106 that facilitates information transfer between various components within the computer, and a mass storage device 2107 for storing an operating system 2113, application programs 2114, and other program modules 2115.

[0218] The basic input / output system 2106 includes a display 2108 for displaying information and an input device 2109, such as a mouse and keyboard, for user input. Both the display 2108 and the input device 2109 are connected to the central processing unit 2101 via an input / output controller 2110 connected to the system bus 2105. The basic input / output system 2106 may also include an input / output controller 2110 for receiving and processing input from a variety of other devices, such as a keyboard, mouse, or electronic stylus. Similarly, the input / output controller 2110 also provides output to a display screen, printer, or other types of output devices.

[0219] The mass storage device 2107 is connected to the central processing unit 2101 via a mass storage controller (not shown) connected to the system bus 2105. The mass storage device 2107 and its associated computer-readable media provide non-volatile storage for the server 2100. In other words, the mass storage device 2107 may include a computer-readable medium (not shown) such as a hard disk or a CD-ROM (Compact Disc Read-Only Memory) drive.

[0220] Without loss of generality, computer-readable media may include computer storage media and communication media. Computer storage media include volatile and non-volatile, removable and non-removable media implemented by any method or technology for storing information such as computer-readable instructions, data structures, program modules or other data. Computer storage media include RAM, ROM, EPROM (Erasable Programmable Read Only Memory), EEPROM (Electrically Erasable Programmable Read Only Memory), flash memory or other solid-state storage technologies, CD-ROM, DVD (Digital Video Disc) or other optical storage, tape cassettes, magnetic tape, disk storage or other magnetic storage devices. Of course, those skilled in the art will appreciate that computer storage media are not limited to the above-mentioned ones. The above-mentioned system memory 2104 and mass storage device 2107 can be collectively referred to as memory.

[0221] According to various embodiments of the present application, the server 2100 may also be connected to a remote computer on a network such as the Internet for operation. That is, the server 2100 may be connected to the network 2112 via a network interface unit 2111 connected to the system bus 2105, or the network interface unit 2111 may be used to connect to other types of networks or remote computer systems (not shown).

[0222] The memory further includes a computer program, which is stored in the memory and configured to be executed by one or more processors to implement the above-mentioned video generation method.

[0223] In an exemplary embodiment, a non-volatile computer-readable storage medium is further provided, wherein a computer program is stored in the non-volatile computer-readable storage medium, and when the computer program is executed by a processor, the computer implements the above-mentioned video generation method. Optionally, the non-volatile computer-readable storage medium may include: a read-only memory (ROM), a random access memory (RAM), a solid-state drive (SSD), or an optical disk. Among them, the random access memory may include a resistance random access memory (ReRAM) and a dynamic random access memory (DRAM).

[0224] In an exemplary embodiment, a computer program product is further provided, the computer program product including a computer program stored in a computer-readable storage medium. A processor of a computer device reads the computer program from the computer-readable storage medium and executes the computer program, causing the computer device to perform the above-described video generation method.

[0225] In an exemplary embodiment, a computer program is further provided. The computer program is loaded and executed by a processor to enable a computer to implement the above-mentioned video generation method.

[0226] It should be noted that the collection and processing of relevant data in this application should be strictly in accordance with the requirements of relevant national laws and regulations when applied in practice, and the informed consent or separate consent of the personal information subject should be obtained. Subsequent data use and processing should be carried out within the scope of authorization of laws and regulations and the personal information subject.

[0227] It should be understood that the "multiple" mentioned in this article refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent three situations: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the previous and subsequent associated objects are in an "or" relationship. In addition, the step numbers described in this article only illustrate a possible execution sequence between the steps. In some other embodiments, the above steps may not be executed in the order of the numbers, such as two steps with different numbers are executed at the same time, or two steps with different numbers are executed in the opposite order to the diagram. The embodiments of the present application do not limit this.

[0228] The above description is merely an optional embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A video generation method, wherein: The method is performed by a computer device, and the method comprises: Displaying a picture of a virtual scene; In response to a framing operation on the virtual scene, displaying n framing pictures obtained by photographing the virtual scene from n framing perspectives, where different framing pictures are obtained by photographing the virtual scene from different framing perspectives, and n is a positive integer; In response to an operation for generating a video, a scene display video corresponding to the virtual scene is displayed, wherein the scene display video is generated based on m framing pictures among the n framing pictures, where m is a positive integer less than or equal to n.

2. The method according to claim 1, wherein: The displaying of n framing pictures obtained by photographing the virtual scene from n framing perspectives includes: In the picture display column, the n framing pictures obtained by shooting the virtual scene from the n framing angles are displayed; wherein the picture display column is displayed on the upper layer of the picture of the virtual scene.

3. The method according to claim 2, wherein: The picture display bar also displays a video generation control; The step of displaying a scene presentation video corresponding to the virtual scene in response to the operation for generating a video comprises: In response to an operation on the video generation control, the scene presentation video corresponding to the virtual scene is displayed.

4. The method according to claim 2 or 3, wherein: The picture display bar has a corresponding display or hide control, and the display or hide control is used to switch the picture display bar between a display state and a hidden state; the method also includes: When the picture display bar is in the hidden state, in response to an operation on the display or hide control, switching the picture display bar from the hidden state to the display state; or, When the picture display bar is in the display state, in response to an operation on the display or hide control, the picture display bar is switched from the display state to the hidden state.

5. The method according to any one of claims 1 to 4, wherein: A shooting control is also displayed on the upper layer of the screen of the virtual scene, and the framing operation is an operation on the shooting control.

6. The method according to any one of claims 1 to 5, wherein: The method further comprises: In response to the operation of adjusting the viewing angle, a picture obtained by observing the virtual scene from the adjusted viewing angle is displayed.

7. The method according to any one of claims 1 to 6, wherein: The method further comprises: In response to an operation of selecting a framed picture, a mark is displayed to indicate a selected framed picture among the n framed pictures; wherein the m framed pictures include the selected framed picture.

8. A video generation method, wherein: The method is performed by a computer device, and the method comprises: Obtain m framing pictures obtained by shooting a virtual scene, where different framing pictures are obtained by shooting the virtual scene from different framing perspectives, and m is a positive integer; Based on the m framed pictures, a scene display video corresponding to the virtual scene is generated.

9. The method according to claim 8, wherein: The step of generating a scene display video corresponding to the virtual scene based on the m framed pictures includes: Determine the camera movement modes corresponding to the m framing pictures respectively, where the camera movement modes are used to indicate the moving path and shooting angle of the virtual camera; Based on the camera movement modes respectively corresponding to the m framing pictures, scene display clips respectively corresponding to the m framing pictures are generated; wherein the scene display clip corresponding to the i-th framing picture among the m framing pictures is a video clip obtained by controlling the virtual camera to shoot the virtual scene based on the moving path and shooting angle of the virtual camera indicated by the camera movement mode corresponding to the i-th framing picture, and i is a positive integer less than or equal to m; The scene display video is generated according to the scene display segments respectively corresponding to the m framed images.

10. The method according to claim 9, wherein: The determining of the camera movement modes corresponding to the m frame pictures respectively includes: For the i-th framing picture, according to the framing point position of the i-th framing picture, determine the framing point category corresponding to the i-th framing picture, the framing point category being an outdoor framing point or an indoor framing point; If the viewing angle category of the i-th viewing angle picture is the outdoor viewing angle, determining that the camera movement mode corresponding to the i-th viewing angle picture is the first camera movement mode; If the viewing angle category of the i-th viewing angle picture is the indoor viewing angle, determining that the camera movement mode corresponding to the i-th viewing angle picture is the second camera movement mode; The first camera movement mode and the second camera movement mode are different.

11. The method according to claim 9 or 10, wherein: The generating of scene display clips corresponding to the m framing pictures respectively based on the camera movement modes respectively corresponding to the m framing pictures comprises: When the camera movement mode corresponding to the i-th framing picture is the first camera movement mode, based on a first moving path and a first shooting angle, controlling the virtual camera to shoot the virtual scene, to obtain a scene display segment corresponding to the i-th framing picture; Wherein, the first camera movement mode includes: zooming in and rotating the camera; The first moving path includes a first sub-path indicated by the zooming in of the lens, which moves from a first position to a second position along a first direction, and a second sub-path indicated by the rotation of the lens, which rotates from the second position to a third position around a first straight line at a first angle in a horizontal plane; the second position is a viewing angle position of the i-th framing picture, the distance between the first position and the second position is a first distance, the first direction is the lens orientation when taking the i-th framing picture, and the first straight line is perpendicular to the horizontal plane; The first shooting angle includes a first shooting sub-angle indicated by the lens zooming in when the virtual camera moves along the first sub-path, and a second shooting sub-angle indicated by the lens rotation when the virtual camera moves along the second sub-path.

12. The method according to claim 9 or 10, wherein: The generating of scene display clips corresponding to the m framing pictures respectively based on the camera movement modes respectively corresponding to the m framing pictures comprises: When the camera movement mode corresponding to the i-th framing picture is the second camera movement mode, based on the second moving path and the second shooting angle, the virtual camera is controlled to shoot the virtual scene to obtain a scene display segment corresponding to the i-th framing picture; Wherein, the second camera movement mode includes: zooming in and close-up; The second moving path includes a third sub-path indicated by the zoom-in of the lens moving from the fourth position to the second position along the first direction, and a fourth sub-path indicated by the close-up of the lens moving from the second position to the fifth position; the second position is a viewing angle position of the i-th framing picture, the distance between the fourth position and the second position is a second distance, the first direction is a lens direction when taking the i-th framing picture, and the fifth position is a set viewing angle position corresponding to a first virtual object included in the i-th framing picture; The second shooting angle includes a third shooting sub-angle indicated by the lens zoom-in and the virtual camera's movement along the third sub-path, and a fourth shooting sub-angle indicated by the lens close-up and the virtual camera's movement along the fourth sub-path, wherein the fourth shooting sub-angle is used to control the lens direction of the virtual camera to be adjusted from the first direction to a second direction, and the second direction is the set lens direction corresponding to the first virtual object.

13. The method according to claim 12, wherein: The method further comprises: Determine a value score corresponding to at least one virtual item included in the i-th framed picture, wherein the value score is used to represent the shooting value of the virtual item; The virtual item with the highest value score is determined as the first virtual item.

14. The method according to claim 12 or 13, wherein: The fourth sub-path is a path starting from the second position and moving to each of the set viewing angle positions in sequence according to the set shooting order of the plurality of set viewing angle positions corresponding to the first virtual object.

15. The method according to any one of claims 10 to 14, wherein: The determining, according to the viewing angle position of the i-th viewing angle picture, the viewing angle category corresponding to the i-th viewing angle picture includes: Obtaining a construction area of ​​a virtual building corresponding to the i-th framed image; If the location of the viewing point of the i-th viewing picture is outside the construction area, determining that the viewing point category corresponding to the i-th viewing picture is an outdoor viewing point; If the location of the viewing point of the i-th viewing picture is located within the construction area, it is determined that the viewing point category corresponding to the i-th viewing picture is an indoor viewing point.

16. The method according to any one of claims 9 to 14, wherein: The step of generating the scene display video according to the scene display segments respectively corresponding to the m framing pictures comprises: The scene display segments corresponding to the m frame pictures are spliced ​​together to generate the scene display video.

17. A video generating device, wherein: The device comprises: A display module, used for displaying the images of the virtual scene; A framing module, configured to, in response to a framing operation on the virtual scene, display n framing pictures obtained by photographing the virtual scene from n framing angles, wherein different framing pictures are obtained by photographing the virtual scene from different framing angles, and n is a positive integer; A display module is used to display a scene display video corresponding to the virtual scene in response to an operation for generating a video, wherein the scene display video is generated based on m framing pictures among the n framing pictures, where m is a positive integer less than or equal to n.

18. A video generating device, wherein: The device comprises: An acquisition module, used to acquire m framing pictures obtained by shooting a virtual scene, where different framing pictures are obtained by shooting the virtual scene from different framing perspectives, and m is a positive integer; A generation module is used to generate a scene display video corresponding to the virtual scene based on the m framing pictures.

19. A computer device, wherein: The computer device includes a processor and a memory, wherein a computer program is stored in the memory, and the computer program is loaded and executed by the processor so that the computer device implements the method according to any one of claims 1 to 7, or implements the method according to any one of claims 8 to 16.

20. A non-volatile computer-readable storage medium, wherein: The non-volatile computer-readable storage medium stores a computer program, which is loaded and executed by a processor to enable a computer to implement the method according to any one of claims 1 to 7, or to implement the method according to any one of claims 8 to 16.

21. A computer program product, wherein: The computer program product comprises a computer program, which is stored in a non-volatile computer-readable storage medium. The processor reads and executes the computer program from the non-volatile computer-readable storage medium to enable the computer to implement the method according to any one of claims 1 to 7, or implement the method according to any one of claims 8 to 16.

Images