Information display method, information processing method, device, equipment and storage medium

Abstract

The application discloses an information display method, an information processing method, a device, equipment and a storage medium, and relates to the technical field of image processing. The method comprises the following steps: displaying a shooting interface, wherein a real scene collected by a camera and a first character object in the real scene are displayed in the shooting interface; obtaining a shooting image obtained by shooting the first character object; displaying a posture selection interface, wherein at least one character posture for selection is displayed in the posture selection interface; and in response to an operation of selecting M character postures from the at least one character posture, displaying posture images corresponding to the M character postures respectively. The method for obtaining the posture images based on the shooting image is not limited by the posture of the first character object in the real scene, and the adjustment mode for the shooting image is enriched.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular to an information display method, information processing method, apparatus, device and storage medium. Background Technology

[0002] In some scenarios, after a user obtains a captured image, the user may want to adjust the image to achieve a different effect than the actual captured image.

[0003] In related technologies, adjustments to user-captured images are often made by adding new elements or applying filters, resulting in relatively simple adjustment methods. Summary of the Invention

[0004] This application provides an information display method, information processing method, apparatus, device, and storage medium. The technical solutions provided by this application include the following aspects.

[0005] According to one aspect of the embodiments of this application, an information display method is provided, the method comprising:

[0006] The camera displays a shooting interface, which shows the real scene captured by the camera and the first person object located in the real scene.

[0007] Obtain the captured image of the first person object;

[0008] The posture selection interface displays at least one character posture for selection.

[0009] In response to the operation of selecting M character poses from the at least one character pose, pose images corresponding to the M character poses are displayed, wherein the pose images are generated based on the captured images, and in the pose image corresponding to the i-th character pose among the M character poses, the character pose presented by the first character object is the i-th character pose, where M is an integer greater than or equal to 1, and i is a positive integer less than or equal to M.

[0010] According to one aspect of the embodiments of this application, an information processing method is provided, the method comprising:

[0011] Acquire posture indication information and capture images of the first human object. The posture indication information is used to indicate M human postures selected from at least one human posture, where M is an integer greater than or equal to 1.

[0012] Based on the posture indication information and the captured image, posture images corresponding to the M character postures are generated respectively. In the posture image corresponding to the i-th character posture among the M character postures, the character posture presented by the first character object is the i-th character posture, where i is a positive integer less than or equal to M.

[0013] According to one aspect of the embodiments of this application, an information display device is provided, the device comprising:

[0014] A shooting display module is used to display a shooting interface, which displays a real scene captured by the camera and a first person object located in the real scene;

[0015] The acquisition module is used to acquire the captured image obtained by photographing the first person object;

[0016] The selection display module is used to display the posture selection interface, which displays at least one character posture for selection.

[0017] A pose display module is configured to, in response to the operation of selecting M character poses from the at least one character pose, display pose images corresponding to the M character poses respectively, wherein the pose images are generated based on the captured images, and in the pose image corresponding to the i-th character pose among the M character poses, the character pose presented by the first character object is the i-th character pose, where M is an integer greater than or equal to 1, and i is a positive integer less than or equal to M.

[0018] According to one aspect of the embodiments of this application, an information processing apparatus is provided, the apparatus comprising:

[0019] The acquisition module is used to acquire posture indication information and the captured image obtained by capturing the first human object. The posture indication information is used to indicate M human postures selected from at least one human posture, where M is an integer greater than or equal to 1.

[0020] The generation module is used to generate posture images corresponding to the M character postures based on the posture indication information and the captured images, wherein, in the posture image corresponding to the i-th character posture among the M character postures, the character posture presented by the first character object is the i-th character posture, and i is a positive integer less than or equal to M.

[0021] According to one aspect of the embodiments of this application, a computer device is provided, the computer device including a processor and a memory, the memory storing a computer program, the computer program being loaded and executed by the processor to implement the above-described information display method, or to implement the above-described information processing method.

[0022] According to one aspect of the embodiments of this application, a computer-readable storage medium is provided, wherein a computer program is stored in the computer-readable storage medium, and the computer program is loaded and executed by a processor to implement the above-described information display method or the above-described information processing method.

[0023] According to one aspect of the embodiments of this application, a computer program product is provided, the computer program product including a computer program stored in a computer-readable storage medium, and a processor reading from the computer-readable storage medium and executing the computer program to implement the above-described information display method or the above-described information processing method.

[0024] The technical solution provided in this application can bring the following beneficial effects:

[0025] After capturing an image of the first person, a pose image is generated based on that image. The pose of the first person in the pose image is the one selected by the user (e.g., the first person) from a pose selection interface (which displays at least one selectable pose). In other words, in this method, the user can determine the pose of the first person in the pose image by selecting a pose, without the first person actually needing to assume that pose in the real-world scene. Therefore, this method of obtaining a pose image based on a captured image is not limited by the pose of the first person in the real-world scene, enriching the methods for adjusting captured images. Attached Figure Description

[0026] Figure 1 This is a schematic diagram of an image processing scheme provided in one embodiment of this application;

[0027] Figure 2 This is a schematic diagram of a computer system provided in one embodiment of this application;

[0028] Figure 3 This is a flowchart of an information display method provided in one embodiment of this application;

[0029] Figure 4 This is a schematic diagram of a scene for photographing a first person subject according to an embodiment of this application;

[0030] Figure 5 This is a schematic diagram of an attitude selection interface provided in one embodiment of this application;

[0031] Figure 6 This is a flowchart of an information display method provided in another embodiment of this application;

[0032] Figure 7 This is a flowchart of an information processing method provided in one embodiment of this application;

[0033] Figure 8 This is a schematic diagram illustrating the information interaction between a display terminal device, a cloud storage server, and an image server according to an embodiment of this application;

[0034] Figure 9 This is a flowchart of an information processing method provided in another embodiment of this application;

[0035] Figure 10 This is a schematic diagram of the pose image generation process provided in one embodiment of this application;

[0036] Figure 11 This is a schematic diagram of various parts of a first human figure provided in one embodiment of this application;

[0037] Figure 12 This is a block diagram of an information display device provided in one embodiment of this application;

[0038] Figure 13 This is a block diagram of an information processing apparatus provided in one embodiment of this application;

[0039] Figure 14 This is a structural block diagram of a computer device provided in one embodiment of this application. Detailed Implementation

[0040] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0041] Before introducing the technical solution of this application, some terms involved in this application will be explained. The following related explanations are optional and can be combined with the technical solutions of the embodiments of this application in any way, all of which fall within the protection scope of this application. The embodiments of this application include at least some of the following contents.

[0042] Style transfer: Style transfer refers to the transformation of images in two different domains. Specifically, it involves providing a style image and transforming any image into that style while preserving as much of the original image's content as possible.

[0043] Image consistency: Image consistency refers to the property of maintaining the overall characteristics and quality of an image in the fields of image processing or computer vision. The goal of image consistency is to ensure that images maintain a similar visual effect in different environments or processing procedures, so that the human eye can perceive the continuity and stability of the image.

[0044] AR (Augmented Reality) group photos: AR group photos refer to photos taken using augmented reality technology that allow real-world people to pose with virtual elements. Specifically, it adds fun and creative effects by overlaying virtual animations, effects, or decorations onto real photos of people.

[0045] Skeletal coordinates: In this embodiment of the application, skeletal coordinates are coordinates used to describe the position of various parts of a human object in a two-dimensional image.

[0046] In some scenarios, such as offline events for certain game applications, users often want their photos to have the same style as the virtual characters in the game application (such as AR group photos). Therefore, users can modify the visual style of the photo and add virtual elements related to the game application to achieve this goal after taking the photo. However, the user's pose in the photo may not match the style of the virtual character and the virtual elements, resulting in the final photo still not achieving the user's expected effect.

[0047] Please refer to Figure 1 The diagram illustrates an image processing scheme provided in one embodiment of this application.

[0048] In this scheme, such as Figure 1 As shown, on one hand, an image 10 is obtained by photographing the user (e.g., the first character object). On the other hand, at least one character pose is displayed for the user to choose from. After the user selects a pose, a pose image 20 is generated based on the user's chosen pose (e.g., pose A) and the image 10. In pose image 20, the user's visual style is the same as the visual style of the virtual character belonging to the game application, the user's pose is adjusted to the user's chosen pose, and virtual elements matching the user's chosen pose are displayed.

[0049] In the above solution, since the available character poses and the virtual elements that match the character poses can be pre-configured by technicians or the game application operator according to their compatibility with the game application or virtual character, the above solution can ensure that the user can blend in harmoniously and naturally in the final pose image, and that it matches the style of the virtual character.

[0050] It should be noted that this application may display prompt interfaces, pop-ups, or output voice prompts before and during the collection of user data. These prompt interfaces, pop-ups, or voice prompts are used to inform the user that their data is being collected. This ensures that the application only begins the steps for collecting user data after receiving confirmation from the user regarding the prompt interface or pop-up; otherwise (i.e., without user confirmation), the steps for collecting user data end, meaning no user data is collected. In other words, all user data collected by this application (including images obtained from photographing the first person) is processed strictly in accordance with the requirements of relevant national laws and regulations, obtaining the informed consent or separate consent of the data subject, and subsequent data use and processing are carried out within the scope of laws, regulations, and the data subject's authorization.

[0051] Please refer to Figure 2 This illustration shows a schematic diagram of a computer system provided in one embodiment of this application. The computer system includes a display terminal device 30 and a server 40.

[0052] The display device 30 is used to capture images of a first person. In some embodiments, the display device 30 includes a host 31, a camera 32, a screen 33, and a printer 34. The host 31 may have data transmission and processing functions. For example, the host may send the captured images to the server 40 and receive the processing results of the captured images from the server 40, and further process the processing results to obtain a pose image. The camera 32 is used to capture real-world scenes to obtain the captured images. The screen 33 is used to display the pose image generated based on the captured images. The printer 34 is used to print multimedia content (such as a photo album) based on the pose image. Of course, the display device 30 may also be other devices that integrate a camera and a screen. For example, the display device 30 may be an electronic device such as a mobile phone, tablet computer, multimedia playback device, PC (Personal Computer) in-vehicle terminal device, VR (Virtual Reality) device, AR device, MR (Mixed Reality) device, etc. In some embodiments, the display device 30 is equipped with a target application. When the target application is running, the display device 30 will perform steps such as image capture, information transmission and reception, and image processing to obtain the above-mentioned posture image.

[0053] Server 40 provides backend services to display device 30. In some embodiments, server 40 includes cloud storage server 41 and image server 42. Cloud storage server 41 provides storage services, such as storing images captured by display device 30. Image server 42 provides image processing services, such as calling artificial intelligence (AI) models to process images captured by display device 30. Server 40 can be a single server, a server cluster consisting of multiple servers, or a cloud computing service center.

[0054] The display device 30 and the server 40 can communicate via a network, such as a wireless or wired network.

[0055] Furthermore, in this embodiment, the implementation form of the target application is not limited. For example, it can be an application that needs to be downloaded and installed, a mini-program that does not require installation, a web application, etc.

[0056] Please refer to Figure 3 The diagram illustrates a flowchart of an information display method according to an embodiment of this application. The execution entity for each step of the method is a computer device, such as display device 30. The method may include at least one of the following steps (310-340).

[0057] Step 310: Display the shooting interface, which shows the real scene captured by the camera and the first person in the real scene.

[0058] The shooting interface is used to display the real scene captured by the camera.

[0059] In some embodiments, the shooting interface is displayed in response to an operation that triggers the shooting interface.

[0060] The operation that triggers the shooting interface can be an operation on the shooting interface trigger control displayed on the computer device (i.e., the control used to trigger the shooting interface), or an operation on scanning the first graphic code displayed on the computer device (i.e., the graphic code used to trigger the shooting interface, such as a QR code).

[0061] It should be noted that, in the embodiments of this application, the operations on the displayed content (such as controls, character poses, etc.) mentioned can be any operation on the displayed content, such as clicking, long pressing (the pressing time exceeds a set threshold, the set threshold is set by the technician as needed, such as 0.3s, 0.5s, 1s, etc.), sliding, etc., which will not be described in detail in the following embodiments.

[0062] For example, please refer to Figure 4 In a real-world scenario, the first person (object 41) stands in a designated area in front of the camera (32). The shooting interface (42) displays the real-world scene captured by the camera (32) and the first person (object 41) within that scene. When the first person (object 41) changes their expression or posture, the image captured by the camera (32) also changes accordingly.

[0063] Step 320: Obtain the captured image of the first person object.

[0064] In some embodiments, the captured image is acquired in response to the operation of capturing a first person object.

[0065] In some embodiments, the shooting interface and shooting control are displayed synchronously, and the shooting control is used to trigger the acquisition of a captured image. The operation of shooting the first person object is the operation of the shooting control. Of course, the operation of shooting the first person object can also be other operations. For example, if the computer device is a mobile phone, the operation of shooting the first person object can also be the operation of pressing the side button of the mobile phone. This application does not limit this.

[0066] Step 330: Display the posture selection interface, which shows at least one character posture to choose from.

[0067] Step 330 can be performed before, simultaneously with, or after steps 310 or 320, and this application does not limit it in this regard.

[0068] For example, in response to the operation of shooting a first person object, the captured image obtained by shooting the first person object is acquired, and a pose selection interface is displayed.

[0069] Human posture refers to a posture that supports human representation.

[0070] In some embodiments, the posture selection interface displays at least one character posture in the form of text. For example, the posture selection interface displays text such as "hands on hips", "standing", "holding a weapon", "unpacking", "unpacking" etc. (In some video games, "holding a weapon" refers to the posture of holding a virtual item in the game (such as a virtual shooting item), "unpacking" refers to installing a virtual explosive device, and the "unpacking" posture refers to the posture of installing a virtual explosive device. "unpacking" refers to removing a virtual explosive device, and the "unpacking" posture refers to the posture of removing a virtual explosive device.)

[0071] In some embodiments, such as Figure 5 As shown, the posture selection interface 50 displays at least one character posture 15 in a graphical form.

[0072] In some embodiments, at least one character pose is considered as N character poses, meaning that the pose selection interface displays N character poses for selection, where N is an integer greater than 1. In some embodiments, the pose selection interface 50 includes a pose drawing area for drawing character poses.

[0073] Step 340: In response to the operation of selecting at least M character poses, display the pose images corresponding to the M character poses respectively.

[0074] Among them, the pose image is generated based on the captured image. In the pose image corresponding to the i-th pose among M person poses, the pose presented by the first person object is the i-th person pose, where M is an integer greater than or equal to 1 and i is a positive integer less than or equal to M.

[0075] For example, if M characters have three poses, such as hands on hips, jumping, and running, then in the pose image corresponding to the first character pose, the first character object is in the pose of hands on hips; in the pose image corresponding to the second character pose, the first character object is in the pose of jumping; and in the pose image corresponding to the third character pose, the first character object is in the pose of running.

[0076] In some embodiments, the operation of selecting M character poses from at least one character pose can be an operation of clicking on the M character poses respectively, an operation of selecting the M character poses by swiping the screen, or an operation of inputting voice (such as indicating the name of the M character poses in voice). This application does not limit this operation.

[0077] In some embodiments, the operation of selecting M character poses from at least one character pose includes the operation of drawing M character poses (such as the operation of drawing M character poses in the pose drawing area described above).

[0078] In some embodiments, in response to the operation of drawing M character poses (in the pose drawing area described above), pose images corresponding to the M character poses are displayed.

[0079] In some embodiments, the pose drawing area includes drawing controls for drawing content within the pose drawing area. For example, a line setting control for setting lines in the pose drawing area, a graphic setting control for setting graphics in the pose drawing area, a coloring control for coloring graphics in the pose drawing area, etc. In this case, the operation of drawing M character poses includes operations on the drawing controls; that is, the user can draw M character poses using the drawing controls in the pose drawing area.

[0080] In some embodiments, the operation of drawing M character poses includes a swiping operation on the pose drawing area, that is, the user can directly outline the M character poses in the pose drawing area by swiping to draw the M character poses.

[0081] In some embodiments, the operation of drawing M character poses also includes the operation of drawing M character poses through body movements in a real scene (such as outlining M character poses with fingers). In this case, the operation of drawing M character poses can be identified from the real scene captured by the camera.

[0082] In the above embodiment, users can select M character poses by drawing M character poses themselves, which helps users express their pose adjustment needs more intuitively and enhances the interactivity and fun of character pose selection.

[0083] In some embodiments, please refer to Figure 6 The above information display method also includes the following step 350.

[0084] Step 350: In response to the confirmation of obtaining the pose images corresponding to the poses of the M individuals, the download information is displayed.

[0085] The download information is used to download multimedia content based on the pose images corresponding to the poses of M individuals.

[0086] In some embodiments, the multimedia content described above is a photo album created based on the pose images corresponding to the poses of M individuals.

[0087] In some embodiments, the multimedia content may also be comics, videos, posters, etc., created based on the posture images corresponding to the postures of M characters, and this application does not limit this.

[0088] The aforementioned download information may be a download link for downloading multimedia content, a graphic code (such as a QR code), etc., and this application does not limit this.

[0089] Through the above steps, when a user acquires a generated posture image, the image is automatically converted into multimedia content and corresponding download information is provided, thus facilitating user download and sharing.

[0090] In some embodiments, the multimedia content includes plot information and pose images corresponding to the poses of M characters respectively. The plot information is used to describe the plot story in which the first character object participates, in combination with the pose images corresponding to the poses of the M characters respectively. The plot information is determined based on the poses of the M characters and the order in which the poses of the M characters are selected.

[0091] The aforementioned plot information may include text, audio, etc., used to describe the plot story. For example, plot information may be narration played simultaneously with the display of the pose images corresponding to the poses of the M characters, or text displayed simultaneously introducing the content of the pose images. Another example is that the aforementioned multimedia content is in comic book format, with one pose image representing one page of comic book image, and the plot information being the dialogue text of the first character in the comic book image.

[0092] The plot information is determined based on the poses of M characters. In other words, the final plot information (story) may be different when the user selects different character poses.

[0093] For example, when M characters are in the "holding a weapon", "running", and "planting the bomb" positions, the story information is as follows: "Player holding a shooting weapon, ready to fire; Player runs towards location XX; Player successfully plants the bomb." When M characters are in the "holding a weapon", "running", and "defusing the bomb" positions, the story information is as follows: "Player holding a shooting weapon, ready to fire; Player runs towards location XX; Player successfully defuses the bomb."

[0094] The plot information is also determined based on the order in which the poses of the M characters are selected. That is to say, when the user selects the same M character poses, the final plot information (story) may be different if the order of selection is different.

[0095] For example, when M characters are in the following poses: "Running," "Planting the bomb," and "Hands on hips," the story information is as follows: "Player runs towards location XX, player successfully plants the bomb, explosive device is detonated, game won." Alternatively, when M characters are in the following poses: "Hands on hips," "Planting the bomb," and "Running," the story information is as follows: "Player confidently plants the bomb, but the enemy returns to defend, player escapes, explosive device is defused, game lost."

[0096] In the above embodiments, the multimedia content includes not only pose images but also plot information that describes the storyline along with the pose images, enriching the multimedia content provided to the user. Furthermore, the plot information is determined based on the poses of M characters and the order in which these poses are selected. This not only aligns with the semantics of the pose images but also encourages users to perform multiple pose selections to explore more of the storyline.

[0097] The technical solution provided in this application, after capturing an image of a first person, generates a pose image based on the captured image. The pose of the first person in the pose image is the pose selected by the user (e.g., the first person) from a pose selection interface (which displays at least one selectable person pose). In other words, in the above method, the user can determine the pose of the first person in the pose image by selecting a pose, without the first person actually exhibiting that pose in a real scene. Therefore, the method for obtaining a pose image based on a captured image is not limited to the pose of the first person in a real scene, enriching the methods for adjusting captured images.

[0098] In some embodiments, at least one character pose includes a character pose related to a virtual character belonging to a first brand, wherein the first character object has the same visual style as the virtual character in the pose image.

[0099] The primary brand can be an animation brand, a product brand, etc., and this application does not limit this.

[0100] For example, if the first brand is an animation brand, the virtual character belonging to the first brand is a virtual character in the animation product of that animation brand. For example, if the first brand is a product brand, the virtual character belonging to the first brand can be the mascot of that product brand.

[0101] The character poses associated with the virtual character belonging to the first brand can refer to the character poses provided by the brand owner of the first brand, or the character poses that the virtual character has presented or that the virtual character supports in presenting in the products of the first brand.

[0102] For example, if the first brand is an animation brand, the character poses related to the virtual character can be the poses that the virtual character has presented in the animation products of that animation brand.

[0103] In some embodiments, the visual style of the first person object in the pose image is the same as the visual style of the virtual character in the product of the first brand. For example, the visual style of the first person object in the pose image is the same as the visual style of the virtual character printed on the product of the first brand.

[0104] In some embodiments, at least one character pose includes a character pose related to a virtual character belonging to a first application, wherein the first character object has the same visual style as the virtual character in the pose image.

[0105] In some embodiments, virtual characters belonging to the first application include virtual characters presented when the first application is running (supported).

[0106] In some embodiments, the first application is a game application, including but not limited to: multiplayer online battle arena (MOBA) games, open-world games, first-person shooter (FPS) games, third-person shooter (TPS) games, adventure games (ATG), action games (ACT), and simulation games (SLG), etc.

[0107] For example, in the case that the first application is a game application, the virtual characters belonging to the game application may include player characters (PCs) that can be controlled by the user, and non-player characters (NPCs) that cannot be controlled by the user.

[0108] Of course, the first application mentioned above can also be other applications that support the presentation of virtual characters, such as video applications, social applications, etc.

[0109] For example, when the first application is a game application, the character poses associated with the virtual character can be poses that the virtual character supports displaying while the game application is running. For instance, when the game application is a shooting game, the character poses associated with the virtual character can include shooting with a weapon, planting a bomb, defusing a bomb, etc.

[0110] In some embodiments, in the pose image, the visual style of the first person object is the same as the visual style of the virtual character presented by the first application.

[0111] For example, the first application is a game application, and in the pose image, the visual style of the first character object is the same as the visual style of the virtual character presented by the game application when it is running.

[0112] In some embodiments, style transfer is performed through an artificial intelligence model to make the visual style of the first character object and the virtual character the same. This will be described in detail in the following information processing method embodiments, and will not be repeated here.

[0113] In the above embodiment, the at least one optional character pose provided to the user is related to a virtual character belonging to the first application. The visual style of the virtual character is also the reference for the visual style of the first character object in the pose image. Therefore, the above solution can ensure that the pose and visual style of the first character object in the pose image are consistent with the virtual character, thereby improving the style transfer effect of the pose image.

[0114] In some embodiments, virtual elements related to the first application are displayed in the pose image.

[0115] In some embodiments, virtual elements related to the first application include virtual elements displayed (supported) by the first application during runtime. For example, these virtual elements include virtual elements in a virtual scene displayed by the first application during runtime, such as virtual buildings, virtual shooting props, virtual explosive devices, virtual spray paint, etc. For example, these virtual elements include virtual elements displayed by the first application when loading a game match, such as the border and card face of a virtual card (used to present virtual characters participating in the game match). For example, these virtual elements include prompt elements displayed overlaid on the virtual scene to indicate game match-related information, such as virtual progress bars, virtual timers, etc. For example, these virtual elements include various options (such as options for setting parameters of the game application), controls (such as controls for controlling virtual characters), etc., displayed by the first application during runtime.

[0116] In the pose image corresponding to the i-th character's pose, the types and positions of the displayed virtual elements match the i-th character's pose.

[0117] Matching the type and position of virtual elements with the pose of the i-th character can also be understood as having a correspondence between the character's pose, the type and position of virtual elements, and the pose image. For example, please refer to Table 1 below, which shows an example of this correspondence.

[0118] Table 1

[0119]

[0120] In the above embodiment, the types and positions of the virtual elements displayed in the pose image corresponding to the i-th character's pose match the i-th character's pose. Therefore, in the pose images corresponding to different character poses, the types and positions of the virtual elements displayed will adaptively change with the character's pose, that is, virtual elements (such as game elements) can be correctly superimposed according to the character's pose, thereby ensuring the rationality and overall quality of the pose image.

[0121] In some embodiments, the virtual element type that matches the pose of the i-th character includes the target virtual element type.

[0122] In the pose image corresponding to the i-th pose, the first virtual element displayed is selected from virtual elements belonging to the target virtual element category based on the type of the first human object. The type of the first human object is determined based on the captured image.

[0123] The type of the first person subject can be classified according to any factors that can be inferred (extracted) based on the captured image, such as personality, body type, and age group. This application does not limit this.

[0124] In some embodiments, there is a correspondence between the specific virtual element in the target virtual element category, the type of the first person object, and the characteristics presented by the first person object in the captured photograph. Therefore, the type of the first person object that matches it can be determined based on the characteristics presented by the first person object in the captured image, and then the first virtual element that matches it can be determined based on the type of the first person object. For example, please refer to Table 2 below, which shows an example of the above correspondence (in this example, the target virtual element category is a virtual shooting prop, and the type of the first person object is divided according to personality).

[0125] Table 2

[0126]

[0127] In the above embodiment, the type of the first person object is first analyzed based on the actual captured image (i.e., the first person object in the real scene), and then the first virtual element displayed in the posture image is determined based on the type of the first person object. This achieves deep integration of the user's actual characteristics with the virtual element, thereby improving the integration of the first person object in the posture image (for example, when the user is fat, the user holds a large virtual shooting prop in the posture image, and when the user is thin, the user holds a small virtual shooting prop in the posture image).

[0128] In some embodiments, the virtual character belonging to the first application includes a first virtual character, and in the pose image, the first person object and the first virtual character have the same visual style.

[0129] The posture selection interface includes at least one character posture option corresponding to each character posture. In the character posture option, the first virtual character presents the character posture corresponding to the character posture option, and the first virtual character and the first character object belong to the same type.

[0130] In the character pose options, the first virtual character presents the character pose corresponding to the character pose option. That is to say, the character pose options are in the form of images, and their specific content is the first virtual character presenting the corresponding character pose.

[0131] Similar to the primary character object, the type of a virtual character can also be categorized by factors such as personality, body type, and age group, which this application does not limit. For example, the primary virtual character and the primary character object belong to the same personality type (e.g., calm). For example, the primary virtual object and the primary character object belong to the same age group type (e.g., middle-aged). For example, the primary virtual object and the primary character object belong to the same body type (e.g., thin).

[0132] In the above embodiment, the first virtual character, which belongs to the same type as the first character object, is used as a reference for the visual style of the first character object in the pose image. This further improves the style transfer effect of transferring the visual style of the first character object to the visual style of the virtual character belonging to the first application. Furthermore, when showing the user at least one character pose to choose from, the first virtual character is directly displayed to present these character poses, so that the user can anticipate the style transfer effect using this as a reference in advance.

[0133] In some embodiments, the above information display method further includes:

[0134] The object selection interface is displayed, showing at least two virtual characters (images or names) that can be selected from the various virtual characters belonging to the first application.

[0135] In cases where the second virtual character is selected out of at least two virtual characters, the first character object and the second virtual character have the same visual style in the pose image.

[0136] In some embodiments, the object selection interface and the attitude selection interface are displayed synchronously.

[0137] In some embodiments, in response to the operation of selecting M character poses from at least one character pose and selecting a second virtual character from at least two virtual characters, pose images corresponding to the M character poses are displayed.

[0138] The operation of selecting the second virtual character from at least two virtual characters can be an operation targeting the second virtual character, or it can be an operation of inputting voice to select the second virtual character (such as indicating the name of the second virtual character in voice). This application does not limit this.

[0139] In the above embodiment, an object selection interface is provided to support users in selecting a second virtual character as a style transfer reference. That is, users can freely select the visual style of the first character object in the pose image, which improves the interactivity of the solution and the freedom of style transfer.

[0140] In the following information processing method embodiments, the process of generating the pose image will be described in more detail. The information display method embodiments and information processing method embodiments provided in this application are interconnected and can be arbitrarily combined. For any details not described in detail in one embodiment, please refer to the other embodiment.

[0141] Please refer to Figure 7 The diagram illustrates a flowchart of an information processing method provided in one embodiment of this application. The execution entity for each step of the method is a computer device, such as a display terminal device 30 or a server 40. The method may include at least one of the following steps (710-720).

[0142] Step 710: Obtain posture indication information and the captured image of the first person object.

[0143] The pose indication information is used to indicate M character poses selected from at least one character pose, where M is an integer greater than or equal to 1.

[0144] In some embodiments, the M character poses are selected by drawing the M character poses.

[0145] In some embodiments, the pose indication information is generated (or sent) by the display device 30 in response to an operation of selecting at least M character poses.

[0146] In some embodiments, at least one character pose has corresponding identification information, and the pose indication information includes the identification information of each of the M character poses. The identification information of the character pose is used to distinguish different character poses; for example, the identification information of the character pose can be the character pose number, the character pose name, etc.

[0147] In some embodiments, please refer to Figure 8The display device 30 captures images via a camera (e.g., real-time image capture via WebRTC (Web Real-Time Communications)) and uploads the captured images to the cloud storage server 41 (by calling the API (Application Programming Interface) of the cloud storage server 41). The cloud storage server 41 returns a response to the display device 30, which includes a storage link for retrieving the captured images, such as a URL (Uniform Resource Locator). The display device 30 sends the aforementioned storage link and attitude indication information to the image server 42. The image server 42 receives the storage link and attitude indication information and retrieves the captured images from the cloud storage server 41 according to the storage link.

[0148] In some embodiments, when uploading captured images, the display device 30 compresses the captured images to reduce upload time. For example, the display device 30 compresses the captured images into formats such as JPEG (Joint Photographic Experts Group) or WebP.

[0149] In some embodiments, the display device 30 and the cloud storage server 41 use a one-way communication protocol (i.e., a communication protocol where the display device 30 initiates a communication request and the cloud storage server 41 returns a response), such as HTTPS (Hypertext Transfer Protocol Secure). The display device 30 and the image server 42 use a two-way communication protocol (i.e., both the display device 30 and the cloud storage server 41 support actively sending messages), such as WebSocket. In some embodiments, the display device 30 and the image server 42 automatically re-establish a connection after a disconnection to ensure that network fluctuations do not affect their data interaction process.

[0150] Step 720: Based on the posture indication information and the captured images, generate posture images corresponding to the postures of M individuals.

[0151] Among the M character poses, the pose image corresponding to the i-th character pose is the pose of the first character object, where i is a positive integer less than or equal to M.

[0152] In some embodiments, at least one character pose includes a pose related to a virtual character belonging to a first application. Step 720 includes: generating pose images corresponding to M character poses based on style images, pose indication information, and captured images, wherein the style images include the aforementioned virtual characters, and in the pose images, the first character object and the virtual characters have the same visual style.

[0153] For example, in the case where the first application is a game application, the style image includes screenshots of virtual characters when the game application is running.

[0154] In the above embodiment, the at least one optional character pose provided to the user is related to a virtual character belonging to the first application, and the visual style of the virtual character (the visual style of the virtual character in the above style image) is also the reference for the visual style of the first character object in the pose image. Therefore, the above solution can ensure that the pose and visual style of the first character object in the pose image are consistent with the virtual character, thereby improving the style transfer effect of the pose image.

[0155] In addition, in the above embodiment, since the pose images corresponding to the poses of the M individuals are all generated based on the same style image and captured image, it is possible to ensure that they have good image consistency.

[0156] In some embodiments, please refer to Figure 9 Step 720 includes at least one sub-step from steps 722 to 724.

[0157] Sub-step 722: Input the style image, pose indication information and captured image into the image processing model, and output the initial processed images corresponding to the poses of M individuals from the image processing model.

[0158] In the initial image corresponding to the i-th character pose, the first character object presents the i-th character pose, and the first character object has the same visual style as the virtual character.

[0159] Image processing models are deep learning models used to adjust the pose and visual style of people and objects in images.

[0160] In some embodiments, please refer to Figure 8 The image processing model is deployed on the image server 42. The image server 42 inputs the style image, pose indication information and captured image into the image processing model to obtain the initial processed images corresponding to the poses of M people.

[0161] In some embodiments, the image processor 42 employs multi-threading or multi-processing technology to support parallel processing of different pose indication information and different captured images.

[0162] In some embodiments, sub-step 722 includes the following steps:

[0163] 1. Select the first virtual character that belongs to the same type as the first character object from among the virtual characters belonging to the first application.

[0164] The types of virtual characters in the first application can be pre-defined by the technicians or the operator of the first application.

[0165] Please refer to the following example for the method of determining the type of the first character; it will not be repeated here.

[0166] 2. Input the first style image, pose indication information and captured image into the image processing model, and the image processing model outputs the initial processed images corresponding to the poses of M individuals.

[0167] The first style image includes the first virtual character.

[0168] In the above embodiment, the first virtual character, which belongs to the same type as the first character object, is used as a reference for the visual style of the first character object in the pose image (i.e., the first style image mentioned above), which further improves the style transfer effect of transferring the visual style of the first character object to the visual style of the virtual character belonging to the first application.

[0169] In some other embodiments, sub-step 722 includes the following steps:

[0170] 1. Obtain role instruction information, which is used to indicate the second virtual role selected from the various virtual roles belonging to the first application.

[0171] In some embodiments, the role indication information is generated (or sent) by the display device 30 in response to the operation of selecting a second virtual role.

[0172] In some embodiments, the role indication information includes the identification information of the second virtual role, which is used to indicate the second virtual role, such as the number and name of the second virtual role.

[0173] 2. Input the second-style image, pose indication information, and captured image into the image processing model, and the image processing model outputs the initial processed images corresponding to the poses of M individuals.

[0174] The second style of imagery includes a second virtual character.

[0175] In the above embodiment, the user can select a second virtual character as a style transfer reference, that is, the user can freely choose the visual style of the first character object in the pose image, which improves the interactivity of the solution and the freedom of style transfer.

[0176] Sub-step 724: Add virtual elements related to the first application to the initial processing image corresponding to the i-th character pose to obtain the pose image corresponding to the i-th character pose.

[0177] In the initial processed image corresponding to the i-th character pose, the type and position of the added virtual elements are matched with the i-th character pose.

[0178] In some embodiments, please refer to Figure 8 The image server 42 returns the initial processed images corresponding to the poses of M characters to the display terminal device 30. The display terminal device 30 adds virtual elements related to the first application to the initial processed image corresponding to the i-th character pose to obtain the pose image corresponding to the i-th character pose.

[0179] The pose images corresponding to the poses of the M characters can all be obtained by using the same method as the pose image corresponding to the pose of the i-th character, which will not be elaborated upon in this application.

[0180] For example, please refer to Figure 10 The style image 101, posture indication information 102 (such as the text "holding device") and the captured image 10 are input into the image processing model 110. The image processing model outputs the initial processed image 103 corresponding to the "holding device" posture. Virtual elements 104 (virtual shooting props) are added to the initial processed image 103 corresponding to the "holding device" posture to obtain the posture image 20 corresponding to the "holding device" posture.

[0181] In the above embodiment, the types and positions of the virtual elements displayed in the pose image corresponding to the i-th character's pose match the i-th character's pose. Therefore, in the pose images corresponding to different character poses, the types and positions of the virtual elements displayed will adaptively change with the character's pose, that is, virtual elements (such as game elements) can be correctly superimposed according to the character's pose, thereby ensuring the rationality and overall quality of the pose image.

[0182] In some embodiments, sub-step 724 includes at least one of the following steps:

[0183] 1. From at least two virtual element types, determine the virtual element type that matches the pose of the i-th character, and use it as the target virtual element type.

[0184] In some embodiments, at least one character pose is pre-configured with a corresponding virtual element type (for example, see Table 1 in the embodiments above), and the virtual element type pre-configured for the i-th character pose among at least two virtual element types is taken as the target virtual element type.

[0185] In some embodiments, the identification information of the i-th character's pose from the pose indication information is input into the category determination model, which then determines the category of the virtual element that matches the i-th character's pose. The category determination model is a deep learning model used to determine the category of virtual elements that match the character's pose.

[0186] 2. Select a virtual element as the first virtual element from among the virtual elements that are related to the first application and belong to the target virtual element category.

[0187] In some embodiments, among the virtual elements related to the first application and belonging to the target virtual element category, there is only one virtual element, which is designated as the first virtual element.

[0188] The required type of target virtual element can be one or at least two. Similarly, the first virtual element selected from each target virtual element can be one or at least two. This application does not limit this.

[0189] In some embodiments, this step includes the following two steps:

[0190] (1) Determine the type of the first person based on the captured image.

[0191] In some embodiments, features of a first person object are determined from the captured image, and the person type corresponding to the features of the first person object is determined as the type of the first person object.

[0192] In some embodiments, features of a first person object are identified by an image recognition model (the captured image is input into the image recognition model, and the image recognition model outputs features of the first person object). The image recognition model is a deep learning model used to extract image features. For example, the features output by the image recognition model may be features indicating whether the first person object is wearing glasses or has a beard.

[0193] In some embodiments, the skeletal coordinates of the first person object are identified from the captured image when it is presenting an actual pose (i.e., the actual pose of the first person object in the captured image). (When presenting an actual pose, the skeletal coordinates of the first person object include the coordinates of various parts of the first person object in the captured image.) Based on the skeletal coordinates of the first person object when presenting an actual pose, the features presented by the first person object are determined.

[0194] For example, in the aforementioned skeletal coordinates, if the distance between the coordinates of the corner of the first character's mouth and the coordinates of the center of the mouth is greater than a first threshold, it can be determined that the first character has a happy expression; if the distance between the coordinates of the corner of the first character's mouth and the coordinates of the center of the mouth is less than or equal to the first threshold, it can be determined that the first character has a calm expression. If the distance between the coordinates of the first character's hands is greater than a certain threshold, it can be determined that the first character has a large range of limb movements; if the distance between the first character's hands is less than or equal to a certain threshold, it can be determined that the first character has a moderate range of limb movements. The aforementioned first and second thresholds are set as needed by those skilled in the art, and this application does not impose any limitations on them.

[0195] (2) From the virtual elements that are related to the first application and belong to the target virtual element category, determine the virtual element that matches the type of the first character object as the first virtual element.

[0196] In some embodiments, the matching or correspondence between the characteristics of the character object, the type of the character object, and the virtual element (the three) is pre-configured (for example, see Table 2 in the embodiments above).

[0197] In the above embodiment, the type of the first person object is first analyzed based on the actual captured image (i.e., the first person object in the real scene), and then the first virtual element to be added to the initial processed image is determined based on the type of the first person object. This achieves deep integration of the user's actual features with the virtual element, thereby improving the integration of the first person object in the pose image.

[0198] 3. From the initial processed image corresponding to the i-th character pose, identify the skeletal coordinates of the first character object when presenting the i-th character pose.

[0199] In some embodiments, when presenting the pose of the i-th character, the skeletal coordinates of the first character object include the coordinates of each part of the first character object in the initial processed image corresponding to the i-th character pose. Therefore, the pose of the first character object presented in the pose image can be reflected based solely on the skeletal coordinates of the first character object.

[0200] For example, please refer to Figure 11 This illustration shows a schematic diagram of various parts of a first human figure provided in an embodiment of this application. In this example, each part can be regarded as a point in the initial processed image corresponding to the i-th human figure pose. It can be seen that, based on the coordinates of these points, the i-th human figure pose presented by the first human figure in the initial processed image can be completely constructed.

[0201] In some embodiments, the initial processed image corresponding to the pose of the i-th person is input into the part recognition model, and the part recognition model outputs the skeletal coordinates of the first person object when the pose of the i-th person is presented.

[0202] A part recognition model is a deep learning model used to identify parts (i.e. key points) in an image that are used to construct skeletal coordinates.

[0203] 4. Based on the skeletal coordinates of the first character object (when presenting the i-th character pose), add the first virtual element to the initial image corresponding to the i-th character pose to obtain the pose image corresponding to the i-th character pose.

[0204] For example, based on Figure 11 In the initial image corresponding to the i-th character pose, the coordinates of the left shoulder (in the initial image corresponding to the i-th character pose) and the coordinates of the right shoulder are added. A virtual shawl is added to the initial image corresponding to the i-th character pose to obtain the pose image corresponding to the i-th character pose.

[0205] In the above embodiment, by identifying the skeletal coordinates of the first character object when presenting the i-th character pose, the position of the virtual elements superimposed on the first character object can be precisely controlled to ensure that the virtual elements are correctly superimposed, thereby ensuring that the final generated pose image is reasonable and natural.

[0206] In some embodiments, the above information processing method further includes step 730 ( Figure 7 (Not shown in the image).

[0207] Step 730: After obtaining the image confirmation information, multimedia content is created based on the posture images corresponding to the M character poses, and download information for downloading the multimedia content is generated. The image confirmation information is used to indicate confirmation of obtaining the posture images corresponding to the M character poses.

[0208] In some embodiments, the image confirmation information is generated (or sent) by the display device 30 in response to the operation of confirming the acquisition of posture images corresponding to the postures of M individuals.

[0209] In some embodiments, pose images corresponding to the poses of M individuals are filled into a photo album template to obtain multimedia content in the form of a photo album. The aforementioned photo album template is a template used to generate the photo album, and it may be provided by the operator of the first application.

[0210] Through the above steps, when a user acquires a generated posture image, the image is automatically converted into multimedia content and corresponding download information is provided, thus facilitating user download and sharing.

[0211] In some embodiments, when M is greater than 1, the attitude indication information is also used to indicate the order in which the M character attitudes are selected. For example, in the attitude indication information, the identification information of each of the M character attitudes is arranged in the order in which the M character attitudes are selected.

[0212] The above-mentioned creation of multimedia content based on the pose images corresponding to the poses of M individuals includes the following two steps:

[0213] 1. Based on the posture indication information, determine the plot information. The plot information is used to describe the plot story in which the first character object participates by combining the posture images corresponding to the postures of M characters.

[0214] In some embodiments, gesture indication information is input into the plot generation model, and the plot generation model outputs plot information. The plot generation model is a deep learning model with plot reasoning capabilities, such as a large language model.

[0215] In some embodiments, at least one character pose is N character poses. Each combination of the N character poses has corresponding pre-configured plot information, and the combination of character poses includes at least two character poses arranged in sequence. The above steps include:

[0216] (1) Determine the target character posture combination that conforms to the posture indication information and the order in which the M character postures are selected.

[0217] (2) The pre-configured plot information corresponding to the target character's posture combination is determined as plot information.

[0218] 2. Based on the plot information and the posture images corresponding to the postures of M characters, create multimedia content.

[0219] In the above embodiments, the multimedia content includes not only pose images but also plot information that describes the storyline along with the pose images, enriching the multimedia content provided to the user. Furthermore, the plot information is determined based on the poses of M characters and the order in which these poses are selected. This not only aligns with the semantics of the pose images but also encourages users to perform multiple pose selections to explore more of the storyline.

[0220] The technical solution provided in this application, after capturing an image of a first person, generates a pose image based on the captured image. The pose of the first person in the pose image is the pose selected by the user (e.g., the first person) from a pose selection interface (which displays at least one selectable person pose). In other words, in the above method, the user can determine the pose of the first person in the pose image by selecting a pose, without the first person actually exhibiting that pose in a real scene. Therefore, the method for obtaining a pose image based on a captured image is not limited to the pose of the first person in a real scene, enriching the methods for adjusting captured images.

[0221] In summary, this application proposes to generate stylized pose images through AIGC (AI-Generated Content) and combine it with AI recognition of user skeletal points to dynamically overlay virtual elements, achieving personalized immersive image creation. Each pose image not only showcases the user's unique style but also integrates visual symbols from the primary application, making each pose image a personalized "brand commemorative scroll." This solution integrates image consistency technology, AI recognition of key human body coordinates, and dynamic AR group photo technology to transform user photos into personalized photo albums in real time, creating an immersive interactive experience for users. This solution incorporates virtual elements related to the primary application, making each group photo a unique "pose album," while significantly improving user engagement and brand communication effects, optimizing marketing and operational efficiency, and constructing a new and intelligent interactive solution for future digital entertainment and social interaction scenarios.

[0222] The following are embodiments of the apparatus described in this application, which can be used to execute the embodiments of the method described in this application. For details not disclosed in the apparatus embodiments of this application, please refer to the embodiments of the method described in this application.

[0223] Please refer to Figure 12 This diagram illustrates a block diagram of an information display device according to an embodiment of this application. The device has the function of implementing the aforementioned information display method; this function can be implemented in hardware or by hardware executing corresponding software. The device can be a computer device or can be installed within a computer device. The device 1200 includes: a capture display module 1210, an acquisition module 1220, a selection display module 1230, and a posture display module 1240.

[0224] The shooting display module 1210 is used to display a shooting interface, which displays a real scene captured by the camera and a first person object located in the real scene.

[0225] The acquisition module 1220 is used to acquire the captured image obtained by capturing the first person object.

[0226] Select display module 1230, used to display posture selection interface, the posture selection interface displays at least one character posture for selection.

[0227] The posture display module 1240 is used to display posture images corresponding to the M character postures respectively in response to the operation of selecting M character postures from the at least one character posture. The posture images are generated based on the captured images. In the posture image corresponding to the i-th character posture among the M character postures, the character posture presented by the first character object is the i-th character posture. M is an integer greater than or equal to 1, and i is a positive integer less than or equal to M.

[0228] In some embodiments, the at least one character pose includes a character pose related to a virtual character belonging to a first application, wherein the first character object and the virtual character have the same visual style in the pose image.

[0229] In some embodiments, the pose image displays virtual elements related to the first application; wherein, in the pose image corresponding to the i-th character pose, the type and position of the virtual elements displayed match the i-th character pose.

[0230] In some embodiments, the type of virtual element matching the i-th character pose includes a target virtual element type; in the pose image corresponding to the i-th pose, the first virtual element displayed is selected from virtual elements belonging to the target virtual element type based on the type of the first character object, and the type of the first character object is determined based on the captured image.

[0231] In some embodiments, the virtual character belonging to the first application includes a first virtual character, and in the posture image, the first character object and the first virtual character have the same visual style; the posture selection interface includes character posture options corresponding to the at least one character posture, wherein, in the character posture options, the first virtual character presents the character posture corresponding to the character posture option, and the first virtual object and the first character object belong to the same type.

[0232] In some embodiments, the selection display module 1230 is further configured to display an object selection interface, which displays at least two virtual characters from among the virtual characters belonging to the first application, for selection; wherein, when the second virtual character from among the at least two virtual characters is selected, the first character object and the second virtual character have the same visual style in the pose image.

[0233] In some embodiments, the above-described device 1200 further includes a download display module ( Figure 12 (Not shown in the image).

[0234] The download display module is used to display download information in response to the operation of confirming the acquisition of the posture images corresponding to the M character postures, wherein the download information is used to download multimedia content made based on the posture images corresponding to the M character postures.

[0235] In some embodiments, when M is greater than 1, the multimedia content includes plot information and posture images corresponding to the M character postures respectively. The plot information is used to describe the plot story in which the first character participates, in combination with the posture images corresponding to the M character postures respectively. The plot information is determined based on the M character postures and the order in which the M character postures are selected.

[0236] Please refer to Figure 13 This diagram illustrates a block diagram of an information processing apparatus according to an embodiment of this application. The apparatus has the function of implementing the aforementioned information processing method; this function can be implemented in hardware or by hardware executing corresponding software. The apparatus 1300 can be a computer device or can be installed within a computer device. The apparatus 1300 includes: an acquisition module 1310 and a generation module 1320.

[0237] The acquisition module 1310 is used to acquire posture indication information and the captured image obtained by capturing the first human object. The posture indication information is used to indicate M human postures selected from at least one human posture, where M is an integer greater than or equal to 1.

[0238] The generation module 1320 is used to generate posture images corresponding to the M character postures based on the posture indication information and the captured images, wherein, in the posture image corresponding to the i-th character posture among the M character postures, the character posture presented by the first character object is the i-th character posture, and i is a positive integer less than or equal to M.

[0239] In some embodiments, the at least one character pose includes a pose related to a virtual character belonging to the first application.

[0240] The generation module 1320 is used to generate posture images corresponding to the postures of the M characters based on the style image, the posture indication information and the captured image, wherein the style image includes the virtual character, and in the posture image, the first character object and the virtual character have the same visual style.

[0241] In some embodiments, the generation module 1320 includes an initial processing submodule and an adding submodule. Figure 13 (Not shown in the image).

[0242] The initial processing submodule is used to input the style image, the posture indication information and the captured image into the image processing model, and the image processing model outputs the initial processing images corresponding to the M character postures respectively. In the initial processing image corresponding to the i-th character posture, the character posture presented by the first character object is the i-th character posture, and the first character object has the same visual style as the virtual character.

[0243] An additional submodule is added to the initial processed image corresponding to the i-th character pose, adding virtual elements related to the first application to obtain a pose image corresponding to the i-th character pose, wherein the type and position of the added virtual elements in the initial processed image corresponding to the i-th character pose match the i-th character pose.

[0244] In some embodiments, a submodule is added for determining, from at least two virtual element types, a virtual element type that matches the i-th character pose as a target virtual element type; selecting a virtual element as a first virtual element from virtual elements related to the first application and belonging to the target virtual element type; identifying, from the initial processed image corresponding to the i-th character pose, the skeletal coordinates of the first character object when the i-th character pose is presented; and adding the first virtual element to the initial processed image corresponding to the i-th character pose based on the skeletal coordinates of the first character object to obtain a pose image corresponding to the i-th character pose.

[0245] In some embodiments, a submodule is added for determining the type of the first person object based on the captured image; and determining, from virtual elements related to the first application and belonging to the target virtual element category, a virtual element that matches the type of the first person object as the first virtual element.

[0246] In some embodiments, the device 1300 further includes a manufacturing module ( Figure 13 (Not shown in the image).

[0247] The production module is used to produce multimedia content based on the posture images corresponding to the M character postures after obtaining image confirmation information, and to generate download information for downloading the multimedia content. The image confirmation information is used to indicate confirmation of obtaining the posture images corresponding to the M character postures.

[0248] In some embodiments, when M is greater than 1, the posture indication information is also used to indicate the order in which the M character postures are selected.

[0249] The production module is used to determine plot information based on the posture indication information, wherein the plot information is used to describe the plot story in which the first character participates, in combination with the posture images corresponding to the postures of the M characters; and to produce the multimedia content based on the plot information and the posture images corresponding to the postures of the M characters.

[0250] It should be noted that the apparatus provided in the above embodiments is only illustrated by the division of the above functional modules when implementing its functions. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the content 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 belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0251] Please refer to Figure 14 The diagram illustrates a structural block diagram of a computer device provided in one embodiment of this application.

[0252] Typically, computer device 1400 includes a processor 1401 and a memory 1402.

[0253] Processor 1401 may include one or at least two processing cores, such as a quad-core processor, an octa-core processor, etc. Processor 1401 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field Programmable Gate Array), and PLA (Programmable Logic Array). Processor 1401 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, processor 1401 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, processor 1401 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0254] The memory 1402 may include one or at least two computer-readable storage media, which may be tangible and non-transitory. The memory 1402 may also include high-speed random access memory and non-volatile memory, such as one or at least two disk storage devices or flash memory devices. In some embodiments, the non-transitory computer-readable storage media in the memory 1402 stores a computer program that is loaded and executed by the processor 1401 to implement the aforementioned information display method or the aforementioned information generation method.

[0255] Those skilled in the art will understand that Figure 14 The structure shown does not constitute a limitation on the computer device 1400, and may include more or fewer components than shown, or combine certain components, or use different component arrangements.

[0256] In an exemplary embodiment, a computer-readable storage medium is also provided, wherein a computer program is stored therein, which, when executed by a processor, implements the above-described information display method or the above-described information generation method.

[0257] Optionally, the computer-readable storage medium may include: ROM (Read-Only Memory), RAM (Random Access Memory), SSD (Solid State Drives), or optical disc, etc. The random access memory may include ReRAM (Resistance Random Access Memory) and DRAM (Dynamic Random Access Memory).

[0258] In an exemplary embodiment, a computer program product is also provided, comprising 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 the processor executes the computer program, causing the computer device to perform an information display method or implement the aforementioned information generation method.

[0259] It should be noted that the collection and processing of relevant data (such as images obtained from photographing the first person subject) in this application should strictly comply with the requirements of relevant national laws and regulations, obtain the informed consent or separate consent of the personal information subject, and carry out subsequent data use and processing within the scope of laws and regulations and the authorization of the personal information subject.

[0260] It should be understood that "at least two" as mentioned herein refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. Furthermore, the step numbers described herein are merely illustrative of one possible execution order. In some other embodiments, the steps may not be executed in numerical order, such as two steps with different numbers being executed simultaneously, or two steps with different numbers being executed in the reverse order of the illustration. This application does not limit this.

[0261] The above description is merely an exemplary embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. An information display method, characterized in that, The method includes: The camera displays a shooting interface, which shows the real scene captured by the camera and the first person object located in the real scene. Obtain the captured image of the first person object; The posture selection interface displays at least one character posture for selection. In response to the operation of selecting M character poses from the at least one character pose, pose images corresponding to the M character poses are displayed, wherein the pose images are generated based on the captured images, and in the pose image corresponding to the i-th character pose among the M character poses, the character pose presented by the first character object is the i-th character pose, where M is an integer greater than or equal to 1, and i is a positive integer less than or equal to M.

2. The method according to claim 1, characterized in that, The at least one character pose includes a character pose related to a virtual character belonging to the first application, wherein the first character object and the virtual character have the same visual style in the pose image.

3. The method according to claim 2, characterized in that, The posture image displays virtual elements related to the first application; In the pose image corresponding to the i-th character's pose, the type and position of the virtual elements displayed match the i-th character's pose.

4. The method according to claim 3, characterized in that, The types of virtual elements that match the pose of the i-th character include the target virtual element types; In the pose image corresponding to the i-th pose, the first virtual element displayed is selected from virtual elements belonging to the target virtual element category based on the type of the first human object, and the type of the first human object is determined based on the captured image.

5. The method according to any one of claims 2 to 4, characterized in that, The virtual characters belonging to the first application include a first virtual character, and in the pose image, the first character object has the same visual style as the first virtual character; The posture selection interface includes character posture options corresponding to the at least one character posture, wherein the first virtual character presents the character posture corresponding to the character posture option, and the first virtual character and the first character object belong to the same type.

6. The method according to any one of claims 2 to 4, characterized in that, The method further includes: Display an object selection interface, in which at least two virtual characters belonging to the first application are displayed for selection; Wherein, when the second virtual character among the at least two virtual characters is selected, the first character object and the second virtual character have the same visual style in the pose image.

7. The method according to any one of claims 1 to 6, characterized in that, The method further includes: In response to the confirmation of obtaining the posture images corresponding to the M character postures, download information is displayed. The download information is used to download multimedia content created based on the posture images corresponding to the M character postures.

8. The method according to claim 7, characterized in that, When M is greater than 1, the multimedia content includes plot information and posture images corresponding to the M character postures respectively. The plot information is used to describe the plot story in which the first character participates, in combination with the posture images corresponding to the M character postures respectively. The plot information is determined based on the M character postures and the order in which the M character postures are selected.

9. An information processing method, characterized in that, The method includes: Acquire posture indication information and capture images of the first human object. The posture indication information is used to indicate M human postures selected from at least one human posture, where M is an integer greater than or equal to 1. Based on the posture indication information and the captured image, posture images corresponding to the M character postures are generated respectively. In the posture image corresponding to the i-th character posture among the M character postures, the character posture presented by the first character object is the i-th character posture, where i is a positive integer less than or equal to M.

10. The method according to claim 9, characterized in that, The at least one character pose includes poses related to virtual characters belonging to the first application; The step of generating posture images corresponding to the postures of the M individuals based on the posture indication information and the captured images includes: Based on the style image, the posture indication information, and the captured image, posture images corresponding to the postures of the M characters are generated respectively. The style image includes the virtual character, and in the posture image, the first character object and the virtual character have the same visual style.

11. The method according to claim 10, characterized in that, The process of generating pose images corresponding to the poses of the M individuals based on the style image, the pose indication information, and the captured image includes: The style image, the posture indication information, and the captured image are input into the image processing model, and the image processing model outputs the initial processed images corresponding to the M character postures respectively. In the initial processed image corresponding to the i-th character posture, the character posture presented by the first character object is the i-th character posture, and the first character object has the same visual style as the virtual character. In the initial image corresponding to the i-th character pose, virtual elements related to the first application are added to obtain the pose image corresponding to the i-th character pose, wherein the type and position of the added virtual elements in the initial image corresponding to the i-th character pose match the i-th character pose.

12. The method according to claim 11, characterized in that, The step of adding virtual elements related to the first application to the initial processed image corresponding to the i-th character pose to obtain the pose image corresponding to the i-th character pose includes: From at least two virtual element types, determine the virtual element type that matches the pose of the i-th character, and use it as the target virtual element type; From virtual elements that are related to the first application and belong to the target virtual element category, select a virtual element as the first virtual element; From the initial processed image corresponding to the i-th character pose, identify the skeletal coordinates of the first character object when presenting the i-th character pose; Based on the skeletal coordinates of the first character object, the first virtual element is added to the initial processed image corresponding to the i-th character pose to obtain the pose image corresponding to the i-th character pose.

13. The method according to claim 12, characterized in that, The step of selecting a virtual element as the target virtual element from virtual elements related to the first application and belonging to the target virtual element category includes: Based on the captured images, the type of the first person object is determined; From the virtual elements that are related to the first application and belong to the target virtual element category, determine the virtual element that matches the type of the first character object as the first virtual element.

14. The method according to any one of claims 9 to 13, characterized in that, The method further includes: After obtaining the image confirmation information, multimedia content is created based on the posture images corresponding to the M individual character postures, and download information for downloading the multimedia content is generated. The image confirmation information is used to indicate confirmation of obtaining the posture images corresponding to the M individual character postures.

15. The method according to claim 14, characterized in that, When M is greater than 1, the posture indication information is also used to indicate the order in which the M character postures are selected; The process of creating multimedia content based on the pose images corresponding to the poses of the M individuals includes: Based on the posture indication information, plot information is determined. The plot information is used to describe the plot story in which the first character participates by combining the posture images corresponding to the postures of the M characters. The multimedia content is created based on the plot information and the posture images corresponding to the postures of the M characters.

16. An information display device, characterized in that, The device includes: A shooting display module is used to display a shooting interface, which displays a real scene captured by the camera and a first person object located in the real scene; The acquisition module is used to acquire the captured image obtained by photographing the first person object; The selection display module is used to display the posture selection interface, which displays at least one character posture for selection. A pose display module is configured to, in response to the operation of selecting M character poses from the at least one character pose, display pose images corresponding to the M character poses respectively, wherein the pose images are generated based on the captured images, and in the pose image corresponding to the i-th character pose among the M character poses, the character pose presented by the first character object is the i-th character pose, where M is an integer greater than or equal to 1, and i is a positive integer less than or equal to M.

17. An information processing device, characterized in that, The device includes: The acquisition module is used to acquire posture indication information and the captured image obtained by capturing the first human object. The posture indication information is used to indicate M human postures selected from at least one human posture, where M is an integer greater than or equal to 1. The generation module is used to generate posture images corresponding to the M character postures based on the posture indication information and the captured images, wherein, in the posture image corresponding to the i-th character posture among the M character postures, the character posture presented by the first character object is the i-th character posture, and i is a positive integer less than or equal to M.

18. A computer device, characterized in that, The computer device includes a processor and a memory, the memory storing a computer program that is loaded and executed by the processor to implement the method as claimed in any one of claims 1 to 8, or to implement the method as claimed in any one of claims 9 to 15.

19. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that is loaded and executed by a processor to implement the method as claimed in any one of claims 1 to 8, or to implement the method as claimed in any one of claims 9 to 15.

20. A computer program product, characterized in that, The computer program product includes a computer program stored in a computer-readable storage medium, which a processor reads from and executes to implement the method as claimed in any one of claims 1 to 8, or to implement the method as claimed in any one of claims 9 to 15.

Images