Virtual object construction method and apparatus, electronic device, storage medium, and program product

Abstract

The present disclosure provides a virtual object construction method and device, electronic equipment, storage medium and program product, in the field of artificial intelligence, especially in the field of computer vision and large model, which can be applied to metaverse, video production and other application scenarios. The specific implementation scheme includes: in response to an object construction request, an initial image related to a target object is obtained; a large model is used to detect the initial image to obtain a detection result, the detection result representing the matching degree between the initial image and a virtual object construction condition; and a virtual object related to the target object is constructed according to the detection result.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence technology, particularly to the field of computer vision technology and large model technology, and can be applied to application scenarios such as metaverse and video production. Background Technology

[0002] Virtual objects can be computer-generated virtual entities used to simulate living beings such as humans and animals. In scenarios such as virtual reality, metaverse, game development, and film and television production, constructed virtual objects can be used to represent human or animal movements and postures, thereby enhancing the display effect of specific scenarios in virtual spaces. Summary of the Invention

[0003] This disclosure provides a method, apparatus, electronic device, storage medium, and program product for constructing virtual objects.

[0004] According to one aspect of this disclosure, a method for constructing a virtual object is provided, comprising: in response to an object construction request, acquiring an initial image related to a target object; detecting the initial image using a large model to obtain a detection result, wherein the detection result characterizes the degree of matching between the initial image and virtual object construction conditions; and constructing a virtual object related to the target object based on the detection result.

[0005] According to another aspect of this disclosure, a virtual object construction apparatus is provided, comprising: an acquisition module for acquiring an initial image related to a target object in response to an object construction request; a detection module for detecting the initial image using a large model to obtain a detection result, the detection result representing the degree of matching between the initial image and virtual object construction conditions; and a virtual object construction module for constructing a virtual object related to the target object based on the detection result.

[0006] According to another aspect of this disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to implement a method provided according to an embodiment of this disclosure.

[0007] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause the computer to perform a method provided according to an embodiment of this disclosure.

[0008] According to another aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the method provided according to embodiments of this disclosure.

[0009] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0010] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0011] Figure 1 This illustration schematically shows an exemplary system architecture to which the virtual object construction method and apparatus can be applied according to embodiments of the present disclosure;

[0012] Figure 2 A flowchart illustrating a virtual object construction method according to an embodiment of the present disclosure is shown schematically;

[0013] Figure 3 This diagram schematically illustrates an application scenario of the virtual object construction method according to embodiments of the present disclosure.

[0014] Figure 4 This diagram illustrates an application scenario of a virtual object construction method according to another embodiment of the present disclosure.

[0015] Figure 5 This diagram illustrates an application scenario of a virtual object construction method according to yet another embodiment of the present disclosure.

[0016] Figure 6 This schematically illustrates the architecture of a computer system employing a virtual object construction method according to an embodiment of the present disclosure;

[0017] Figure 7 A schematic diagram illustrating the principle of a virtual object construction method according to an embodiment of the present disclosure is shown.

[0018] Figure 8 A schematic diagram illustrating a method for constructing virtual objects according to another embodiment of the present disclosure is shown.

[0019] Figure 9 A block diagram of a virtual object construction apparatus according to embodiments of the present disclosure is schematically shown; and

[0020] Figure 10 A block diagram of an electronic device suitable for implementing a virtual object construction method according to an embodiment of the present disclosure is shown schematically. Detailed Implementation

[0021] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0022] In the technical solution disclosed herein, the acquisition, storage, and application of user personal information comply with the provisions of relevant laws and regulations, necessary confidentiality measures have been taken, and there is no violation of public order and good morals.

[0023] The inventors discovered a growing demand from users for personalized virtual avatar customization. For example, users can create 2D or 3D animated avatars based on their facial features for sharing on social media platforms or for generating content based on these virtual avatars. In film and game production, with user authorization, creating virtual avatars resembling the user's appearance can enhance product quality. However, the process of creating virtual avatars and the quality of their display still fall short of user expectations.

[0024] Embodiments of this disclosure provide a virtual object construction method, apparatus, electronic device, storage medium, and program product. The virtual object construction method includes: in response to an object construction request, acquiring an initial image related to a target object; detecting the initial image using a large model to obtain a detection result, the detection result representing the degree of matching between the initial image and virtual object construction conditions; and constructing a virtual object related to the target object based on the detection result.

[0025] According to embodiments of this disclosure, upon receiving a request to construct a target object, an initial image related to the target object is acquired, and a large model is used to detect the initial image. This allows the detection results to accurately represent the matching degree between the initial image and the virtual object construction conditions. Furthermore, the speed of obtaining the detection results can be improved based on the powerful data processing capabilities of the large model. Thus, initial images that meet the virtual object construction conditions can be accurately selected based on the more precise detection results, and virtual object construction can be performed based on the initial image to improve the matching degree between the virtual object and the target object, thereby improving the construction quality and efficiency of the virtual object.

[0026] Figure 1 The illustration schematically depicts an exemplary system architecture to which virtual object construction methods and apparatus can be applied according to embodiments of the present disclosure.

[0027] It is important to note that Figure 1The examples shown are merely examples of system architectures that can be applied to the embodiments of this disclosure, to help those skilled in the art understand the technical content of this disclosure, but do not mean that the embodiments of this disclosure cannot be used in other devices, systems, environments, or scenarios. For example, in another embodiment, an exemplary system architecture to which the virtual object construction method and apparatus can be applied may include a terminal device, but the terminal device can implement the virtual object construction method and apparatus provided by the embodiments of this disclosure without interacting with the server.

[0028] like Figure 1 As shown, the system architecture 100 according to this embodiment may include terminal devices 101, 102, and 103, a network 104, and a server 105. The network 104 serves as a medium for providing a communication link between the terminal devices 101, 102, and 103 and the server 105. The network 104 may include various connection types, such as wired and / or wireless communication links, etc.

[0029] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, and 103, such as knowledge reading applications, web browser applications, search applications, instant messaging tools, email clients, and / or social platform software, etc. (for example only).

[0030] Terminal devices 101, 102, and 103 can be various electronic devices with displays and web browsing capabilities, including but not limited to smartphones, tablets, laptops, and desktop computers.

[0031] Server 105 can be a server that provides various services, such as a backend management server that supports the content browsed by users using terminal devices 101, 102, and 103 (for example only). The backend management server can analyze and process data such as received user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal devices.

[0032] It should be noted that the virtual object construction method provided in this embodiment can generally be executed by server 105. Correspondingly, the virtual object construction apparatus provided in this embodiment can generally be located in server 105. The virtual object construction method provided in this embodiment can also be executed by a server or server cluster that is different from server 105 and capable of communicating with terminal devices 101, 102, 103 and / or server 105. Correspondingly, the virtual object construction apparatus provided in this embodiment can also be located in a server or server cluster that is different from server 105 and capable of communicating with terminal devices 101, 102, 103 and / or server 105.

[0033] Alternatively, the virtual object construction method provided in this embodiment can also be executed by terminal devices 101, 102, or 103. Correspondingly, the virtual object construction apparatus provided in this embodiment can also be disposed in terminal devices 101, 102, or 103.

[0034] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0035] Figure 2 A flowchart illustrating a virtual object construction method according to an embodiment of the present disclosure is shown schematically.

[0036] like Figure 2 As shown, the virtual object construction method includes operations S210 to S230.

[0037] In operation S210, in response to an object construction request, an initial image related to the target object is obtained.

[0038] In operation S220, the initial image is detected using a large model to obtain the detection results, which characterize the degree of matching between the initial image and the virtual object construction conditions.

[0039] In operation S230, a virtual object related to the target object is constructed based on the detection results.

[0040] According to embodiments of this disclosure, the target object may include any type of living organism, such as humans, pet dogs, pet birds, etc. Embodiments of this disclosure do not limit the specific type of the target object and can be designed based on actual needs. For ease of explanation, embodiments of this disclosure use users capable of operating smart terminal devices such as smartphones as examples of target objects, and are not intended to limit the specific type of the target object.

[0041] According to embodiments of this disclosure, the initial image associated with the target object can be an image recording any object attribute such as the target object's face or actions. The object construction request can be generated based on interactive operations of the target object, but is not limited to this; it can also be generated based on other methods. For example, the object construction request can be generated based on preset request generation information, such as time configuration information or light signal detection information.

[0042] According to embodiments of this disclosure, virtual object construction conditions may include sub-conditions related to image quality, such as image clarity and image brightness, or sub-conditions characterizing the display attributes of the target object, such as the display angle of a specified part of the target object in the image and the expression of the target object. Virtual object construction conditions can be set based on the display requirements of the virtual object to be constructed. Embodiments of this disclosure do not limit the specific types of sub-conditions included in the virtual object construction conditions.

[0043] According to embodiments of this disclosure, the large model can be a generative model built based on deep learning algorithms. The large model can have a large number of model parameters, for example, it can contain billions of model parameters. A detection task for detecting virtual object construction conditions can be generated based on sample images of recorded sample objects. This detection task can be used to fine-tune the large model to achieve its detection function and improve its accuracy in detecting virtual object construction conditions.

[0044] According to embodiments of this disclosure, the detection result can be characterized based on an identifier. For example, the identifier "1" can indicate that the initial image matches the virtual object construction conditions, and the identifier "0" can indicate that the initial image does not match the virtual object construction conditions.

[0045] According to embodiments of this disclosure, the detection result can also characterize the degree of matching between the initial image and the sub-conditions in the virtual object construction conditions. For example, the detection result can be a detection identifier "1" or "0" associated with a sub-condition, so as to determine whether the initial image meets the requirements of one or more sub-conditions based on the detection identifiers of multiple sub-conditions associated with the initial image. In this way, when there are multiple initial images, the initial images that match each of the multiple sub-conditions can be filtered out, thereby obtaining multiple initial images that meet the virtual object construction conditions.

[0046] According to embodiments of this disclosure, constructing a virtual object related to a target object based on detection results may include using the detection results to select initial images that match the virtual object construction conditions. If the selected initial images match multiple sub-conditions in the virtual object construction conditions, the initial images matching the sub-conditions can be used as target images. Virtual object construction algorithms, such as diffusion model algorithms or any other type of algorithm, are then used to process the target images to obtain virtual objects that accurately meet the virtual object construction requirements. The virtual objects may be two-dimensional or three-dimensional.

[0047] In one example, a virtual object can be obtained by processing a target image based on a finely tuned image generative model. Image generative models can be built using generative models with billions of parameters.

[0048] According to embodiments of this disclosure, if the initial image obtained from the detection results cannot match the virtual object construction conditions, the target object can be notified to upload an image that matches the virtual object construction conditions by sending a message. Alternatively, images related to the target object can be obtained through other means, and a large model can be used for detection. Based on the detection results, the target image that matches the virtual object construction conditions can be selected from all the obtained images.

[0049] According to embodiments of this disclosure, acquiring an initial image related to a target object includes the following first image acquisition operation: controlling an image acquisition device to acquire an image of the target object to obtain an initial image.

[0050] According to embodiments of this disclosure, the image acquisition device may be a camera installed in a smart terminal device such as a smartphone or tablet. The target object may perform interactive operations on the smart terminal device to generate an object construction request. The object construction request may be a request instruction instructing the processor of the smart terminal device, or it may be a request message instructing the server to execute the virtual object construction method according to embodiments of this disclosure.

[0051] According to embodiments of this disclosure, the image acquisition device of a smart terminal device can be controlled to acquire images of a target object. This avoids the need for the target object to manually select images for virtual object construction through interactive operations, thus automating image acquisition during the virtual object construction process, improving efficiency, and enhancing user experience.

[0052] In one example, the image acquisition device can be directly controlled based on the processor of the smart terminal device.

[0053] In one example, the image acquisition device can be controlled to acquire images by sending image acquisition messages from the server to the terminal device that is configured with the image acquisition device.

[0054] According to embodiments of this disclosure, controlling an image acquisition device to acquire images of a target object may include: controlling the image acquisition device to acquire multiple images of the target object during an acquisition period, wherein a display interface related to the target object displays an image representing the target object during the acquisition period.

[0055] According to embodiments of this disclosure, the acquisition period can be the time period during which the image acquisition device acquires images. The image acquisition device can achieve multiple image acquisitions by performing video image acquisition, thus obtaining multiple consecutive initial images. The large model can then detect these multiple initial images. Alternatively, the image acquisition device can also acquire multiple initial images by taking multiple shots during the acquisition period. For example, during the acquisition period, the image acquisition device can be controlled to perform multiple image acquisitions at preset time intervals (e.g., 0.2 seconds) to obtain multiple initial images.

[0056] According to embodiments of this disclosure, the display interface associated with the target object may include the display screen of a terminal device on which an image acquisition device is installed. For example, the display screen of a smartphone with a front-facing camera. However, it is not limited to this; the display interface associated with the target object may also include other display interfaces capable of displaying the image of the current target object, such as a television display screen communicatively connected to the image acquisition device.

[0057] According to embodiments of this disclosure, the display interface shows an image representing the target object during the acquisition period. This allows the target object to adjust its posture, angle, and other object image attributes in real time to match the virtual object construction conditions based on the image displayed on the display interface. This allows the target object to adjust its posture or angle more freely without interactive operations, thereby improving the efficiency of obtaining target images that meet the virtual object construction conditions and improving the overall efficiency of the virtual object construction process.

[0058] Figure 3 The diagram illustrates an application scenario of the virtual object construction method according to an embodiment of the present disclosure.

[0059] like Figure 3 As shown, this application scenario may include a smartphone 300. The smartphone 300's display interface may show a virtual "Start" button (B301), and the smartphone 300 is equipped with an image acquisition device P301. After the target object performs an interactive operation on the virtual "Start" button (B301) on the display interface, the image acquisition device P301 of the smartphone 300 can capture images of the target object during the acquisition period. During the acquisition period, the image acquisition device P301 can acquire the current image of the target object in real time, and the smartphone 300's display interface can display the image 301 corresponding to the current image of the target object in real time. Image acquisition can be achieved by controlling the image acquisition device P301 to take a photo, or by taking a screenshot of the smartphone 300's display interface.

[0060] like Figure 3As shown, during the acquisition period, the smartphone 300's display interface can show the current acquisition stage as "Step 1 Frontal Portrait" to prompt the target object to adjust its posture according to the prompt information. The smartphone 300's display interface can also display an image acquisition progress bar M301. The dark portion of the image acquisition progress bar M301 indicates the number of initial images that meet the virtual construction conditions acquired at the current moment. Upon acquiring the initial image T301 of the target object's frontal portrait, the progress bar M301 can advance a preset distance, and the "Step 2 Side Portrait" displayed on the smartphone 300's display interface will prompt the target object that the next initial image to be acquired must meet the sub-condition "facial side angle" of the virtual object construction conditions.

[0061] like Figure 3 As shown, the display interface of the smartphone 300 may also include a display frame K301, which is used to prompt the target object that its face or body should not exceed the display frame in the initial image currently captured.

[0062] According to embodiments of this disclosure, the virtual object construction method may further include: displaying an auxiliary prompt object on a display interface that matches at least one virtual object construction condition.

[0063] Figure 4 The diagram illustrates an application scenario of a virtual object construction method according to another embodiment of the present disclosure.

[0064] like Figure 4 As shown, this application scenario may include a smartphone 400. The smartphone 400's display interface may show a virtual "Start" button (B401), and the smartphone 400 is equipped with an image acquisition device P401. After the target object performs an interactive operation on the virtual "Start" button (B401) on the display interface, the image acquisition device P401 of the smartphone 400 can capture images of the target object during the acquisition period. During the acquisition period, the image acquisition device P401 can acquire the current image of the target object in real time, and the display frame K401 of the smartphone 400's display interface can display the image corresponding to the current image of the target object in real time. Image acquisition can be achieved by controlling the image acquisition device P401 to take a photo, or by taking a screenshot of the display frame K401 on the smartphone 400's display interface.

[0065] like Figure 4As shown, the sub-conditions of the virtual object construction conditions that need to be met in the current acquisition phase during the acquisition period are posture sub-conditions, such as the sub-condition "standing with arms crossed". The display interface of the smartphone 400 can display the posture of the auxiliary prompt object F401 according to the sub-condition "standing with arms crossed", so that the target object can adjust its posture according to the posture of the auxiliary prompt object F401. The display interface of the smartphone 400 can also display an image acquisition progress bar M401. The dark part of the image acquisition progress bar M401 can indicate the number of initial images that meet the virtual construction conditions at the current moment.

[0066] It should be understood that when the depth color area of ​​the image acquisition progress bar M401 fills the entire progress bar area, it can be said that all the initial images that match the virtual object construction conditions have been acquired. The initial image that matches the virtual object construction conditions is taken as the target image. The virtual object construction model can be used to process the target image to obtain the virtual object related to the target object.

[0067] According to embodiments of this disclosure, acquiring an initial image related to a target object may further include the following second image acquisition operation: acquiring an initial image from a preset storage area based on an image acquisition instruction, wherein the image acquisition instruction is determined according to an object construction request.

[0068] According to embodiments of this disclosure, an image acquisition instruction can be generated based on an object construction request, thereby automatically acquiring an initial image from a preset storage area according to the image acquisition instruction, and constructing a virtual object without the target object participating in interactive operations.

[0069] According to embodiments of this disclosure, the image acquisition instruction can also be generated based on the interactive operation of the target object. For example, the initial image can be determined based on the target object's selection operation of images in the smartphone's photo album. Then, the initial image determined based on the selection operation is encapsulated into a message and sent to a server with a large model to achieve initial image detection.

[0070] According to embodiments of this disclosure, acquiring an initial image related to a target object may further include combining a first image acquisition operation and a second image acquisition operation to obtain an initial image acquired based on each of the first and second image acquisition operations, thereby achieving multi-channel acquisition of the initial image.

[0071] It should be noted that the information obtained in any embodiment of this disclosure, including but not limited to initial images and intermediate images, is obtained with the consent and authorization of the relevant users. Before authorization, the relevant users are clearly informed that the purpose of obtaining the information is to construct the virtual objects they need. After obtaining the information, necessary confidentiality measures such as desensitization and encryption are adopted to avoid information leakage.

[0072] According to embodiments of this disclosure, detecting an initial image using a large model includes: updating a prompt template related to the target object based on the initial image to obtain prompt information; and processing the prompt information using the large model to obtain a detection result.

[0073] According to embodiments of this disclosure, the prompt template (or prompt template) can be a tag or text used to help a large model understand the conditional detection task of constructing virtual objects on an initial image. The prompt template can be based on a sequence of prompt tags used to control the large model to perform accurate detection. The prompt tag sequence can include prompt tags of any type such as characters, fields, and text.

[0074] In one example, the prompt template can be based on a paragraph enclosed by " / / ":

[0075] / / Detect whether the following image meets the sub-condition and output the detection result. The sub-condition is "side profile face".

[0076] "{picturel}", "{picture2}"...;

[0077] Please output the detection results for each of the above images, represented by the sub-condition identifier "02" and the detection identifier "Y" or "N". / /

[0078] By filling one or more initial images into the prompt template "{picture1}", "{picture2}", etc., you can get the prompt information.

[0079] It should be noted that the prompt templates in the above examples are for illustrative purposes only and are not intended to limit the specific content of the prompt templates in the embodiments of this disclosure. Those skilled in the art can design prompt templates according to actual needs.

[0080] According to embodiments of this disclosure, by using a finely tuned large model to detect the initial image, the detection results can more accurately characterize the degree of matching between the initial image and the sub-conditions in the virtual object construction conditions. It can also realize batch detection of multiple images or consecutive frames of images using a large model, thereby improving detection efficiency and the overall efficiency of virtual object construction.

[0081] According to embodiments of this disclosure, the virtual object construction conditions include at least one image attribute sub-condition. The image attribute sub-condition may characterize sub-conditions related to image attributes such as image sharpness and image brightness, or it may further include sub-conditions related to object attributes represented by the image, such as the target object's pose, position, expression, and occluded area. Those skilled in the art can set these conditions based on the actual needs of constructing the virtual object.

[0082] According to embodiments of this disclosure, constructing a virtual object related to a target object based on detection results may include: determining defect attribute sub-conditions from image attribute sub-conditions based on defect detection results in the detection results, wherein the defect attribute sub-conditions characterize the defect type of at least one initial image; obtaining a target image that matches the defect attribute sub-conditions; and constructing a virtual object based on the target image.

[0083] According to embodiments of this disclosure, defect detection results can indicate whether an initial image detected by a large model matches an image attribute sub-condition. Based on the defect detection results of multiple initial images, it can be determined whether an initial image matching each image attribute sub-condition has been obtained. If at least one image attribute sub-condition does not have a matching initial image, that image attribute sub-condition can be identified as a defective attribute sub-condition. A defective attribute sub-condition can characterize one or more currently acquired initial images that cannot match a defective attribute sub-condition.

[0084] According to embodiments of this disclosure, the current defect attribute sub-conditions can be determined more accurately and quickly based on the detection results of the large model. This can more precisely indicate the defect type of the currently acquired initial image used to construct the virtual object. Furthermore, the target image can be more accurately obtained based on the image attributes indicated by the defect attribute sub-conditions, thereby reducing the time required to construct the virtual object.

[0085] According to embodiments of this disclosure, the virtual object construction conditions may further include other types of sub-conditions, such as image quantity sub-conditions and object type sub-conditions. The object type sub-condition may indicate whether the type of the target object contained in the initial image meets the construction requirements of the virtual object. The type of the target object may include an identity type. Based on the object type sub-condition related to the identity type, it can be detected whether multiple initial images record the identity of the target object and whether it is consistent with the identity of the target object authorized for image acquisition, thereby preventing the constructed virtual object from containing image information of target objects with multiple identities and avoiding leakage of identity information and image feature information. Furthermore, based on the current detection results for the initial image, defect attribute sub-conditions can be determined from the multiple types of sub-conditions in the virtual object construction conditions to improve the accuracy of acquiring the target image.

[0086] According to embodiments of this disclosure, obtaining a target image that matches a defect attribute sub-condition may include: obtaining an intermediate image related to a target object; using a large model to detect the intermediate image to obtain an intermediate detection result; and determining the intermediate image as the target image if the intermediate detection result indicates that the intermediate image matches the defect attribute sub-condition.

[0087] According to embodiments of this disclosure, the intermediate image may include an image related to the target object acquired after determining the defect attribute sub-condition. The intermediate image may be acquired based on at least one of the first image acquisition operation and the second image acquisition operation described in embodiments of this disclosure.

[0088] According to embodiments of this disclosure, detecting intermediate images using a large model can include determining a preset prompt template that matches the defect attribute sub-conditions, updating the prompt template using the intermediate image, so that the obtained prompt information can more accurately understand the defect type corresponding to the defect attribute sub-conditions to be detected in the detection task, improve the detection accuracy and efficiency of intermediate images, and thus improve the efficiency of virtual object construction.

[0089] According to embodiments of this disclosure, obtaining an intermediate image related to a target object may include: controlling an image acquisition device to acquire an image of the target object during an intermediate acquisition period to obtain an intermediate image, wherein a display interface related to the target object displays an auxiliary prompt object that matches the defect attribute sub-condition during the intermediate acquisition period.

[0090] According to embodiments of this disclosure, an image acquisition control and an auxiliary prompt control can be invoked based on determined defect attribute sub-conditions. The image acquisition control can control the image acquisition device to activate its image acquisition function. For example, the image acquisition control can control the front-facing camera of a smartphone to acquire a real-time image of the target object and display it on the smartphone's display interface. The image acquisition control can also periodically acquire images of the target object according to a preset acquisition time interval. The auxiliary prompt control can invoke an auxiliary prompt object that matches the defect attribute sub-condition and display the auxiliary prompt object on the display interface. During the periodic acquisition process by the image acquisition device according to the preset acquisition time interval, the target object can imitate the posture, actions, expressions, etc., of the auxiliary prompt object to enable the image acquisition device to acquire intermediate images that match the defect attribute sub-conditions more quickly.

[0091] It should be noted that the posture of the target object involved in the embodiments of this disclosure may include the target object's body movement posture, such as standing, half-squatting, etc., and may also include facial posture, such as looking up, looking down, turning the head to the left, etc.

[0092] According to embodiments of this disclosure, the defect attribute sub-conditions may include multiple sub-conditions. For example, defect attribute sub-conditions that indicate the image required for constructing a virtual object may include: the pose attribute sub-condition "side profile portrait" and the size attribute sub-condition "30mm*40mm". Based on these multiple defect attribute sub-conditions, corresponding auxiliary prompt controls and image preprocessing controls can be invoked to detect intermediate images acquired during intermediate acquisition periods. If the detected intermediate image matches "side profile portrait", the intermediate image is cropped to obtain the target image that satisfies multiple defect attribute sub-conditions. This allows for the rapid and accurate acquisition of the target image for constructing the virtual object through large model detection and control invocation.

[0093] Figure 5 The illustration shows an application scenario diagram of a virtual object construction method according to yet another embodiment of the present disclosure.

[0094] like Figure 5 As shown, this application scenario may include a smartphone 500. The smartphone 500 is equipped with an image acquisition device P501. After the large model detects the initial image sent by the smartphone 500, it can determine the defect attribute sub-condition as "side profile portrait" based on the defect detection results. Based on the defect attribute sub-condition "side profile portrait," an image acquisition control can be invoked to control the image acquisition device P501, causing P501 to map the image of the target object onto the display interface of the smartphone 500 in real time, thus displaying the mapped image of the target object in real time. The image acquisition control can also control the smartphone 500 to take screenshots of the mapped image displayed in real time at preset intermediate acquisition intervals, obtaining intermediate images acquired during the intermediate acquisition period. Based on the defect attribute sub-condition "side profile portrait," an auxiliary prompt object F501 matching "side profile portrait" can also be invoked and displayed on the display interface, allowing the target object to adjust its actions or posture in the mapped image on the display interface by imitating the actions of the auxiliary prompt object F501. When the mapped image 501 displayed on the screen has a similar appearance to the auxiliary prompt object F501, the image acquisition control can obtain the mapped image 501 and perform image preprocessing operations such as cropping and scaling to obtain the intermediate image T501. This allows for the rapid acquisition of an intermediate image that matches the defect attribute sub-conditions by combining detection using a large language model with the invocation of image attribute adjustment controls.

[0095] According to embodiments of this disclosure, for complex situations where virtual object construction conditions include multiple sub-condition combinations, and each sub-condition combination includes multiple types of sub-conditions, the method provided by embodiments of this disclosure can detect the initial image using a large model to determine multiple defect attribute sub-conditions in the sub-condition combination. Then, by calling the controls corresponding to each of the multiple defect attribute sub-conditions in the sub-condition combination, the process of acquiring, detecting, and preprocessing intermediate images can be realized. This allows the batch-acquired intermediate images to be precisely processed by calling the controls, generating target images that satisfy multiple defect attribute sub-conditions. This improves the accuracy and quality of the acquired target images, achieving adaptation between the target images and the virtual object construction requirements, thereby improving the construction accuracy and efficiency of virtual objects under complex conditions.

[0096] According to embodiments of this disclosure, obtaining an intermediate image related to a target object may further include: obtaining the intermediate image from a preset storage area related to the target object.

[0097] According to embodiments of this disclosure, the preset storage area includes at least one of a first type of storage area and a second type of storage area.

[0098] According to embodiments of this disclosure, the first type of storage area can be represented as a device storage area in the terminal device that sends the object construction request. For example, the album storage area corresponding to the authorized album in the target object's smartphone.

[0099] According to embodiments of this disclosure, the second type of storage area can represent a cloud storage area associated with the target object. For example, within the target object's cloud storage space, there is a photo album cloud storage area specified by the target object.

[0100] According to embodiments of this disclosure, a permission authentication control and an image acquisition control can be invoked based on defect attribute sub-conditions. The permission authentication control authenticates the target object's permission to acquire images. After successful authentication, the image acquisition control acquires an intermediate image from a preset storage area specified by the target object. A large model is then used to detect the automatically acquired intermediate image. This allows for precise selection of target images matching the defect attribute sub-conditions, even when the target object cannot adjust its posture or actions according to the defect attribute sub-conditions. This avoids prolonged image acquisition of the target object, which reduces the efficiency of virtual object construction. Furthermore, the target object can be pre-captured and stored in a preset storage area to construct virtual objects based on its appearance at a specified time (e.g., middle school or university). This allows the constructed virtual objects to meet the personalized needs of the target object, improving the flexibility and adaptability of virtual object construction.

[0101] Figure 6 The diagram illustrates the architecture of a computer system employing a virtual object construction method according to an embodiment of the present disclosure.

[0102] like Figure 6 As shown, the computer system 600 can be used to execute the virtual object construction method provided in the embodiments of this disclosure. The computer system 600 may include a basic library layer, a persistence layer, a business layer, and an interaction layer. The basic library layer can be used to provide system-level services, such as providing low-level code service resources for obtaining an initial image. The persistence layer can be used to manage the executable file for performing virtual object construction.

[0103] The business layer can include an out-of-frame detection module, an image acquisition module, an image filtering module, and an acquisition service module. The out-of-frame detection module can cache the acquired initial or intermediate images and adjust their sizes to standardize them. It can also detect image regions related to the target object in the initial and intermediate images to determine whether a specified part of the target object (e.g., the face) exceeds the image's display frame. The image acquisition module can acquire images of the target object displayed in real-time on the interface. The image filtering module can add filters to the initial or intermediate images based on the target object's configuration requirements or the virtual object's construction requirements to improve the image display effect. The acquisition service module can control the image acquisition device to perform image acquisition at preset intervals. It can also interact with large models located locally or in the cloud, sending initial and intermediate images to devices or equipment deploying large models and receiving detection results, constructed virtual images, etc. The interaction layer can be used to render UI (User Interface) components displayed on the terminal device, such as rendering progress bars, auxiliary display objects, etc.

[0104] Figure 7 A schematic diagram illustrating a method for constructing virtual objects according to an embodiment of the present disclosure is shown.

[0105] like Figure 7 As shown, the virtual object construction method can be executed based on the image acquisition component 701, the task management component 702, the bounding box detection component 703, and the image data extraction component 704.

[0106] The image acquisition component 701 can execute step S701 to acquire an initial image and transmit the initial image to the task management component 702.

[0107] Task management component 702 can execute step S702, sending an out-of-bounds detection command. After receiving the out-of-bounds detection command, out-of-bounds detection component 703 can perform out-of-bounds detection on the initial image.

[0108] The out-of-box detection component 703 performs operation S703, sending a face image to the image data extraction component 704, which may contain the facial features of the target object.

[0109] The image data extraction component 704 extracts face-related image data from the face image and performs operation S704 to send the face-related image data to the bounding box detection component 703.

[0110] The out-of-frame detection component 703 can perform operation S705 to detect the number of faces. It can detect the number of faces in face-related image data based on the face-related image data. If the number of faces is greater than 1 or equal to zero, the initial image can be determined as an unqualified image that is not detected.

[0111] The bounding box detection component 703 can also perform operation S706 to perform size conversion on the face-related image data. For example, it can convert the data according to a preset rectangular bounding box size to calculate the area and position of the face region in the face-related image data. Then, it performs operation S707 to determine whether the target object's face is outside the bounding box based on the area and position of the face region. If the result of operation S707 is that there is no bounding box, the bounding box detection component 703 performs operation S708 to return the bounding box detection result to the task management component 702.

[0112] Task management component 702 executes operation S709, sending facial image-related data to image acquisition component 701. Facial image data where the face does not go outside the bounding box can be stored in the buffer of image acquisition component 701. This facilitates the transfer of cached facial image data to a large model for detection.

[0113] Figure 8 A schematic diagram illustrating a method for constructing virtual objects according to another embodiment of this disclosure is shown.

[0114] like Figure 8 As shown, the virtual object construction method can be executed based on the image acquisition component 701, the task management component 702, the bounding box detection component 703, and the image data extraction component 704.

[0115] The image acquisition component 801 can perform operation S801, send an initial image acquisition request, and construct a generation task to generate virtual objects.

[0116] The interactive rendering component 802 can perform operation S802, requesting bounding box detection. For example, based on the image acquisition request sent by the image acquisition component 801, it can take a screenshot of the image displayed on the target object in the interactive interface to obtain an initial image. Then, it generates a bounding box detection request based on the acquired initial image. By sending the bounding box detection request to the task management component, it requests the task management component 803 to execute the bounding box detection task.

[0117] The task management component 803 can perform operation S803 to send the face image in the initial image to the image data extraction component 804 according to the virtual object generation task.

[0118] The image data extraction component 804 extracts facial data from the initial image containing facial features, extracting facial-related image data. Then, it executes operation S804, sending the facial-related image data to the task management component 803.

[0119] Task management component 803 can perform operation S805, requesting a refresh of interactive elements so that interactive rendering component 802 can refresh the image related to the target object displayed on the interactive interface, or it can refresh the detection results in the interactive interface. Task management component 803 can also perform operation S806, detecting whether the face is abnormal. This involves detecting whether the face of the target object in the face-related data is abnormal. For example, detecting whether there are multiple faces in the face-related data, or whether the face is outside the frame, etc.

[0120] If the detection result of operation S806 is normal, the task management component 803 can execute operation S807 to transmit facial-related data to the large model server 805. The large model server 805 can deploy the fine-tuned large model, which can process the facial-related data to detect the initial image and execute operation S808 to return the detection result to the task management component 803.

[0121] The task management component 803 can perform operation S809 based on the detection results to determine the defect type of the currently acquired initial image. Based on the defect type, it determines the relevant data of the corresponding auxiliary prompt object. Then, it performs operation S810 to send auxiliary prompts to the interactive rendering component 802. By transmitting the relevant data of the auxiliary prompt object to the interactive rendering component 802, the auxiliary prompt object corresponding to the defect type (defect attribute sub-condition) can be rendered on the display interface, allowing the target object to adjust its posture according to the auxiliary prompt object.

[0122] Figure 9 A block diagram of a virtual object construction apparatus according to an embodiment of the present disclosure is shown schematically.

[0123] like Figure 9As shown, the virtual object construction device 900 may include: an acquisition module 910, a detection module 920, and a virtual object construction module 930.

[0124] The acquisition module 910 is used to acquire an initial image related to the target object in response to an object construction request.

[0125] The detection module 920 is used to detect the initial image using a large model and obtain the detection results, which characterize the degree of matching between the initial image and the virtual object construction conditions.

[0126] Virtual object construction module 930 is used to construct virtual objects related to the target object based on the detection results.

[0127] According to embodiments of this disclosure, the virtual object construction conditions include at least one image attribute sub-condition.

[0128] According to embodiments of this disclosure, the virtual object construction module includes: a first determination submodule, a target image acquisition submodule, and a construction submodule.

[0129] The first determining submodule is used to determine the defect attribute subcondition from the image attribute subcondition based on the defect detection result in the detection result. The defect attribute subcondition represents the defect type of at least one initial image.

[0130] The target image acquisition submodule is used to acquire target images that match the defect attribute subconditions.

[0131] The construction submodule is used to build virtual objects based on the target image.

[0132] According to embodiments of this disclosure, the target image acquisition submodule includes: an intermediate image acquisition unit, a detection unit, and a target image determination unit.

[0133] The intermediate image acquisition unit is used to acquire intermediate images related to the target object.

[0134] The detection unit is used to perform detection on the intermediate image using a large model to obtain intermediate detection results.

[0135] The target image determination unit is used to determine the intermediate image as the target image when the intermediate detection result characterizes the intermediate image and the defect attribute sub-condition.

[0136] According to embodiments of this disclosure, the intermediate image acquisition unit includes an acquisition subunit.

[0137] The acquisition subunit is used to control the image acquisition device to acquire images of the target object during the intermediate acquisition period to obtain intermediate images. During the intermediate acquisition period, the display interface related to the target object displays auxiliary prompts that match the defect attribute sub-conditions.

[0138] According to embodiments of this disclosure, the intermediate image acquisition unit includes an acquisition subunit.

[0139] The acquisition subunit is used to acquire an intermediate image from a preset storage area associated with the target object; the preset storage area includes at least one of the following: a device storage area in the terminal device that sent the object construction request; or a cloud storage area associated with the target object.

[0140] According to embodiments of this disclosure, acquiring an initial image related to a target object includes at least one of the following image acquisition operations: controlling an image acquisition device to acquire an image of the target object to obtain an initial image; and acquiring the initial image from a preset storage area based on an image acquisition instruction, wherein the image acquisition instruction is determined according to an object construction request.

[0141] According to embodiments of this disclosure, controlling an image acquisition device to acquire images of a target object includes: controlling the image acquisition device to acquire multiple images of the target object during an acquisition period, wherein a display interface related to the target object displays an image representing the target object during the acquisition period.

[0142] According to embodiments of this disclosure, the virtual object construction apparatus further includes a display module.

[0143] The display module is used to display auxiliary prompt objects on the display interface that match the construction conditions of at least one virtual object.

[0144] According to embodiments of this disclosure, the detection module includes an update submodule and a detection submodule.

[0145] The update submodule is used to update the prompt template related to the target object based on the initial image to obtain prompt information.

[0146] The detection submodule is used to process the prompt information using the large model to obtain the detection result.

[0147] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0148] According to an embodiment of the present disclosure, an electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform a method provided according to an embodiment of the present disclosure.

[0149] According to embodiments of the present disclosure, a non-transitory computer-readable storage medium stores computer instructions, wherein the computer instructions are used to cause a computer to perform a method provided according to embodiments of the present disclosure.

[0150] According to an embodiment of the present disclosure, a computer program product includes a computer program that, when executed by a processor, implements the method provided according to an embodiment of the present disclosure.

[0151] Figure 10 A block diagram schematically illustrates an electronic device suitable for implementing a virtual object construction method according to embodiments of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0152] like Figure 10 As shown, device 1000 includes a computing unit 1001, which can perform various appropriate actions and processes according to a computer program stored in read-only memory (ROM) 1002 or a computer program loaded from storage unit 1008 into random access memory (RAM) 1003. The RAM 1003 may also store various programs and data required for the operation of device 1000. The computing unit 1001, ROM 1002, and RAM 1003 are interconnected via bus 1004. Input / output (I / O) interface 1005 is also connected to bus 1004.

[0153] Multiple components in device 1000 are connected to I / O interface 1005, including: input unit 1006, such as keyboard, mouse, etc.; output unit 1007, such as various types of monitors, speakers, etc.; storage unit 1008, such as disk, optical disk, etc.; and communication unit 1009, such as network card, modem, wireless transceiver, etc. Communication unit 1009 allows device 1000 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0154] The computing unit 1001 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 1001 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1001 performs the various methods and processes described above, such as the virtual object construction method. For example, in some embodiments, the virtual object construction method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 1008. In some embodiments, part or all of the computer program may be loaded and / or installed on device 1000 via ROM 1002 and / or communication unit 1009. When the computer program is loaded into RAM 1003 and executed by the computing unit 1001, one or more steps of the virtual object construction method described above may be performed. Alternatively, in other embodiments, computing unit 1001 may be configured to perform a virtual object construction method by any other suitable means (e.g., by means of firmware).

[0155] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0156] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0157] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0158] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0159] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0160] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, distributed system servers, or servers incorporating blockchain technology.

[0161] It should be understood that the various forms of processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0162] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A virtual object construction method, comprising: obtaining initial images related to a target object in response to an object construction request; detecting the initial images by using a large model to obtain detection results, the detection results representing matching degrees between the initial images and virtual object construction conditions; determining a defect attribute sub-condition from image attribute sub-conditions according to a defect detection result in the detection results, the defect attribute sub-condition representing a defect type of at least one of the initial images, the virtual object construction conditions including the image attribute sub-conditions; constructing the virtual object according to a target image matching the defect attribute sub-condition.

2. The method of claim 1, wherein, The target image is determined based on the following operations: obtaining intermediate images related to the target object; detecting the intermediate images by using the large model to obtain intermediate detection results; and in a case where the intermediate detection results represent that the intermediate images match the defect attribute sub-condition, determining the intermediate images as the target image.

3. The method of claim 2, wherein, The obtaining of the intermediate images related to the target object comprises: controlling an image acquisition device to acquire images of the target object in an intermediate acquisition period to obtain the intermediate images, wherein a display interface related to the target object displays an auxiliary prompt object matching the defect attribute sub-condition in the intermediate acquisition period.

4. The method of claim 2, wherein, The obtaining of the intermediate images related to the target object comprises: obtaining the intermediate images from a preset storage area related to the target object; The preset storage area includes at least one of the following: a device storage area in a terminal device sending the object construction request; a cloud storage area related to the target object.

5. The method of claim 1, wherein, The obtaining of the initial images related to the target object comprises at least one of the following image acquisition operations: controlling an image acquisition device to acquire images of the target object to obtain the initial images; and obtaining the initial images from a preset storage area based on an image acquisition instruction, the image acquisition instruction being determined according to the object construction request. The controlling of the image acquisition device to acquire images of the target object comprises:

6. The method of claim 5, wherein, controlling the image acquisition device to acquire images of the target object multiple times in an acquisition period, wherein a display interface related to the target object displays images representing the target object in the acquisition period.

7. The method of claim 6, further comprising: displaying an auxiliary prompt object matching at least one of the virtual object construction conditions on the display interface. The detecting of the initial images by using a large model comprises:

8. The method of claim 1, wherein, updating a prompt template related to the target object according to the initial images to obtain prompt information; and processing the prompt information by using the large model to obtain the detection results.

9. A virtual object construction apparatus, comprising: an obtaining module configured to obtain initial images related to a target object in response to an object construction request; a detection module configured to detect the initial images by using a large model to obtain detection results, the detection results representing matching degrees between the initial images and virtual object construction conditions; and ​ a virtual object construction module configured to construct a virtual object related to the target object according to the detection result; wherein the virtual object construction module is configured to: determine a defect attribute sub-condition from the image attribute sub-condition according to a defect detection result in the detection result, the defect attribute sub-condition representing a defect type of at least one of the initial images, and the virtual object construction condition comprising the image attribute sub-condition; construct the virtual object according to a target image matching the defect attribute sub-condition.

10. The apparatus of claim 9, wherein, The virtual object construction module comprises: an intermediate image acquisition unit configured to acquire an intermediate image related to the target object; a detection unit configured to detect the intermediate image by using the large model to obtain an intermediate detection result; and a target image determination unit configured to determine the intermediate image as the target image in a case where the intermediate detection result represents that the intermediate image matches the defect attribute sub-condition.

11. The apparatus of claim 10, wherein, The intermediate image acquisition unit comprises: an acquisition sub-unit configured to control an image acquisition device to acquire an image of the target object in an intermediate acquisition period to obtain the intermediate image, wherein a display interface related to the target object displays an auxiliary prompt object matching the defect attribute sub-condition in the intermediate acquisition period.

12. The apparatus of claim 10, wherein, The intermediate image acquisition unit comprises: an acquisition sub-unit configured to acquire the intermediate image from a preset storage area related to the target object; The preset storage area comprises at least one of the following: a device storage area in a terminal device sending the object construction request; a cloud storage area related to the target object.

13. The apparatus of claim 9, wherein, The initial image acquisition operation related to the target object comprises at least one of the following: controlling an image acquisition device to acquire an image of the target object to obtain the initial image; and acquiring the initial image from a preset storage area based on an image acquisition instruction, the image acquisition instruction being determined according to the object construction request. The controlling an image acquisition device to acquire an image of the target object comprises:

14. The apparatus of claim 13, wherein, controlling the image acquisition device to acquire an image of the target object multiple times in an acquisition period, wherein a display interface related to the target object displays an image representing the target object in the acquisition period.

15. The apparatus of claim 14, further comprising: a display module configured to display an auxiliary prompt object matching at least one of the virtual object construction conditions on the display interface.

16. An electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1 to 8. The computer instructions are used to enable the computer to perform the method of any one of claims 1 to 8.

17. A non-transitory computer readable storage medium having stored thereon computer instructions, wherein, ​ 18. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 8.

Images