Method, apparatus, device, and program for creating a 3D navigation vehicle logo

The method of 3D reconstruction and customization of navigation vehicle logos addresses the inefficiencies in existing 3D skeleton logo creation, reducing costs and time while enhancing user engagement and logo variety.

JP2026538987APending Publication Date: 2026-11-19TENCENT TECHNOLOGY (SHENZHEN) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
JP2026522568
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Priority Date
2023-11-10
Filing Date
2024-08-16
Publication Date
2026-11-19

AI Technical Summary

Technical Problem

The creation of 3D skeleton vehicle logos in navigation applications is lengthy and costly, requiring multiple parties and high development costs.

Method used

A method and apparatus for creating 3D navigation vehicle logos through 3D reconstruction of source images from different angles, allowing for user customization and display on navigation interfaces, including modules for image acquisition, reconstruction, and adjustment.

Benefits of technology

This approach reduces production costs and time, enables user customization, and enriches the variety of available 3D navigation vehicle logos, while improving efficiency and convenience in generating and displaying these logos.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2026538987000001_ABST
    Figure 2026538987000001_ABST
Patent Text Reader

Abstract

This invention discloses a method, apparatus, device, and storage medium for creating a 3D navigation vehicle logo, belonging to the field of map navigation. This method is applicable to scenarios such as cloud technology, smart transportation, and driver assistance. The method includes the steps of: displaying a source image of a first object on an image acquisition interface in response to an image acquisition operation, wherein the source image includes images obtained by photographing the first object from different shooting angles, and the first object is a 3D entity object in a real environment; displaying a 3D navigation vehicle logo of the first object, wherein the 3D navigation vehicle logo is obtained by performing a 3D reconstruction of the first object based on the source image; and displaying an adjusted 3D navigation vehicle logo in response to an operation to adjust the display form of the 3D navigation vehicle logo, wherein the adjusted 3D navigation vehicle logo is displayed on the navigation interface. In this manner, the invention supports users in providing custom objects to generate 3D navigation vehicle logos of custom objects, enriching the types of 3D navigation vehicle logos and reducing the production cost of 3D navigation vehicle logos.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] [Cross-Reference to Related Applications] This application claims the priority of the Chinese patent application filed with the China National Intellectual Property Administration on November 10, 2023, with the application number 2023115027754 and the application title "Method, Apparatus, Device and Storage Medium for Creating Three-Dimensional Navigation Vehicle Logo", the entire content of which is incorporated into this application by reference.

[0002] [Technical Field] This application relates to the technical field of map navigation, and in particular, relates to the creation of three-dimensional navigation vehicle logos.

Background Art

[0003] With the advent and development of navigation application programs, people's travel has become more convenient. When using a navigation application program, it is necessary to display a positioning point on the navigation interface to determine the position where the user is located on the navigation interface.

[0004] In the related art, in order to improve the identification capability of positioning points, a 3D skeleton vehicle logo is provided to the user in the navigation application program, and the 3D skeleton vehicle logo is displayed on the navigation interface as a positioning point. In the production process of the 3D skeleton vehicle logo, workers produce the dynamic 3D skeleton vehicle logo using 3D model production software. After the 3D skeleton vehicle logo is created, the 3D skeleton vehicle logo is released to the navigation application program to allow the user to use it.

[0005] However, in the related art, the creation period of the 3D skeleton vehicle logo is long, it is necessary to contact multiple related parties in the production process of the 3D skeleton vehicle logo, and the development cost of the 3D skeleton vehicle logo is high.

Summary of the Invention

[0006] This application provides a method, apparatus, device, storage medium, and program product for creating a 3D navigation vehicle logo. The proposed technology is as follows: [Means for solving the problem]

[0007] According to one embodiment of the present application, a method for creating a 3D navigation vehicle logo is provided, the method is: Steps include: displaying a source image of a first object on an image acquisition interface in response to an image acquisition operation, wherein the source image includes images obtained by photographing the first object from different shooting angles, and the first object is a three-dimensional entity object in a real environment; A step of displaying a 3D navigation vehicle logo for the first object, wherein the 3D navigation vehicle logo is obtained by performing a 3D reconstruction of the first object based on the source image, The method includes a step of displaying an adjusted 3D navigation vehicle logo in response to an adjustment operation of the display form of the 3D navigation vehicle logo, wherein the adjusted 3D navigation vehicle logo is used for display on a navigation interface.

[0008] According to one embodiment of the present application, a method for creating a 3D navigation vehicle logo is provided, the method is: A step of obtaining a source image relating to a first object, wherein the source image includes images obtained by photographing the first object from different angles, and the first object is a three-dimensional entity object in a real environment. A step of recognizing keypoints in the source image and determining point cloud data of the first object, wherein the point cloud data describes the position and display form of the keypoints of the first object in the actual environment. A step of performing a three-dimensional reconstruction based on the point cloud data to determine the original surface texture of the first object, wherein the original surface texture reflects the surface material of the first object. The method includes the step of mapping a texture onto point cloud data based on the surface texture of the first object to create a three-dimensional navigation vehicle logo for the first object, wherein the three-dimensional navigation vehicle logo is used for display in a navigation interface.

[0009] According to one embodiment of the present application, a three-dimensional navigation vehicle logo creation apparatus is provided, the apparatus being a source acquisition module that, in response to an image acquisition operation, displays a source image of a first object on an image acquisition interface, wherein the source image includes images obtained by photographing the first object from different shooting angles, and the first object is a three-dimensional entity object in a real environment. A vehicle logo display module that displays a three-dimensional navigation vehicle logo for the first object, wherein the three-dimensional navigation vehicle logo is obtained by performing a three-dimensional reconstruction of the first object based on the source image, A vehicle logo adjustment module that displays an adjusted 3D navigation vehicle logo in response to an adjustment operation of the display form of the 3D navigation vehicle logo, the vehicle logo adjustment module being used to display the adjusted 3D navigation vehicle logo on a navigation interface.

[0010] According to one embodiment of the present application, a three-dimensional navigation vehicle logo creation apparatus is provided, the apparatus comprising a source acquisition module that acquires a source image relating to a first object, the source image including images obtained by photographing the first object from different angles, the first object being a three-dimensional entity object in a real environment, A data determination module that recognizes keypoints in the source image and determines point cloud data of the first object, wherein the point cloud data describes the position and display form of the keypoints of the first object in the actual environment. A three-dimensional reconstruction module that performs three-dimensional reconstruction based on the point cloud data to determine the original surface texture of the first object, wherein the original surface texture reflects the surface material of the first object. A vehicle logo creation module that maps a texture to point cloud data based on the surface texture of the first object to create a three-dimensional navigation vehicle logo for the first object, wherein the three-dimensional navigation vehicle logo is used to be displayed on a navigation interface.

[0011] According to one embodiment of the present application, a computer device is provided, the computer device including a processor and memory, a computer program stored in the memory, and the computer program being read and executed by the processor, thereby realizing the method for creating the 3D navigation vehicle logo described above.

[0012] According to one embodiment of the present application, a computer-readable storage medium is provided, in which a computer program is stored, and the computer program is read and executed by a processor, thereby realizing the method for creating the 3D navigation vehicle logo described above.

[0013] According to one embodiment of the present application, a computer program product is provided, the computer program product includes a computer program, the computer program is stored in a computer-readable storage medium, and a processor reads the computer program from the computer-readable storage medium and executes it, thereby realizing the method for creating the three-dimensional navigation vehicle logo described above. [Effects of the Invention]

[0014] The beneficial effects of the invention provided by the embodiments of this application include at least the following: In addition to generating 3D skeleton vehicle logos using related technologies, this system generates and displays 3D navigation vehicle logos of subjects by performing 3D reconstruction on source images of subjects uploaded by the user. Users can freely customize the 3D navigation vehicle logos displayed in the navigation interface, fulfilling user customization requests for 3D navigation vehicle logos and enriching the types of 3D navigation vehicle logos available.

[0015] Furthermore, by automatically generating static 3D navigation vehicle logos, the production cost of 3D navigation vehicle logos can be reduced, the generation period for 3D navigation vehicle logos can be shortened, 3D navigation vehicle logos can be obtained more conveniently and quickly, and the need for iterative updates of 3D navigation vehicle logos can be met. [Brief explanation of the drawing]

[0016] [Figure 1] This is a schematic diagram of an implementation environment for the solution provided in one exemplary embodiment of this application. [Figure 2] This is a schematic diagram of the conceptual invention of the embodiment of this application. [Figure 3] This is a flowchart of a method for creating a 3D navigation vehicle logo, provided as one exemplary embodiment of this application. [Figure 4]This is a schematic diagram of first prompt information provided by one exemplary embodiment of the present application. [Figure 5] This is a schematic diagram of source image upload provided by one exemplary embodiment of the present application. [Figure 6] This is a schematic diagram of second prompt information provided by one exemplary embodiment of the present application. [Figure 7] This is a schematic diagram of identifier information acquisition provided by one exemplary embodiment of the present application. [Figure 8] This is a schematic diagram of an orientation adjustment process provided by one exemplary embodiment of the present application. [Figure 9] This is a schematic diagram before entering an image collection interface provided by one exemplary embodiment of the present application. [Figure 10] This is a schematic diagram of a navigation interface provided by one exemplary embodiment of the present application. [Figure 11] This is a schematic diagram of the display effect of a 3D navigation vehicle logo provided by one exemplary embodiment of the present application. [Figure 12] This is an interaction diagram of a vehicle logo application process provided by one exemplary embodiment of the present application. [Figure 13] This is a flowchart of a method for generating a 3D navigation vehicle logo provided by another exemplary embodiment of the present application. [Figure 14] This is a block diagram of an apparatus for generating a 3D navigation vehicle logo provided by one exemplary embodiment of the present application. [Figure 15] This is a block diagram of an apparatus for generating a 3D navigation vehicle logo provided by another exemplary embodiment of the present application. [Figure 16] This is a structural block diagram of a computer device provided by one exemplary embodiment of the present application. DETAILED DESCRIPTION

[0017] To make the purpose, technical proposal, and advantages of this application clearer, embodiments of this application will be described in more detail below with reference to the drawings.

[0018] Running Scenario: This is the scenario that a user enters after starting the navigation process using a navigation application program. In other words, the running scenario is the application scenario from the time the navigation application program starts navigating to the user until the navigation is completed.

[0019] A 3D (Three-Dimensional) model refers to the representation of an object in a way that corresponds to a 3D polygon. 3D models of objects are used to reconstruct, to some extent, the object's appearance in a real-world environment. Here, "object" may correspond to the object in the claim. The object may be a real-world object or a virtual one. Generally, 3D models are generated using 3D modeling tools.

[0020] 3D (Three Dimensional) Navigation Vehicle Logo: Used to display the user's location on the navigation interface. After the user sets the start and end points in the navigation application program and starts navigation, positioning points are displayed on the navigation interface, and these positioning points indicate the user's location on the map. To make the positioning points more engaging and improve the interest of the navigation interface, a 3D navigation vehicle logo can be displayed on the navigation interface instead of the positioning points. The 3D navigation vehicle logo belongs to the 3D model.

[0021] OBJ (Object) file: A standard 3D model file format used for converting models between 3D software models. For example, after creating a 3D model in a 3D modeling tool such as 3ds Max or LightWave, an OBJ file of that 3D model is exported, and that 3D model is imported into Maya using the OBJ file to render or generate model animations.

[0022] Figure 1 is a schematic diagram of an implementation environment for a solution provided by one exemplary embodiment of this application. The implementation environment for the solution includes terminal equipment 10, a server 20, and computer equipment 30.

[0023] The terminal device 10 may be an electronic device such as a computer, tablet, smartphone, wearable device, smart home appliance, in-vehicle terminal, or drone. The client of the target application program is running on the terminal device 10. The target application program may be an independent application program or a child application program of a parent application program, and the target application program provides a function for creating a 3D vehicle logo.

[0024] For example, the target application program is a 3D model creation application program, and after the user creates a 3D navigation vehicle logo in the target application program, the 3D navigation vehicle logo is imported into the navigation application program. When the navigation application program provides navigation to the user, the 3D navigation vehicle logo is displayed. For example, the target application program is a navigation application program, and the target application program provides a function for creating a 3D navigation vehicle logo.

[0025] Optionally, the terminal device 10 may be equipped with a camera, or there may be an image transmission path between the terminal device 10 and the camera. The terminal device 10 acquires a source image of the subject via the camera, transmits the source image to the server, and initiates the process of creating a 3D navigation vehicle logo, thereby obtaining the 3D navigation vehicle logo.

[0026] Server 20 provides background services to clients of target application programs on terminal devices 10. For example, Server 20 may be an independent physical server, a server cluster consisting of multiple physical servers, or a distributed system, or it may be a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), big data, and artificial intelligence platforms, but is not limited to these. Server 20 is equipped with at least a data receiving function.

[0027] Computer equipment 30 includes, but is not limited to, electronic devices such as smartphones, desktop computers, tablets, laptop computers, in-vehicle terminals, servers, intelligent robots, smart TVs, media players, or several other electronic devices with strong computing capabilities.

[0028] In the proposed method for creating a 3D navigation vehicle logo provided in this application, the computer device 30 performs the algorithmic computing. Specifically, the computer device 30 creates a 3D navigation vehicle logo by performing 3D reconstruction based on the source image.

[0029] The function of computer device 30 to create a 3D navigation vehicle logo can be implemented by server 20 (i.e., computer device 30 and server 20 are the same device). Alternatively, computer device 30 and server 20 are two independent devices, and after computer device 30 creates a 3D navigation vehicle logo, it transmits the 3D navigation vehicle logo to server 20, and server 20 feeds the 3D navigation vehicle logo back to terminal device 10.

[0030] In one example, after the server 20 receives the source image uploaded by the terminal device 10 via the target application program, it transmits the source image to the computer device 30. The computer device 30 performs a 3D reconstruction based on the source image to determine the 3D navigation vehicle logo. The computer device 30 sends the 3D navigation vehicle logo to the server 20, which then provides the 3D navigation vehicle logo to the terminal device 10.

[0031] In another example, computer equipment 30 acquires a source image via a network and creates a 3D navigation vehicle logo based on the source image. The computer equipment 30 then stores the 3D navigation vehicle logo or transmits it to server 20.

[0032] In another example, terminal device 10 directly transmits a source image to computer device 30 via a target application program, computer device 30 generates a 3D navigation vehicle logo based on the source image, and then feeds the 3D navigation vehicle logo back to terminal device 10.

[0033] Figure 2 is a schematic diagram of the conceptual invention of the embodiment of this application.

[0034] In the embodiment provided in this application, a terminal device collects source images, allowing the user to collect source images of subjects based on their actual needs. The terminal device then transmits the source images to a computer device for 3D reconstruction to obtain a 3D navigation vehicle logo. In the process of the terminal device performing navigation using a navigation application program, the 3D navigation vehicle logo can be displayed on the navigation interface. This method reduces the cost of generating the 3D navigation vehicle logo and enables convenient creation of the 3D navigation vehicle logo on a mobile device.

[0035] Figure 3 is a flowchart of a method for creating a 3D navigation vehicle logo provided by one exemplary embodiment of the present application. Exemplarily, the execution body of the method may be the terminal device 10 in Figure 1, and the method for creating a 3D navigation vehicle logo will be described below using the terminal device as the execution body. As shown in Figure 3, the method includes the following steps (310-330).

[0036] Step 310: In response to the image acquisition operation, the image acquisition interface displays source images of the first object, the source images include images obtained by photographing the first object from different shooting angles, and the first object is a three-dimensional entity object in a real environment.

[0037] In some embodiments, the first object is any three-dimensional entity object in the real environment. For example, the first object may be an object, person, or building in the real environment. The user can customize the selection of the first object, and when the user attempts to create a three-dimensional navigation vehicle logo corresponding to a certain object, the terminal device collects a source image of the first object, designating that object as the first object. The first object is also called the subject.

[0038] In some embodiments, the source image represents an aspect of a first object in a real environment. The type of source image includes, but is not limited to, at least one of video or a group of images. For example, if the source image is a video, the images contained in the source image are video frames in the video. Also, for example, if the source image is a group of images, the images contained in the source image are any of the images in the group.

[0039] Optionally, the source image may include multiple images, each obtained by photographing a first object. For example, each image may record at least one of the following views of the first object: front, side, back, top, etc. The multiple images are obtained by photographing the first object from different angles. The shooting angle includes at least one of the following: shooting altitude, shooting direction, and shooting distance.

[0040] The image acquisition interface is used to display the source image of a first object. In some embodiments, the image acquisition operation acquires the source image. The image acquisition operation includes, but is not limited to, at least one of the following: a click operation, a button operation, a slide operation, and a long press operation. Exemplarily, the image acquisition interface displays an image acquisition control, and in response to a trigger operation of the image acquisition control, the terminal device displays the source image on the image acquisition interface.

[0041] For example, the source of the first object's source image may include, but not be limited to, at least one of the following: downloading from the internet, storing in a terminal device's local database, or real-time collection by the terminal device. For instance, the terminal device may use a camera in the image collection interface to capture and record the first object in real time, thereby obtaining the source image of the first object. For example, the terminal device may store the source image of the first object in a media database and, when attempting to generate a 3D navigation vehicle logo, upload the source image of the first object to the image collection interface.

[0042] Step 320: Display the 3D navigation vehicle logo for the first object, which is obtained by performing a 3D reconstruction of the first object based on the source image.

[0043] In some embodiments, the 3D navigation vehicle logo of the first object refers to a 3D model having a spatial structure similar to the first object. In the navigation process, the 3D navigation vehicle logo of the first object is displayed on the navigation interface as a positioning point. Optionally, in the navigation process, the display position and orientation of the 3D navigation vehicle logo on the navigation interface relate to the position and orientation of the terminal device in the real environment. By displaying the 3D navigation vehicle logo on the navigation interface, the user's location is positioned on the navigation interface. By uploading a custom source image, the user is guaranteed to obtain a personalized 3D navigation vehicle logo.

[0044] Optionally, the 3D navigation vehicle logo is a static 3D model, meaning its shape and structure do not change during use. By generating a 3D navigation vehicle logo that belongs to a static 3D model, the efficiency of the 3D navigation vehicle logo is improved, and the display overhead for displaying the 3D navigation vehicle logo on the navigation interface is reduced, thereby decreasing the power consumption of terminal devices.

[0045] In some embodiments, after displaying the source image of a first object on the image acquisition interface, the process of creating a 3D navigation vehicle logo is initiated. Illustratively, in response to a 3D reconstruction operation of the first object, the terminal device begins creating the 3D navigation vehicle logo of the first object. Illustratively, if the source image satisfies the creation conditions, the terminal device begins creating the 3D navigation vehicle logo of the first object.

[0046] Optionally, the process for creating the 3D navigation vehicle logo may be completed by a terminal device or by a background device in the target application program, and the background device may include a computer in the above-described implementation environment. Exemplaryly, after obtaining a source image of the first object, the terminal device sends the source image of the first object to the computer device, the computer device creates the 3D navigation vehicle logo of the first object based on the source image of the first object, and feeds the 3D navigation vehicle logo of the first object back to the terminal device, and the terminal device then displays the 3D navigation vehicle logo of the first object. Because the computing performance requirements for the process of creating the 3D navigation vehicle logo of the first object are high, the time required for the creation process can be shortened if the 3D navigation vehicle logo of the first object is created by a background device in the target application program.

[0047] Step 330: In response to the operation to adjust the display format of the 3D navigation vehicle logo, the adjusted 3D navigation vehicle logo is displayed, and the adjusted 3D navigation vehicle logo is displayed on the navigation interface.

[0048] In some embodiments, the display configuration of the 3D navigation vehicle logo is used to control the display effect of the 3D navigation vehicle logo. Optionally, the display configuration of the 3D navigation vehicle logo includes at least one of the following: the surface texture of the 3D navigation vehicle logo, the display size of the 3D navigation vehicle logo, and the display orientation of the 3D navigation vehicle logo. The surface texture of the 3D navigation vehicle logo includes, but is not limited to, the display color, surface material, and pattern of the 3D navigation vehicle logo. The display size of the 3D navigation vehicle logo is the size occupied by the display of the 3D navigation vehicle logo, and the display orientation of the 3D navigation vehicle logo, also called the orientation of the 3D navigation vehicle logo, is used to represent the direction of the 3D navigation vehicle logo.

[0049] The display format of the first object in a real-world environment may not perfectly match user preferences. By adjusting the display format of the 3D navigation vehicle logo, the adjusted 3D navigation vehicle logo will better align with user needs, enabling customization of the 3D navigation vehicle logo. Furthermore, by adjusting the display format of the 3D navigation vehicle logo in this manner, the requirements for source images are reduced, and the difficulty of collecting source images is also decreased.

[0050] Optionally, the operation to adjust the display format of the 3D navigation vehicle logo includes, but is not limited to, at least one of the following: click, button, slide, and long press operations. For specific details regarding the adjustment of the display format of the 3D navigation vehicle logo, please refer to the following examples.

[0051] In some embodiments, after adjusting the display format of the 3D navigation vehicle logo, the terminal device saves the adjusted 3D navigation vehicle logo. When performing navigation using the navigation application program, the terminal device displays the adjusted 3D navigation vehicle logo on the navigation interface.

[0052] In one example, a first user account is logged into the target application program of a terminal device. The first user account owns multiple 3D navigation vehicle logos, and the server stores the ownership relationship between the first user account and the multiple navigation vehicle logos. In response to an operation to adjust the display form of the first navigation vehicle logo among the multiple 3D navigation vehicle logos, the terminal device displays the adjusted first navigation vehicle logo and sends vehicle logo update information to the server. The server generates the adjusted first navigation vehicle logo based on the vehicle logo update information and establishes the ownership relationship between the first user account and the adjusted first navigation vehicle logo.

[0053] As described above, compared to the generation of 3D skeleton vehicle logos using related technologies, this method generates and displays a 3D navigation vehicle logo for a subject by performing a 3D reconstruction on a source image of the subject uploaded by the user. Users can freely customize the 3D navigation vehicle logo displayed on the navigation interface, fulfilling their customization requests for 3D navigation vehicle logos and enriching the types of 3D navigation vehicle logos available.

[0054] Furthermore, by automatically generating static 3D navigation vehicle logos, the production cost of 3D navigation vehicle logos can be reduced, the generation period for 3D navigation vehicle logos can be shortened, 3D navigation vehicle logos can be obtained more conveniently and quickly, and the need for iterative updates of 3D navigation vehicle logos can be met.

[0055] In some embodiments, the image acquisition interface displays an image acquisition control, and before the terminal device displays the source image of the first object on the image acquisition interface, the process further includes step 305 (not shown), namely, in response to a trigger operation of the image acquisition control, the terminal device displays a field of view screen of the camera's acquisition process of the first object on the image acquisition interface, the field of view screen corresponds to an image, the terminal device displays first prompt information on top of the field of view screen, the first prompt information prompts the camera to acquire a recommended movement trajectory of the first object, and in response to a source image acquisition completion operation, the terminal device begins executing from the step of displaying the source image of the first object on the image acquisition interface.

[0056] Optionally, the source image is a video of a first object. During the video recording process of the first object, a camera surrounds the first object and continuously collects images of the first object from different angles. Exemplarily, the video of the first object is recorded in real time in the image acquisition interface.

[0057] Optionally, the field of view is the camera view displayed on the terminal device during the first object's capture process. After it is determined that the capture is complete, the field of view is included in the source image.

[0058] The image acquisition control acquires the source image of the first object in real time, and the trigger operation for the image acquisition control includes, but is not limited to, clicks, slides, gestures, and button operations.

[0059] In some embodiments, in response to a trigger operation of the image acquisition control, the terminal device invokes the camera unit, the camera unit controls the camera to capture a source image of the first object, and the image acquisition control displays a view of the camera's acquisition process of the first object.

[0060] To ensure that details regarding the appearance of the first object are read from the source image captured by the user, the shooting angles of multiple images included in the source image change continuously. During the process in which the camera captures the source image of the first object, the terminal device displays first prompt information on the upper layer of the field of view screen. Optionally, the first prompt information includes at least one of the following: the collection of the recommended movement trajectory of the first object by the camera, and the recommended position of the first object on the field of view screen.

[0061] For example, the recommended movement trajectory includes at least one of either a 360-degree clockwise shot of the first object or a 360-degree counterclockwise shot of the first object. For example, the recommended position in the field of view is located in the central region of the field of view.

[0062] By displaying the first prompt information, the user is instructed to photograph the first object according to the recommended movement trajectory, thereby positioning the first object in the recommended location in the field of view image.

[0063] Exemplary, the first type of prompt information includes, but is not limited to, at least one of text information, logo information, and animation information. For example, the first prompt information includes the text information, "Take a 360° photo around the first object." In one example, the first prompt information is looped by a page animation, and the first prompt information ensures the integrity of the source image content by prompting the user to rotate 360° around the object and take a photo.

[0064] Figure 4 is a schematic diagram of the first prompt information provided in one exemplary embodiment of the present application.

[0065] As shown in Figure 4, the first prompt information 410 includes information about a cube animation that rotates horizontally continuously and is used to prompt the user to take a 360° photograph of the first object.

[0066] After completing the collection of source images, the terminal device displays the source images on the image collection interface, uploads the source images, and obtains the 3D navigation vehicle logo of the first object created by the computer device.

[0067] Figure 5 is a schematic diagram of the source image upload provided in one exemplary embodiment of this application.

[0068] As shown in Figure 5, after completing the collection of source images, the terminal device uploads the source images.

[0069] In some embodiments, the image acquisition interface displays an acquisition complete control 510, and the operation to complete the acquisition of source images is triggered by the acquisition complete control 510, for example, by clicking the acquisition complete control.

[0070] Optionally, the display position of the image acquisition completion control in the image acquisition interface is the same as the display position of the image acquisition control. In response to the trigger operation of the image acquisition control, the terminal device displays the field of view screen of the camera's acquisition process of the first object in the image acquisition interface, then displays the image acquisition completion control at the display position of the image acquisition control and cancels the display of the image acquisition control.

[0071] By capturing and acquiring a source image of the first object in real time and displaying prompt information on the field of view screen, it is ensured that the source image records the subject in the direction of capture, improving the accuracy of the 3D navigation vehicle logo generated based on the source image, and making the 3D navigation vehicle logo appear closer to the subject.

[0072] The following describes the process of uploading source images from a terminal device using several examples.

[0073] In some embodiments, before the terminal device displays the 3D navigation vehicle logo for the first object, the process further includes step 313 (not shown), namely, the terminal device displays second prompt information in response to a 3D reconstruction operation of the first object, the second prompt information prompting the remaining creation time for the 3D navigation vehicle logo, and if the remaining creation time is greater than the first time interval, the terminal device updates the second prompt information at each of the first time intervals until the creation of the 3D navigation vehicle logo is complete, and displays the updated second prompt information.

[0074] In some embodiments, the 3D reconstruction operation of the first object controls the terminal device to upload the source image of the first object. That is, the terminal device initiates the process of creating a 3D navigation vehicle logo through the 3D reconstruction operation of the first object.

[0075] Optionally, the remaining creation time represents the time you need to wait before acquiring the 3D navigation vehicle logo. The first time interval is pre-set; for example, the first time interval is equal to 30 seconds.

[0076] Figure 6 is a schematic diagram of a second prompt information provided in one exemplary embodiment of the present application. See 610 for the display effect of the second prompt information.

[0077] Optionally, in response to a 3D reconstruction operation of the first object, the terminal device sends a source image to the computer device and obtains second prompt information from the computer device. The terminal device displays the second prompt information and records the display time of the second prompt information. If the display time of the second prompt information is equal to the first time interval, the terminal device obtains updated second prompt information from the computer device, displays the updated second prompt information, measures the display time of the second prompt information again, and repeats the process from the step "If the display time of the second prompt information is equal to the first time interval, the terminal device obtains updated second prompt information from the computer device" until the computer device completes the creation of the 3D navigation vehicle logo.

[0078] By using a polling method, the remaining creation time is updated at regular time intervals, thereby providing users with a relatively accurate remaining creation time while avoiding communication overhead caused by frequent updates of the remaining creation time.

[0079] Generating a 3D navigation model based on a source image requires a large amount of computing power. However, to avoid situations where the computing performance of computer equipment is limited or the source image data is too large to successfully generate a 3D navigation vehicle logo, in addition to the method of initiating the 3D navigation vehicle logo creation process by having the user perform a 3D reconstruction operation on a first object, the following further provides a method in which the terminal equipment automatically triggers the 3D navigation vehicle logo creation process.

[0080] In some embodiments, the method for creating a 3D navigation vehicle logo further includes step 316 (not shown), namely, if the amount of data in the source image reaches an upper limit and the 3D reconstruction operation of the first object has not been received, the terminal device displays second prompt information.

[0081] Optionally, the data size of the source image is used to determine the total number of images contained within the source image. The more images contained within the source image, the larger the data size of the source image; and the fewer images contained within the source image, the smaller the data size of the source image. Optionally, the upper limit of the data size is the maximum amount of data the source image can contain. The upper limit of the data size may be set in advance; for example, the upper limit of the data size is 600 images.

[0082] For source images belonging to an image group, the data size of the source image is equal to the number of images in the image group. For source images belonging to a video, the data size of the source image is indicated by the video playback time, in which case the upper limit of the data size is the maximum recording time of the video. For example, the upper limit of the data size is equal to 60 seconds.

[0083] For example, the image acquisition interface displays a fourth prompt, which represents the maximum remaining recording time for the video. If the maximum remaining recording time for the video is 0, it indicates that the amount of data in the source image has reached the data limit, and the terminal device sends the source image to the computer device and displays the second prompt.

[0084] By limiting the number of images included in the source image based on a data volume limit, the computing pressure on the 3D navigation vehicle logo generation process is reduced, thereby shortening the waiting time until the 3D navigation vehicle logo is obtained.

[0085] In some embodiments, in response to an image acquisition operation, the terminal device displays a source image of a first object on the image acquisition interface, and then, in response to an identifier information setting operation, displays identifier information for a 3D navigation vehicle logo, further comprising the steps of: the identifier information uniquely identifies the 3D navigation vehicle logo; and if the identifier information for the 3D navigation vehicle logo satisfies a naming convention and the source image satisfies a content convention, the terminal device displays the 3D navigation vehicle logo of the first object.

[0086] In some embodiments, the identifier information for the 3D navigation vehicle logo includes, but is not limited to, the name and number of the 3D navigation vehicle logo. Optionally, the identifier information for the 3D navigation vehicle logo supports user customization. Exemplaryly, in response to a 3D reconstruction operation of a first object, the terminal device sends a source image to the computer device to display an identifier input interface, which displays a name input control. The identifier information setting operation is an input operation to the name input control, and the terminal device obtains the identifier information for the 3D navigation vehicle logo through this operation.

[0087] Figure 7 is a schematic diagram of identifier information acquisition provided by one exemplary embodiment of the present application. As shown in Figure 7, the identifier input interface 700 displays a name input control 710.

[0088] Optionally, after obtaining identifier information for the 3D navigation vehicle logo, the terminal device sends this identifier information to the server, which then performs a legality verification on the identifier information. If the identifier information does not pass the legality verification, the terminal device displays a fifth prompt, which is used to prompt the user to re-enter the identifier information. If the identifier information passes the legality verification, the terminal device displays a second prompt.

[0089] By performing compliance tests on identifier information and source images, abnormalities and improper naming of the generated 3D navigation vehicle logos can be avoided, improving the accuracy and efficiency of 3D navigation vehicle logo generation.

[0090] The following describes the process of adjusting the display form of a 3D navigation vehicle logo through several examples. As can be seen from the above examples, the display form of a 3D navigation vehicle logo includes at least one of the following: the surface texture of the 3D navigation vehicle logo, the display size of the 3D navigation vehicle logo, and the display orientation of the 3D navigation vehicle logo. After creating the 3D navigation vehicle logo, the user can choose whether to adjust the display form of the 3D navigation vehicle logo based on their actual needs, and the following examples of display form adjustments may be performed individually or freely combined.

[0091] Example 1: Adjust the orientation of the 3D navigation vehicle logo in the navigation interface.

[0092] In some embodiments, the display configuration includes the orientation of a 3D navigation vehicle logo in the navigation interface, and step 330 may be implemented as several of the following steps.

[0093] Substep 331-a: In response to an operation to adjust the attitude of the 3D navigation vehicle logo, the terminal device rotates the orientation of the 3D navigation vehicle logo.

[0094] In some embodiments, the orientation of the 3D navigation vehicle logo in the navigation interface is the direction of the 3D navigation vehicle logo in the navigation interface. The orientation of the 3D navigation vehicle logo in the navigation interface may also be understood as the front view direction of the 3D navigation vehicle logo.

[0095] In some embodiments, adjusting the orientation of the 3D navigation vehicle logo involves adjusting the azimuth angle of the 3D navigation vehicle logo, thereby achieving rotation of the orientation of the 3D navigation vehicle logo in the navigation interface. Adjusting the orientation of the 3D navigation vehicle logo includes, but is not limited to, sliding operations, button operations, gesture operations, and voice operations.

[0096] Optionally, the adjustment operation for the orientation of the 3D navigation vehicle logo is a sliding operation. In response to the adjustment operation for the orientation of the 3D navigation vehicle logo, the terminal device controls the 3D navigation vehicle logo to rotate according to the target rotation direction, thereby changing the orientation of the 3D navigation vehicle logo. The target rotation direction is the rotation direction corresponding to the sliding operation.

[0097] For example, the target rotation direction relates to the direction of the sliding operation. For instance, the target rotation direction corresponding to an up-and-down sliding operation adjusts the pitch angle of the 3D navigation vehicle logo. The target rotation direction corresponding to a left-and-right sliding operation adjusts the yaw angle of the 3D navigation vehicle logo.

[0098] For example, the target rotation direction relates to the region where the sliding operation occurs. For instance, in a terminal device, the target rotation direction corresponding to the sliding operation in the upper one-third region adjusts the pitch angle of the 3D navigation vehicle logo, and in a terminal device, the target rotation direction corresponding to the sliding operation in the middle one-third region adjusts the yaw angle of the 3D navigation vehicle logo.

[0099] Here, the specific embodiments of the adjustment operation for the attitude of the 3D navigation vehicle logo can be set based on actual needs, and this application is not limited thereto.

[0100] In some embodiments, after receiving an operation to adjust the orientation of the 3D navigation vehicle logo, the terminal device determines the target rotation direction and, in response to the operation to adjust the orientation of the 3D navigation vehicle logo, rotates the 3D navigation vehicle logo so as to continuously change the orientation of the 3D navigation vehicle logo.

[0101] Substep 331-b: In response to the operation to complete the adjustment of the 3D navigation vehicle logo's orientation, the terminal device displays the adjusted 3D navigation vehicle logo.

[0102] Optionally, the operation to complete the adjustment of the 3D navigation vehicle logo's posture includes, but is not limited to, at least one of the following: a slide operation, a button operation, a gesture operation, and a voice operation.

[0103] For example, if the adjustment of the orientation of the 3D navigation vehicle logo is a sliding operation, the completion of the adjustment of the orientation of the 3D navigation vehicle logo may be indicated by the disappearance of the sliding signal. That is, in response to the sliding signal of the sliding operation, the terminal device rotates the 3D navigation vehicle logo, and when the sliding operation disappears, the terminal device displays the adjusted 3D navigation vehicle logo.

[0104] Figure 8 is a schematic diagram of a direction adjustment process provided by one exemplary embodiment of the present application. The direction of the 3D navigation vehicle logo can be adjusted in the direction adjustment interface 800.

[0105] Because the 3D navigation vehicle logo has a three-dimensional structure, the display effect of the 3D navigation vehicle logo differs depending on its orientation. By adjusting the orientation of the 3D navigation vehicle logo, the display effect of the 3D navigation vehicle logo in the navigation interface becomes richer, meeting user needs for the navigation vehicle logo, reducing the number of times the navigation vehicle logo needs to be created, decreasing the number of 3D navigation vehicle logos that require server maintenance, and lowering the data storage pressure on the server.

[0106] Example 2: Adjust the surface texture of the 3D navigation vehicle logo.

[0107] In some embodiments, the display form includes a surface texture of a 3D navigation vehicle logo, and step 330 is realized as the following steps.

[0108] Substep 333-a: The terminal device displays at least one candidate surface texture, which is generated based on the original surface texture of the 3D navigation vehicle logo, and the original surface texture reflects the surface material of the first object.

[0109] In some embodiments, the original surface texture is a surface texture determined based on a source image. The original surface texture is used to simulate the surface material of the first object. Optionally, the original surface texture determined based on the source image relates to factors such as the surface material of the first object and the ambient light at the time the source image was captured.

[0110] Both the original surface texture and the candidate surface texture described above belong to a type of surface texture, which is understood as a triangular mesh. Each triangle in the triangular mesh corresponds to a local area of ​​the surface of the first object, and the display effect of the triangle (e.g., color, reflection effect, pattern, etc.) determines the display effect of that triangle in the local area corresponding to the surface of the first object. Exemplarily, a computer can use the original surface texture to render point cloud data of the first object to generate a 3D navigation vehicle logo.

[0111] Candidate surface textures are generated based on the original surface texture. Optionally, the triangular mesh corresponding to the candidate surface texture is identical in form to the triangular mesh corresponding to the original surface texture. That is, for any first triangle at any position in the triangular mesh corresponding to the candidate surface texture, a second triangle exists at the same position in the triangular mesh corresponding to the original surface texture. The shapes of the first and second triangles are similar, but the display effects of the first and second triangles are different.

[0112] In one example, the terminal device displays a three-dimensional navigation vehicle logo of a first object and at least one candidate surface texture on the form adjustment interface.

[0113] Substep 333-b: In response to the selection operation of a first surface texture from at least one candidate surface texture, the terminal device displays the 3D navigation vehicle logo having the first surface texture as the adjusted 3D navigation vehicle logo, which is generated by texture mapping the first surface texture to the point cloud data of the first object.

[0114] Optionally, the selection operation for a first surface texture from at least one candidate surface texture can be a click operation, a slide operation, or the like on the first surface texture. For example, if the selection operation for the first surface texture from at least one candidate surface texture is a click operation, the terminal device will display the adjusted 3D navigation vehicle logo in response to the click operation on the first surface texture.

[0115] For example, the adjusted 3D navigation vehicle logo is generated by a computer device. After obtaining the first surface texture selection operation, the terminal device sends a texture adjustment request to the computer device. Based on the texture adjustment request, the computer device generates the adjusted 3D navigation vehicle logo and sends it to the terminal device.

[0116] A texture adjustment request includes at least one of an account identifier, a vehicle logo identifier, and a first texture identifier, where the account identifier represents a first user account logged into the terminal device, the vehicle logo identifier indicates the 3D navigation vehicle logo of the first object, and the first texture identifier indicates the first surface texture.

[0117] Optionally, the computer equipment sends the adjusted 3D navigation vehicle logo to the server, which updates the 3D navigation vehicle logo owned by the first user account. The server then sends the 3D navigation vehicle logo to the terminal equipment.

[0118] The 3D navigation vehicle logo generated by 3D reconstruction based on the source image is limited by the actual material of the subject, resulting in a limited surface texture for the 3D navigation vehicle logo. By adjusting the surface texture of the 3D navigation vehicle logo and generating the adjusted 3D navigation vehicle logo, the texture display effect of the 3D navigation vehicle logo can be enriched.

[0119] Example 3: Adjust the display size of the 3D navigation vehicle logo.

[0120] In some embodiments, the display format includes the display size of the 3D navigation vehicle logo in the navigation interface, and step 330 is implemented as several substeps.

[0121] Substep 335-a: In response to the display size adjustment operation, the terminal device enlarges or reduces the display size of the 3D navigation vehicle logo.

[0122] In some embodiments, the operation to adjust the display size includes, but is not limited to, sliding, button operations, and click operations.

[0123] As an example, to adjust the display size, two fingers touch the terminal device and slide to change the straight-line distance between the two fingers. When the straight-line distance between the two fingers increases, the terminal device enlarges the 3D navigation vehicle logo, and when the straight-line distance between the two fingers decreases, the terminal device shrinks the 3D navigation vehicle logo.

[0124] Substep 335-b: In response to the operation to complete the display size adjustment, the terminal device displays the adjusted 3D navigation vehicle logo.

[0125] Because the size of the user-selected subject is variable, adjusting the display size of the 3D navigation vehicle logo reduces the impact of introducing the 3D navigation vehicle logo on the navigation interface and the navigation process. This allows the 3D navigation vehicle logo to act as a positional prompt while avoiding it obscuring other navigation information on the navigation interface.

[0126] The following describes the post-processing process for 3D navigation vehicle logos using several examples.

[0127] In some embodiments, the terminal device displays a 3D navigation vehicle logo of a first object, and then the terminal device displays a vehicle logo fusion interface in which at least one ornament is displayed, wherein a 3D model of the ornament is pre-installed; the terminal device displays the first ornament at a first position in a bounding box in response to a selection operation of the first ornament among the at least one ornament, wherein the bounding box is a virtual 3D space surrounding the 3D navigation vehicle logo; and the terminal device displays a fused 3D navigation vehicle logo in response to a vehicle logo fusion termination operation, wherein the fused 3D navigation vehicle logo is obtained by fusing at least one 3D model contained in the bounding box, and the fused 3D navigation vehicle logo is displayed in the navigation interface.

[0128] In some embodiments, the vehicle logo fusion interface is an interface that enables the fusion of a 3D navigation vehicle logo with an ornament. Optionally, the ornament has a 3D structure, and the 3D model of the ornament is known. Exemplarily, the 3D model of the ornament is a dynamic 3D model, i.e., the display form of the ornament is variable.

[0129] Optionally, the type of decoration may include, but is not limited to, at least one of the following: plants, animals, virtual vehicles, clothing, etc. Exemplarily, the type of decoration displayed in the vehicle logo fusion interface is related to the type of the first object. For example, if the first object is a person, then at least one decoration displayed in the vehicle logo fusion interface may include virtual vehicles, clothing, etc. Also, for example, if the first object is a stationary object, then at least one decoration displayed in the vehicle logo fusion interface may include plants, animals, etc.

[0130] After acquiring the source image, the computer device uses a category recognition model to recognize the image in the source image and determine the type of the first object. After creating a 3D navigation vehicle logo for the first object, the computer device sends the 3D navigation vehicle logo and the type of the first object to the server. Based on the type of the first object, the server determines at least one ornament. After the terminal device enters the vehicle logo fusion interface, the server sends ornament information to the terminal device, and the terminal device displays the at least one ornament on the vehicle logo fusion interface based on the ornament information, and the ornament information includes the display form of at least one ornament.

[0131] In some embodiments, the bounding box is a three-dimensional spatial region centered on the 3D navigation vehicle logo. The 3D navigation vehicle logo is located inside the bounding box. Optionally, the first position is any position within the bounding box. Exemplarily, the first position does not overlap with the position of the 3D navigation vehicle logo within the bounding box.

[0132] Optionally, the selection operation for the first ornament among at least one ornament includes, but is not limited to, click operations, slide operations, button operations, and gesture operations. The selection operation for the first ornament among at least one ornament is abbreviated as the selection operation for the first ornament.

[0133] For example, in response to a click operation on the first ornament, the terminal device decides to select the first ornament and merge it with the 3D navigation vehicle logo, the terminal device determines the position of the 3D navigation vehicle logo in the bounding box, determines the first position based on the position of the 3D navigation vehicle logo in the bounding box, and the terminal device displays the first ornament at the first position in the bounding box.

[0134] In some embodiments, the vehicle logo fusion completion operation generates the fused 3D navigation vehicle logo by notifying the system to fuse the first ornament with the 3D navigation vehicle logo. Optionally, the vehicle logo fusion interface displays a fusion confirmation control, and the vehicle logo fusion completion operation is a trigger operation for this fusion confirmation control, for example, by clicking the fusion confirmation control.

[0135] In some embodiments, the merged 3D navigation vehicle logo includes the 3D navigation vehicle logo and a first ornament. Optionally, in the process of displaying the merged 3D navigation vehicle logo on the navigation interface, the relative distance between the 3D navigation vehicle logo and the first ornament does not change.

[0136] The 3D navigation vehicle logo generated based on the source image is a static 3D model. By fusing the ornament with the 3D navigation vehicle logo, the 3D navigation vehicle logo becomes more dynamic, improving the prompting capabilities of the fusing 3D navigation vehicle logo in the navigation interface. Furthermore, by creating the 3D navigation vehicle logo first and then generating the fusing 3D navigation vehicle logo, and generating the fusing 3D navigation vehicle logo in stages, the computing overhead of the computer equipment can be reduced compared to directly generating the 3D navigation vehicle logo in one go.

[0137] Here, the examples of generating the fused 3D navigation vehicle logo and the examples of adjusting the display form of the 3D navigation vehicle logo may be freely combined.

[0138] For example, after displaying the 3D navigation vehicle logo, the terminal device first adjusts the display format of the 3D navigation vehicle logo to generate the adjusted 3D navigation vehicle logo, and then fuses the adjusted 3D navigation vehicle logo with the first decoration to obtain the fused 3D navigation vehicle logo.

[0139] Furthermore, for example, after displaying the 3D navigation vehicle logo, the terminal device first fuses the 3D navigation vehicle logo with the first ornament to obtain the fused 3D navigation vehicle logo, then adjusts the display format of the fused 3D navigation vehicle logo to obtain the adjusted 3D navigation vehicle logo.

[0140] In one example, the process of creating a 3D navigation vehicle logo involves several steps, as follows:

[0141] Step A10: In response to the image acquisition operation, the terminal device displays the source image of the first object on the image acquisition interface. The terminal device displays the 3D navigation vehicle logo of the first object.

[0142] Step A20: The terminal device displays at least one candidate surface texture and, in response to a selection operation of the first surface texture from the at least one candidate surface texture, displays the adjusted 3D navigation vehicle logo.

[0143] Optionally, after completing the morphological adjustment operation, the terminal device will display a fusion start control.

[0144] Step A30: The terminal device displays a vehicle logo fusion interface with at least one ornament displayed. Optionally, the terminal device displays the vehicle logo fusion interface in response to a trigger operation of the fusion start control.

[0145] Step A40: In response to the selection operation of the first ornament, the terminal device displays the first ornament at the first position in the bounding box, which is a virtual three-dimensional space surrounding the adjusted three-dimensional navigation vehicle logo.

[0146] Step A50: In response to the vehicle logo fusion termination operation, the terminal device displays the fused 3D navigation vehicle logo, which is obtained by fusing with at least one 3D model contained within a bounding box.

[0147] Optionally, after obtaining the merged 3D navigation vehicle logo, the terminal device disables the entry for adjusting the display format of the merged 3D navigation vehicle logo. In other words, after generating the merged 3D navigation vehicle logo, the user does not adjust the display format of the merged 3D navigation vehicle logo.

[0148] For specific details regarding each step of this embodiment, please refer to the above embodiment, and we will not repeat them here. The form of the 3D navigation vehicle logo after fusion is simpler. Therefore, the flow time can be shortened by controlling the terminal device to adjust the display form before fusing the vehicle logo.

[0149] The following example illustrates and explains the process of using a 3D navigation vehicle logo.

[0150] In some embodiments, the process of using a 3D navigation vehicle logo further includes the steps of: the terminal device displaying the 3D navigation vehicle logo on the navigation interface; and the terminal device adjusting the position and orientation of the 3D navigation vehicle logo on the navigation interface based on the position and orientation of the terminal device in the real environment.

[0151] Optionally, the orientation of the terminal device in the real environment represents the orientation of the terminal device in the real environment. For example, if the terminal device moves north, its orientation in the real environment is north. Optionally, the navigation interface displays a navigation map, and the 3D navigation vehicle logo is displayed on the navigation map, reflecting the terminal device's position in the real environment.

[0152] The position of the 3D navigation vehicle logo in the navigation interface may be understood as the position of the 3D navigation vehicle logo on the navigation map. The position of the 3D navigation vehicle logo in the navigation interface corresponds to the position of the terminal device in the real environment.

[0153] The orientation of the 3D navigation vehicle logo includes the orientation of the 3D navigation vehicle logo, and the orientation of the 3D navigation vehicle logo indicates the direction of change of the position of the 3D navigation vehicle logo in the navigation interface.

[0154] Optionally, the navigation interface supports the display of up to t 3D navigation vehicle logos, where t is a positive integer. Each of these t 3D navigation vehicle logos corresponds to a different terminal device, and the position and orientation of the i-th 3D navigation vehicle logo in the navigation interface are relative to the position and orientation of the i-th terminal device corresponding to that i-th 3D navigation vehicle logo in the real environment.

[0155] Here, a solution that displays a 3D navigation vehicle logo compatible with other terminal devices on the navigation interface requires authorization from users of other devices and can only be implemented if it complies with local laws and regulations. This function is simply used for following within the same convoy, preventing vehicles from falling behind the convoy, and is used in application scenarios where the team is heading to the same destination.

[0156] Optionally, the navigation interface displays t 3D navigation vehicle logos only if t terminal devices each input the same destination into the navigation application program and the t terminal devices mutually authorize each other. Illustratively, in this case, the navigation interface displays a vehicle logo sharing identifier, which prompts that the 3D navigation vehicle logo has been displayed on the navigation interface of another terminal device. Illustratively, at every second time interval, the navigation interface displays an authorization request, and in response to an acceptance operation of the authorization request, the terminal device allows other terminal devices to continuously display the 3D navigation vehicle logo corresponding to that terminal device on the navigation interface. In response to a rejection operation of the authorization request, the terminal device sends a rejection prompt to the server, and based on the rejection prompt, the server does not send position change information of the terminal device's 3D navigation vehicle logo on the navigation interface to other devices. This allows the vehicle logo sharing function on the navigation interface to be immediately disabled based on actual needs.

[0157] The following describes a method for creating a 3D navigation vehicle logo on the terminal device side, using an overall embodiment. The main body of this embodiment is the terminal device, for example, the target client on the terminal device. This embodiment includes the following steps.

[0158] Step B10: Display the logo selection interface where the first collection entry is displayed, the logo selection interface is used to manage at least one 3D navigation vehicle logo, the first collection entry is used to achieve source image collection, and in response to a trigger operation of the first collection entry, display the image collection interface.

[0159] Optionally, the first collection entry may be implemented as a banner in the logo selection interface.

[0160] In some embodiments, the step of the terminal device displaying an image acquisition interface in response to a trigger operation of a first acquisition entry includes the step of displaying a vehicle logo creation interface with a first control and a second control displayed in response to a trigger operation of a first acquisition entry, and the step of the terminal device displaying an image acquisition interface in response to a trigger operation of the second control. The first control is used to display a vehicle logo ownership interface, which is used to display a 3D navigation vehicle logo owned by a first user account logged into the terminal device, and the second control is used to display an image acquisition control.

[0161] In some embodiments, before the terminal device displays the image acquisition interface, the process further includes a step of displaying a sixth prompt information if the first user account meets the user requirements. The sixth prompt information is used to request authorization for the source image acquisition process. Exemplarily, the sixth prompt information is displayed in the form of a pop-up window.

[0162] Optionally, user conditions include the first user account entering the image collection interface for the first time, or the first user account not entering for the first time but not having granted the target application program permission to collect source images. If the first user account does not meet the user conditions, the terminal device displays the sixth prompt information.

[0163] In some embodiments, before displaying the image acquisition interface, the process further includes displaying a seventh prompt information if the first user account meets the user requirements. The seventh prompt information is used to prompt how to create a 3D navigation vehicle logo.

[0164] Figure 9 is a schematic diagram of an exemplary embodiment of the present application, showing the process before entering the image acquisition interface.

[0165] The terminal device enters the vehicle logo production interface, which displays the first control 920 and the second control 930, via the first collection entry 910. In response to the trigger operation of the second control 930, the terminal device displays the image collection interface. If the first user account meets the user requirements, the sixth prompt information 940 and the seventh prompt information 950 are displayed.

[0166] Step B20: The image acquisition interface displays the image acquisition controls, and in response to a trigger operation of the image acquisition controls, the image acquisition interface displays the field of view of the camera's acquisition process of the first object.

[0167] Step B30: The first prompt information is displayed on the upper layer of the field of view screen, and the first prompt information is used to prompt the camera to collect the recommended movement trajectory of the first object.

[0168] Step B40: In response to the image acquisition operation, the source image of the first object is displayed in the image acquisition interface.

[0169] Step B50: In response to a 3D reconstruction operation of the first object, display second prompt information, or if the amount of data in the source image has reached the upper limit of the data amount and a 3D reconstruction operation of the first object has not been received, display second prompt information.

[0170] Step B55: In response to the identifier information setting operation, the identifier information of the 3D navigation vehicle logo is displayed, and the identifier information is used to uniquely identify the 3D navigation vehicle logo. If the identifier information of the 3D navigation vehicle logo satisfies the naming convention and the source image satisfies the content convention, the step of displaying the 3D navigation vehicle logo of the first object (for example, step 310) is performed.

[0171] Step B60: If the remaining creation time is greater than the first time interval, update the second prompt information at each first time interval until the creation of the 3D navigation vehicle logo is complete, and display the updated second prompt information.

[0172] Step B70: Display the 3D navigation vehicle logo for the first object.

[0173] Step B80: Display a vehicle logo fusion interface with at least one ornament displayed, a 3D model of the ornament pre-installed, and in response to a first ornament selection operation, display the first ornament in a first position in the bounding box, and in response to a vehicle logo fusion end operation, display the fused 3D navigation vehicle logo.

[0174] Step B90: In response to the adjustment operation for the display format of the 3D navigation vehicle logo, the adjusted 3D navigation vehicle logo is displayed.

[0175] Step B100: The terminal device displays a 3D navigation vehicle logo on the navigation interface, and the terminal device adjusts the position and orientation of the 3D navigation vehicle logo on the navigation interface based on the position and orientation of the terminal device in the actual environment.

[0176] Figure 10 is a schematic diagram of a navigation interface provided in one exemplary embodiment of the present application.

[0177] As shown in Figure 10, the navigation interface 1000 displays a 3D navigation vehicle logo 1010.

[0178] For details not described in this embodiment, please refer to the above embodiments.

[0179] Figure 11 is a schematic diagram of the display effect of a 3D navigation vehicle logo provided by one exemplary embodiment of this application.

[0180] When the 3D navigation vehicle logo is located at the first direction 1110, the display mode of the 3D navigation vehicle logo in the navigation interface is 1100-a; when the 3D navigation vehicle logo is located at the second direction 1120, the display mode of the 3D navigation vehicle logo in the navigation interface is 1100-b; when the 3D navigation vehicle logo is located at the third direction 1130, the display mode of the 3D navigation vehicle logo in the navigation interface is 1100-c; and when the 3D navigation vehicle logo is located at the fourth direction 1140, the display mode of the 3D navigation vehicle logo in the navigation interface is 1100-d.

[0181] Figure 12 is an interaction diagram of the vehicle logo application process provided in one exemplary embodiment of this application.

[0182] In some examples, the method for creating a 3D vehicle logo provided in this application involves multiple platforms, primarily including a vehicle logo management platform (also known as a themed bulletin board), child application programs (i.e., target application programs), parent application programs, shared pages (H5), and clients, servers (including computer equipment), Apollo configuration management, etc.

[0183] The vehicle logo management platform is the primary entry point for creating 3D navigation vehicle logos and is used to manage the 3D navigation vehicle logos owned by user accounts. The vehicle logo management platform provides users with the first collection entry.

[0184] The child application program is the target application program in the above embodiment and is used to acquire source images and customize the 3D navigation vehicle logo. As described in the above embodiment, in response to the trigger operation of the first collection entry, the terminal device displays a vehicle logo creation interface that includes the first and second controls. When attempting to create a 3D navigation vehicle logo, the user triggers the second control.

[0185] In response to the trigger operation of the second control, the terminal device displays the image acquisition interface. Optionally, before displaying the image acquisition interface, the terminal device determines whether the first user account is entering the image acquisition interface for the first time. If the first user account is entering the image acquisition interface for the first time, the terminal device displays the sixth prompt information and the seventh prompt information (also called the strategy page) in the form of pop-up windows.

[0186] If the first user account does not meet the user requirements, the terminal device displays the image acquisition interface and, in response to operations on the image acquisition controls, acquires a source image of the first object. If the source image is a video, the first object may be captured in real time on the image acquisition interface. During the capture process, the terminal device displays first prompt information on the field of view screen, which is used to prompt at least one of the following: a recommended capture trajectory for capturing the first object, or a recommended position of the first object in the image.

[0187] Optionally, during the process of capturing the first object, the image acquisition interface may display a fourth prompt indicating the maximum remaining capture time. This fourth prompt may be a countdown from the time the first object is captured until the maximum capture time has elapsed.

[0188] If the maximum remaining recording time is equal to 0, or if the user performs a 3D reconstruction operation on the first object, the terminal device uses the recorded video as the source image. The terminal device sends the source image to the server, which then performs a compliance check on the source image.

[0189] Subsequently, in response to the identifier information setting operation, the terminal device displays the identifier information for the 3D navigation vehicle logo, and the terminal device sends the identifier information for the 3D navigation vehicle logo to the server, where the server performs a compliance check on the identifier information for the 3D navigation vehicle logo.

[0190] If the identifier information for the 3D navigation vehicle logo satisfies the naming convention, the terminal device displays a failure prompt and prompts the user to re-enter the identifier information for the 3D navigation vehicle logo. If the identifier information for the 3D navigation vehicle logo satisfies the naming convention and the source image satisfies the content convention, the server sends the source image to the computer device, which then performs 3D reconstruction on the source image to generate the 3D navigation vehicle logo.

[0191] During the process in which the computer equipment completes the creation of the 3D navigation vehicle logo, the terminal equipment displays a second prompt indicating the remaining time to create the 3D navigation vehicle logo. The terminal equipment updates the second prompt information according to the first time interval. After the creation of the 3D navigation vehicle logo is complete, the terminal equipment displays the 3D navigation vehicle logo.

[0192] After creating the 3D navigation vehicle logo, the terminal device will respond to user input by adjusting the display format of the 3D navigation vehicle logo and supporting fusion processing for the 3D navigation vehicle logo. For specific details regarding this step, please refer to the above embodiment, which will not be repeated here.

[0193] After creating a 3D navigation vehicle logo with a first user account, the first user account is supported to socially share the 3D navigation vehicle logo. This function can be completed jointly by a child application program and a parent application program.

[0194] Parent application program: Primarily responsible for user account login. In addition, the target application program is responsible for allowing users to view the 3D navigation vehicle logo details page content outside the app, and for sharing the 3D navigation vehicle logo between different accounts.

[0195] Server: Synchronize account information and complete compliance checks. In order to carry out the production flow in accordance with laws and regulations, compliance checks must be performed on both the image source captured and uploaded by the terminal device and the identifier information of the 3D navigation vehicle logo.

[0196] In some embodiments, after a terminal device displays a 3D navigation vehicle logo for a first object, the method for reconstructing the 3D navigation vehicle logo further includes the steps of: displaying the first navigation vehicle logo and the second navigation vehicle logo in response to an acquisition operation for the first navigation vehicle logo and the second navigation vehicle logo, wherein the first navigation vehicle logo belongs to the 3D navigation vehicle logo and the second navigation vehicle logo belongs to the 3D navigation vehicle logo; and displaying a combined navigation vehicle logo in response to a vehicle logo combination operation, wherein the combined navigation vehicle logo consists of the first navigation vehicle logo and the second navigation vehicle logo, and the combined navigation vehicle logo is displayed on the navigation interface.

[0197] Optionally, a first navigation vehicle logo is created by a first user account logged into the target application program of a terminal device (referred to as the first terminal in this embodiment), and a second navigation vehicle logo is created by a first user account logged into the target application program of another terminal device (referred to as the second terminal in this embodiment).

[0198] Optionally, the step of a first terminal displaying a first navigation vehicle logo and a second navigation vehicle logo in response to an operation to acquire a first navigation vehicle logo and a second navigation vehicle logo includes the step of the first terminal receiving vehicle logo provision information transmitted from the second terminal, wherein the vehicle logo provision information is used to authorize the first terminal to acquire the second navigation vehicle logo; the step of the first terminal transmitting a vehicle logo acquisition request to a server based on the vehicle logo provision information; and the step of the terminal device receiving the second navigation vehicle logo transmitted from the server based on the vehicle logo acquisition request.

[0199] The vehicle logo information includes a second terminal identifier and a second navigation vehicle logo identifier.

[0200] In some embodiments, the step of a first terminal displaying a combined navigation vehicle logo in response to a vehicle logo combination operation includes the step of the first terminal generating a vehicle logo combination request and sending it to a server in response to the vehicle logo combination operation, wherein the vehicle logo combination request includes identifier information for the first navigation vehicle logo, identifier information for the second navigation vehicle logo, and the offset position of the first navigation vehicle logo relative to the second navigation vehicle logo, thereby, if the server decides to allow the combination of the first navigation vehicle logo and the second navigation vehicle logo based on the vehicle logo combination request, it sends a vehicle logo combination instruction to a computer device, and based on the vehicle logo combination instruction, the computer device places the first navigation vehicle logo and the second navigation vehicle logo in the same virtual space and obtains the combined navigation vehicle logo.

[0201] For example, a vehicle logo combination instruction includes identifier information for a first navigation vehicle logo, identifier information for a second navigation vehicle logo, and the offset position of the first navigation vehicle logo relative to the second navigation vehicle logo.

[0202] The server estimates the volume of the combined navigation vehicle logos based on the offset position of the first navigation vehicle logo relative to the second navigation vehicle logo. Optionally, if the volume of the combined navigation vehicle logos is less than or equal to a volume limit, the server decides to allow the combination of the first and second navigation vehicle logos. If the volume of the combined navigation vehicle logos exceeds the volume limit, the server decides not to allow the combination of the first and second navigation vehicle logos. A volume limit is pre-set to control the volume of the combined navigation vehicle logos and prevent them from obscuring road condition information on the navigation interface.

[0203] For example, after the first terminal receives vehicle logo information transmitted from the second terminal, it responds to the application operation of the second navigation vehicle logo by displaying the second navigation vehicle logo on the navigation interface, that is, directly using the 3D navigation vehicle logo created by the second terminal. This allows different users to conveniently share the 3D navigation vehicle logo.

[0204] Since 3D navigation vehicle logos are generated from source images, and the source images that different users can collect are limited, the above method supports the synthesis of 3D navigation vehicle logos collected by multiple users. After creating a 3D navigation vehicle logo, a function is provided to combine the 3D navigation vehicle logos, thereby reducing the requirements for source images. Furthermore, by generating navigation vehicle logos that combine using 3D navigation vehicle logos, more 3D navigation vehicle logos are provided to users, improving the richness of the 3D navigation vehicle logos.

[0205] Figure 13 is a flowchart of a method for creating a 3D navigation vehicle logo provided by another exemplary embodiment of this application. Exemplarily, the execution body of the method may be the computer device 30 shown in Figure 1, and the method for creating a 3D navigation vehicle logo will be described below using the computer device as the execution body. As shown in Figure 2, the method includes the following steps (1310-1340).

[0206] Step 1310: Obtain source images of the first object, which include images obtained by photographing the first object from different angles, and the first object is a 3D entity object in a real environment.

[0207] In some embodiments, the source image is transmitted from the terminal device to the computer device. In some other embodiments, the source image is obtained by the computer device searching for and downloading it from the internet. For a specific description of the source image and the first object, please refer to the embodiments on the terminal device side, and will not repeat here.

[0208] Step 1320: Keypoints are recognized in the source image to generate point cloud data for the first object, and the point cloud data is used to describe the position and display form of the keypoints of the first object in the real environment.

[0209] In some embodiments, keypoints represent the surface contour of a first object. In other words, keypoints are points on the surface of a first object. Optionally, keypoints include at least one of the following: contour edge points on the first object, color within the contour of the first object, or points on a boundary with significant undulations in shape. Keypoints are also called feature points. Exemplaryly, keypoints are determined based on the transformation region of pixel values ​​of pixel points in an image. For example, keypoints are extreme points of change in pixel points in an image.

[0210] In some embodiments, point cloud data is a dataset of keypoints and is used to reconstruct a first object in a virtual three-dimensional space.

[0211] Optionally, the point cloud data includes keypoint location and luminosity information. The location information indicates the 3D coordinates of the keypoints, and the luminosity information represents the color of the keypoints and their refraction and reflectivity to light.

[0212] Step 1330: Perform a 3D reconstruction based on the point cloud data to determine the original surface texture of the first object, and the original surface texture reflects the surface material of the first object.

[0213] In this embodiment, the original surface texture of the first object is the original surface texture mentioned in the above embodiment. For a detailed description of the original surface texture portion, please refer to the above embodiment, and it will not be repeated here.

[0214] Step 1340: Texture mapping is performed on the point cloud data based on the surface texture of the first object to create a 3D navigation vehicle logo for the first object, and the 3D navigation vehicle logo is displayed in the navigation interface.

[0215] In some embodiments, a computer device renders point cloud data based on a surface texture to obtain a 3D navigation vehicle logo for a first object. After generating the 3D navigation vehicle logo for the first object, the computer device sends the 3D navigation vehicle logo for the first object to a server, which then transfers the 3D navigation vehicle logo for the first object to a terminal device.

[0216] As described above, compared to the related technology in which engineers generate 3D skeleton vehicle logos, the embodiment of this application uses computer equipment to perform 3D reconstruction based on the source image of the subject to generate a 3D navigation vehicle logo for the subject. This reduces the production cost of the 3D navigation vehicle logo, shortens the generation cycle of the 3D navigation vehicle logo, allows for more convenient and rapid acquisition of the 3D navigation vehicle logo, and meets the need for iterative updating of the 3D navigation vehicle logo.

[0217] Furthermore, in this method, by creating a 3D navigation vehicle logo in the cloud using computer equipment, mobile devices gain the capability to generate 3D navigation vehicle logos, thereby improving the convenience of the 3D navigation vehicle logo creation process.

[0218] The point cloud data determination process will be introduced and explained below through several examples.

[0219] In some embodiments, step 1320, which recognizes keypoints in a source image and determines the point cloud data of a first object, includes several substeps.

[0220] Substep 1321: The computer equipment recognizes keypoints in multiple images from the source image and determines keypoint information for each image. The keypoint information includes a keypoint descriptor, which is used to represent the local structural features of the keypoint in the image.

[0221] In some embodiments, multiple images in the source image are multiple images selected from the source image. For example, if the source image belongs to a video, any two adjacent images among the multiple images are two video frames that are spaced k frames apart in the video, where k is a positive integer. Optionally, the computer device selects one image for every k consecutive image frames in the video to obtain multiple images, and then performs a 3D reconstruction based on these multiple images.

[0222] For images with consecutive shooting angles, such as two consecutive video frames in a video, there is a significant overlap in the amount of information contained in those two consecutive video frames. By selecting some images from the source image, the overlap in the amount of information contained in each of those selected images is reduced. Subsequently, a computer device participates in a 3D reconstruction process using these selected images, thereby reducing the amount of computing power required to generate a 3D navigation vehicle logo.

[0223] In some embodiments, a descriptor represents a visual feature within the region to which a keypoint belongs in an image. The visual feature includes shape and texture features within the keypoint region, where the shape feature represents the shape of the local region around the keypoint of the first object, and the texture feature represents the texture of the local region around the keypoint of the first object. Optionally, the descriptor is represented in vector form. The vector dimensions of the descriptors possessed by multiple keypoints in the image are equal.

[0224] In some embodiments, the steps of a computer device recognizing keypoints in multiple images from a source image and determining keypoint information for each image include: for each of the multiple images, the computer device performing at least one blurring and downsampling process on the image to obtain a Gaussian image set, wherein the Gaussian image set includes multiple Gaussian image groups, and each Gaussian image group includes Gaussian images having different degrees of blurring; for each Gaussian image group, the computer device performing a difference process on two adjacent Gaussian images in the Gaussian image group to obtain a difference image group; the computer device determining at least one extreme point based on the trend of pixel value changes of pixel points in at least one difference image of the difference image group; the computer device establishing an extreme point change curve based on the at least one extreme point to determine at least one keypoint of a first object, and the computer device determining keypoint information for an image based on the at least one keypoint and the Gaussian image set.

[0225] In some embodiments, for one of several images, a computer generates a Gaussian pyramid of that image. Blurring is the process of processing pixel points in an image using a Gaussian kernel. The Gaussian kernel performs a fusion process (e.g., calculates the average) on the pixel values ​​of pixel points in one region to obtain a fused pixel value, so that after the fusion process, the value of each pixel point in that region becomes equal to the fused pixel value.

[0226] Optionally, a set of Gaussian images is called a Gaussian pyramid. In a Gaussian pyramid, multiple sets of Gaussian images have a hierarchical structure. The higher the hierarchy of the Gaussian image set, the smaller the size of the Gaussian images within it and the higher the degree of blurring. The lowest level of Gaussian image sets includes the image itself, or upsampled images obtained by upsampling the image. Upsampling increases the size of an image, while downsampling decreases the size of an image.

[0227] Optionally, a difference image can be obtained by performing a difference operation on two Gaussian images with similar degrees of blurring within the same set of Gaussian images. The difference operation is implemented by subtracting the pixel point values ​​at corresponding positions in the two Gaussian images.

[0228] For example, a computer device performs a difference operation on two adjacent Gaussian images within the same set of Gaussian images to obtain a difference image. For instance, if we assume that a first set of Gaussian images among multiple sets of Gaussian images contains x Gaussian images, then the first set of difference images determined based on this first set of Gaussian images will contain x-1 difference images, where x is a positive integer greater than 1.

[0229] In some embodiments, the step of a computer device establishing an extremum change curve based on at least one extremum point to determine at least one key point of a first object includes the steps of the computer device performing a Taylor expansion based on at least one extremum point and fitting it to generate an extremum change curve, the extremum change curve including the at least one extremum point, and the computer device differentiating the extremum change curve to determine at least one continuous extremum point, with the computer device designating the continuous extremum point as a key point.

[0230] Because the pixel points in the image change discretely, determining keypoints using an extreme point change curve improves the accuracy of keypoints recognized from the image, thereby increasing the similarity between the generated 3D navigation vehicle logo and the subject.

[0231] In some embodiments, the step of a computer device determining keypoint information of an image based on at least one keypoint and a set of Gaussian images includes, for each of the at least one keypoint, the computer device determining the associated region of the keypoint from the Gaussian image corresponding to the keypoint, wherein the Gaussian image corresponding to the keypoint is the Gaussian image in the set of Gaussian images whose degree of blur is closest to the degree of blur of the difference image corresponding to the keypoint, and the keypoint is the central point of the associated region; the computer device statistically calculates the magnitude of the gradient of each pixel point included in the associated region and determines the direction in which the magnitude of the gradient is maximum as the principal direction of the keypoint; the computer device transforms the coordinate system of the Gaussian image corresponding to the keypoint based on the principal direction of the keypoint to obtain an adjusted Gaussian image; and in the adjusted Gaussian image, the computer device statistically calculates the magnitude of the gradient of the pixel points that are in a first radius region with the keypoint as the center to obtain a descriptor of the keypoint.

[0232] Optionally, the difference image corresponding to a keypoint is the difference image used by the determined keypoint.

[0233] Optionally, the computer device determines the keypoint descriptors based on the SIFT (Scale Invariant Feature Transform) algorithm, i.e., obtains keypoint information.

[0234] Substep 1323: The computer equipment determines camera parameters based on the keypoint information of the image, and the camera parameters include intrinsic and extrinsic camera parameters used to capture the source image.

[0235] In some embodiments, the step of a computer device determining camera parameters based on keypoint information of an image is: A computer device determines at least one keypoint chain based on keypoint information of multiple images, wherein the keypoint chain represents changes in the capture positions of the multiple images. The computer device estimates the parameters based on at least one keypoint chain to determine the initial parameters, and The process includes the step of a computer device performing joint optimization on at least one keypoint and initial parameters to obtain camera parameters.

[0236] Optionally, camera parameters include intrinsic and extrinsic camera parameters, with intrinsic parameters including focal length and principal point, and extrinsic camera parameters including camera position and camera rotation angle.

[0237] In some embodiments, the step of a computer device determining at least one keypoint chain based on the keypoint information of each image in the source images includes the step of the computer device performing similarity matching on the keypoint information of a first image and the keypoint information of a second image in the original image group for each original image group in the source images to obtain at least one pair of matching points, wherein the difference between the shooting angle of the first image and the shooting angle of the second image is less than or equal to a first threshold; the step of the computer device removing noise from at least one pair of matching points to obtain at least one keypoint group; and the step of the computer device performing similarity matching on the keypoint group comprising the source image to determine at least one keypoint chain, wherein the keypoint group comprising the source image includes the keypoint group of each original image group.

[0238] Optionally, the computer device determines at least one keypoint chain based on sequential matching. Specifically, the computer device performs similarity matching on adjacent images to obtain at least one matching point group. The computer device may use the RANSAC (Random Sample Consensus) algorithm to remove noise from at least one set of matching points and fit the noise using the least squares method. Subsequently, the computer device performs matching on consecutive frames to generate and determine at least one keypoint chain.

[0239] Optionally, the computer equipment decides to estimate parameters based on a keypoint chain to obtain initial parameters, and employs Bundle Adjustment (BA) to co-optimize keypoint location information and camera parameters. Specifically, the computer equipment estimates the reprojection error based on the initial parameters and keypoint location information, calculates residuals based on the reprojection error, constructs a linear equation based on the reciprocal of the residuals with respect to camera parameters and keypoint location information, and updates the camera parameters and keypoint location information by finding the increment of the linear equation.

[0240] Substep 1325: The computer equipment determines the point cloud data of the first object based on the camera parameters.

[0241] In some embodiments, the point cloud data includes keypoint location information and keypoint luminosity information, the keypoint location information is determined based on camera parameters and source images, and the luminosity information represents the display form of the keypoints. The steps of a computer device determining the point cloud data of a first object based on camera parameters include: for a third image from the source images, the computer device generating a reconstructed image based on the third image and camera parameters using a scenario reconstruction network; the computer device adjusting the parameters of the scenario reconstruction network based on the difference between the reconstructed image and the third image to obtain a trained scenario reconstruction network; for each of at least one keypoints, the computer device predicting based on the keypoint location information via the trained scenario reconstruction network to generate keypoint luminosity information; and the computer device determining the point cloud data of a first object based on the keypoint luminosity information and location information.

[0242] Optionally, the scenario reconstruction network constructs a three-dimensional space, which is used to reconstruct the first object and the real environment in which the first object is located when the source image is captured.

[0243] In some embodiments, the scenario reconstruction network is a NeRF (Neural Radiance Fields) network. Optionally, the step of the scenario reconstruction network generating a reconstructed image based on a third image and camera parameters includes: a step in which a computer device determines a viewpoint position and a line of sight direction based on camera parameters, wherein the viewpoint position is used to simulate the location in real space when the camera photographs a first object in three-dimensional space, and the line of sight direction is used to simulate the direction of light reflection from which the first object is imaged when the camera photographs the first object in three-dimensional space; a step in which the computer device calculates the integral of luminosity information of at least one point that has passed through the line of sight direction in three-dimensional space to obtain the pixel value of the pixel point corresponding to that line of sight direction in the reconstructed image; and a step in which, after determining the pixel value of the pixel point corresponding to each line of sight direction in the reconstructed image, obtains a reconstructed image from the pixel value of each of the above pixel points.

[0244] Optionally, the difference between the reconstructed image and the third image is calculated using the mean squared error. The computer equipment adjusts the network parameters of the scenario reconstruction network based on gradient descent.

[0245] In some embodiments, the process further includes the steps of: recognizing keypoints in a source image and generating point cloud data of a first object; the computer equipment performing plane fitting based on the point cloud data to recognize background points, wherein the background points are planar keypoints unrelated to the first object in three-dimensional space; the computer equipment performing outlier recognition based on the point cloud data to determine at least one outlier, wherein the outlier is noise due to environmental factors when the first object is photographed; and the computer equipment removing the background points and outliers from the point cloud data to obtain processed point cloud data, wherein the processed point cloud data is used for three-dimensional reconstruction.

[0246] Optionally, computer equipment can fit and recognize planes in point cloud data based on a random sample consensus algorithm. This removes planar structures, such as ground and walls, from the point cloud data. Furthermore, point cloud data may contain noise or outliers, which can be generated due to sensor errors, reflections, etc. To improve the quality of the point cloud, these outliers must be recognized and removed. Common methods include statistical and density-based methods for outlier removal. Points in point cloud data generally represent multiple different objects or scenario structures. To perform individual processing or modeling on these structures, the point cloud needs to be divided into multiple clusters or groups using clustering based on Euclidean distance.

[0247] In some embodiments, the step of a computer device performing a 3D reconstruction based on point cloud data to determine the surface texture of a first object includes the steps of performing a Poisson reconstruction based on the point cloud data to generate first texture information, and performing a smoothing process on the first texture information to obtain second texture information, and simplifying the second texture information to obtain the surface texture of the first object.

[0248] Optionally, the steps of a computer device performing a Poisson reconstruction based on point cloud data to generate first texture information include: establishing an octree structure based on keypoint location information, wherein the octree structure includes at least one leaf node having the same depth, and each leaf node includes at least one keypoint in the same three-dimensional space; establishing an implicit function corresponding to each of the at least one leaf node, wherein the implicit function is used to calculate the normal vector of the keypoint included in the leaf node, and the normal vector of the keypoint represents the direction of the keypoint in the local plane of the surface of the first object; obtaining a Poisson equation by determining the parameters of the implicit function based on finite elements; and determining the isosurfaces of the first object based on the Poisson equation, performing triangulation on the isosurfaces of the first object to generate first texture information.

[0249] The following are apparatus embodiments of this application, which are used to carry out method embodiments of this application. Details not disclosed in the apparatus embodiments of this application should be referred to in the method embodiments of this application.

[0250] Figure 14 is a block diagram of a three-dimensional navigation vehicle logo creation device provided by one exemplary embodiment of the present application. The device 1400 is A source acquisition module 1410 that displays a source image of a first object on an image acquisition interface in response to an image acquisition operation, wherein the source image includes images obtained by photographing the first object from different shooting angles, and the first object is a three-dimensional entity object in a real environment. A vehicle logo display module 1420 that displays a three-dimensional navigation vehicle logo for the first object, wherein the three-dimensional navigation vehicle logo is obtained by performing a three-dimensional reconstruction of the first object based on the source image, A vehicle logo adjustment module 1430 that displays an adjusted 3D navigation vehicle logo in response to an adjustment operation of the display form of the 3D navigation vehicle logo, wherein the adjusted 3D navigation vehicle logo is displayed on the navigation interface.

[0251] In some embodiments, the display configuration includes the orientation of the 3D navigation vehicle logo in the navigation interface, and the vehicle logo adjustment module 1430 rotates the orientation of the 3D navigation vehicle logo in response to an adjustment operation of the orientation of the 3D navigation vehicle logo, and displays the adjusted 3D navigation vehicle logo in response to an operation to end the adjustment of the orientation of the 3D navigation vehicle logo.

[0252] In some embodiments, the display form includes the surface texture of the 3D navigation vehicle logo, the vehicle logo adjustment module 1430 displays at least one candidate surface texture, the candidate surface texture is generated based on the original surface texture of the 3D navigation vehicle logo, the original surface texture reflects the surface material of the first object, and in response to a selection operation of the first surface texture from the at least one candidate surface texture, the 3D navigation vehicle logo having the first surface texture is displayed as the adjusted 3D navigation vehicle logo, the adjusted 3D navigation vehicle logo is generated by mapping the texture to the point cloud data of the first object based on the first surface texture.

[0253] In some embodiments, the vehicle logo adjustment module 1430 further displays a vehicle logo fusion interface in which at least one ornament is displayed, the three-dimensional model of the ornament is pre-installed, and in response to a selection operation of a first ornament among the at least one ornament, the first ornament is displayed in a first position in the bounding box, the bounding box being a virtual three-dimensional space surrounding the three-dimensional navigation vehicle logo, and in response to a vehicle logo fusion termination operation, the fused three-dimensional navigation vehicle logo is displayed, the fused three-dimensional navigation vehicle logo is obtained by fusing at least one three-dimensional model contained in the bounding box, and the fused three-dimensional navigation vehicle logo is displayed in the navigation interface.

[0254] In some embodiments, the apparatus 1400 further includes an image acquisition module, which, in response to a trigger operation of the image acquisition control, displays a field of view screen of the camera's acquisition process of the first object on the image acquisition interface, the field of view screen corresponds to the image, and displays first prompt information on top of the field of view screen, the first prompt information is used to prompt the camera to acquire a recommended movement trajectory of the first object, and in response to a completion operation of source image acquisition, the process begins from the step of displaying the source image of the first object on the image acquisition interface.

[0255] In some embodiments, the apparatus 1400 further includes an information display module which displays second prompt information in response to a three-dimensional reconstruction operation of the first object, the second prompt information is used to prompt the remaining creation time of the three-dimensional navigation vehicle logo, and if the remaining creation time is greater than a first time interval, the second prompt information is updated at each of the first time intervals until the creation of the three-dimensional navigation vehicle logo is completed, and the updated second prompt information is displayed.

[0256] In some embodiments, the information display module further displays the second prompt information if the amount of data in the source image has reached its upper limit and the 3D reconstruction operation of the first object has not been received.

[0257] In some embodiments, the apparatus 1400 further includes an identifier determination module, which, in response to an identifier information setting operation, displays identifier information for the 3D navigation vehicle logo, the identifier information uniquely identifies the 3D navigation vehicle logo, and if the identifier information for the 3D navigation vehicle logo satisfies a naming convention and the source image satisfies a content convention, the apparatus begins executing from the step of displaying the 3D navigation vehicle logo for the first object.

[0258] Figure 15 is a block diagram of a three-dimensional navigation vehicle logo creation device provided by one exemplary embodiment of the present application. The device 1500 is Source acquisition module 1510 that acquires source images relating to a first object, wherein the source images include images obtained by photographing the first object from different angles, and the first object is a three-dimensional entity object in a real environment. A data determination module 1520 that recognizes key points in the source image and determines point cloud data of the first object, wherein the point cloud data describes the position and display form of the key points of the first object in the actual environment. A three-dimensional reconstruction module 1530 that performs three-dimensional reconstruction based on the point cloud data to determine the original surface texture of the first object, wherein the original surface texture reflects the surface material of the first object. A vehicle logo creation module 1540 that creates a three-dimensional navigation vehicle logo (mark) of the first object by texture mapping the point cloud data based on the surface texture of the first object, wherein the three-dimensional navigation vehicle logo is displayed on the navigation interface.

[0259] In some embodiments, the data determination module 1520 includes a keypoint determination unit that recognizes keypoints in a plurality of images from the source images and determines keypoint information for each of the images, wherein the keypoint information includes a descriptor of the keypoint, and the descriptor includes a keypoint determination unit that represents the local structural features of the keypoint in the image, and a parameter determination unit that determines camera parameters based on the keypoint information of the image, wherein the camera parameters include intrinsic and extrinsic camera parameters used to capture the source images, and a data determination unit that determines point cloud data of the first object based on the camera parameters.

[0260] In some embodiments, the keypoint determination unit performs a blurring and downsampling process on each of the multiple images at least once to obtain a Gaussian image set, the Gaussian image set includes a plurality of Gaussian image groups, each Gaussian image group includes Gaussian images with different blurring levels, and for each Gaussian image group, performs a difference process on two adjacent Gaussian images in the Gaussian image group to obtain a difference image group, determines at least one extreme point based on the pixel value change trend of the pixel points in at least one difference image of the difference image group, establishes an extreme point change curve based on the at least one extreme point to determine at least one keypoint of the first object, and determines the keypoint information of the image based on the at least one keypoint and the Gaussian image set.

[0261] In some embodiments, the parameter determination unit includes a keypoint-related subunit that determines at least one keypoint chain based on keypoint information of the plurality of images, wherein the keypoint chain includes a keypoint-related subunit that represents a change in the shooting position of the plurality of images, a parameter estimation subunit that estimates parameters based on the at least one keypoint chain and determines initial parameters, and a parameter optimization subunit that performs joint optimization on the at least one keypoint and the initial parameters to obtain the camera parameters.

[0262] In some embodiments, the keypoint-related subunit performs similarity matching on the keypoint information of a first image and the keypoint information of a second image in each original image group in the source image to obtain at least one pair of matching points, wherein the difference between the shooting angle of the first image and the shooting angle of the second image is less than or equal to a first threshold, noise is removed from the at least one pair of matching points to obtain at least one keypoint group, similarity matching is performed on the keypoint group comprising the source image to determine the at least one keypoint chain, and the keypoint group comprising the source image includes the keypoint group of each original image group.

[0263] In some embodiments, the point cloud data includes the location information and luminosity information of the keypoints, the location information of the keypoints is determined based on the camera parameters and the source image, the luminosity information represents the display form of the keypoints, the data determination unit generates a reconstructed image for a third image from the source images via a scenario reconstruction network based on the third image and the camera parameters, adjusts the parameters of the scenario reconstruction network based on the difference between the reconstructed image and the third image to obtain a trained scenario reconstruction network, generates luminosity information for each of the at least one keypoints based on the location information of the keypoints via the trained scenario reconstruction network, and determines the point cloud data of the first object based on the luminosity information and the location information of the keypoints.

[0264] In some embodiments, the apparatus 1500 further includes a data optimization module, which performs plane fitting based on the point cloud data to recognize background points, which are planar keypoints unrelated to the first object in the three-dimensional space; which performs outlier recognition based on the point cloud data to determine at least one outlier, which is noise due to environmental factors when the first object is photographed; which removes the background points and outlier from the point cloud data to obtain processed point cloud data, which is used to perform three-dimensional reconstruction.

[0265] Here, regarding the apparatus provided in the above embodiment, when realizing its functions, the above-mentioned division of each functional module is simply explained by example. In actual application, depending on the needs, the above functions may be assigned to different functional modules to complete them, that is, by dividing the internal structure of the device into different functional modules, thereby completing all or some of the functions described above. Furthermore, the apparatus embodiment provided in the above embodiment belongs to the same concept as the method embodiment, and its specific implementation process can be found in the method embodiment, which will not be repeated here. The beneficial effects of the apparatus provided in the above embodiment can be found in the description of the method embodiment, which will not be repeated here.

[0266] Figure 16 is a structural block diagram of a computer device provided in one exemplary embodiment of the present application. The 3D navigation vehicle logo creation device 1600 may be the computer device described above.

[0267] Generally, computer equipment 1600 includes a processor 1601 and memory 1602. The processor 1601 includes one or more processing cores, such as a 4-core processor or a 16-core processor. In some embodiments, the processor 1601 may further include an AI (Artificial Intelligence) processor, which handles computing operations related to machine learning. Memory 1602 includes one or more computer-readable storage media, which may be tangible and non-temporary. Memory 1602 may further include high-speed random-access memory and non-volatile memory, such as one or more magnetic disk storage devices and flash storage devices. In some embodiments, at least one program is stored in the non-temporary computer-readable storage media in memory 1602, and this at least one program is read and executed by the processor 1601 to realize the method for creating a 3D navigation vehicle logo provided by each of the above embodiment of the method.

[0268] Embodiments of this application further provide a computer-readable storage medium in which a computer program is stored, and the computer program is read and executed by a processor, thereby realizing the method for creating a 3D navigation vehicle logo provided by each embodiment of the method described above.

[0269] The computer-readable medium includes computer storage media and communication media. The computer storage media includes volatile and non-volatile, removable and fixed media implemented by any method or technique for storing information such as computer-readable instructions, data structures, program modules, or other data.

[0270] Embodiments of this application further provide a computer program product, the computer program product includes a computer program, the computer program is stored in a computer-readable storage medium, and a processor reads the computer program from the computer-readable storage medium and executes it to realize the method for creating a 3D navigation vehicle logo provided by each of the above embodiment of the method.

[0271] Here, “plural” as used herein means two or more. “And / or” describes the relationship between related objects and indicates that three relationships exist; for example, A and / or B indicates three situations: A existing alone, A and B existing simultaneously, and B existing alone. The sign “ / ” generally indicates that the related objects before and after it have an “or” relationship.

[0272] Herein, before collecting relevant user data in this application, and during the process of collecting relevant user data, a prompt interface, a pop-up window, or audio prompt information may be displayed. Such prompt interface, pop-up window, or audio prompt information is used to prompt the user that relevant data is currently being collected. Thus, in this application, the relevant step of acquiring relevant user data will only begin if the user's confirmation action is obtained for such prompt interface or pop-up window. Otherwise (i.e., if the user's confirmation action is not obtained for such prompt interface or pop-up window), the relevant step of acquiring relevant user data will end, i.e., the user's relevant data will not be acquired. In other words, in this application, regarding the collection of source images, obtaining known consent or individual consent from the data subject, in accordance with the requirements of relevant national laws and regulations, will only be done if the user's consent and authorization have been obtained. Subsequent data use and processing activities will be carried out within the scope of laws, regulations, and authorization of the data subject, and the collection, use, and processing of relevant user data must comply with relevant national and regional laws, regulations, and standards.

[0273] The foregoing are merely preferred embodiments of this application and do not limit it. Any completed modifications, equivalent substitutions, improvements, etc., within the spirit and principles of this application should fall within the scope of protection of this application.

Claims

1. A method for creating a 3D navigation vehicle logo executed by a terminal device, wherein the method is: Steps include: displaying a source image of a first object on an image acquisition interface in response to an image acquisition operation, wherein the source image includes images obtained by photographing the first object from different shooting angles, and the first object is a three-dimensional entity object in a real environment; A step of displaying a three-dimensional navigation vehicle logo for the first object, wherein the three-dimensional navigation vehicle logo is obtained by performing a three-dimensional reconstruction of the first object based on the source image, A method comprising the steps of displaying an adjusted three-dimensional navigation vehicle logo in response to an adjustment operation of the display form of the three-dimensional navigation vehicle logo, wherein the adjusted three-dimensional navigation vehicle logo is used for display on a navigation interface.

2. The aforementioned display format includes the orientation of the 3D navigation vehicle logo in the navigation interface, The step of displaying the adjusted 3D navigation vehicle logo in response to an operation to adjust the display form of the 3D navigation vehicle logo is: The steps include: rotating the orientation of the three-dimensional navigation vehicle logo in response to an adjustment operation of the orientation of the three-dimensional navigation vehicle logo; The method according to claim 1, further comprising the step of displaying the adjusted three-dimensional navigation vehicle logo in response to the completion of the adjustment operation of the posture of the three-dimensional navigation vehicle logo.

3. The aforementioned display format includes the surface texture of the 3D navigation vehicle logo, The step of displaying the adjusted 3D navigation vehicle logo in response to an operation to adjust the display form of the 3D navigation vehicle logo is: A step of displaying at least one candidate surface texture, wherein the candidate surface texture is generated based on the original surface texture of the 3D navigation vehicle logo, and the original surface texture reflects the surface material of the first object, The method according to claim 1, comprising the step of displaying a three-dimensional navigation vehicle logo having the first surface texture as the adjusted three-dimensional navigation vehicle logo in response to an operation to select a first surface texture from the at least one candidate surface texture, wherein the adjusted three-dimensional navigation vehicle logo is generated by texture mapping the first surface texture onto the point cloud data of the first object.

4. After the step of displaying the three-dimensional navigation vehicle logo of the first object, A step of displaying a vehicle logo fusion interface in which at least one ornament is displayed, wherein the three-dimensional model of the ornament is pre-installed. Steps include: displaying the first ornament at a first position in a bounding box in response to a selection operation of the first ornament among the at least one ornament, wherein the bounding box is a virtual three-dimensional space surrounding the three-dimensional navigation vehicle logo; The process further includes a step of displaying a merged 3D navigation vehicle logo in response to a vehicle logo fusion termination operation, wherein the merged 3D navigation vehicle logo is obtained by fusion with at least one 3D model contained in the bounding box, The method according to claim 1, wherein the merged three-dimensional navigation vehicle logo is used to be displayed on the navigation interface.

5. The image acquisition interface displays an image acquisition control, and before the step of displaying the source image of the first object in the image acquisition interface, A step in which, in response to a trigger operation of the image acquisition control, the field of view of the camera's acquisition process of the first object is displayed on the image acquisition interface, wherein the field of view corresponds to the image, A step of displaying first prompt information on the upper layer of the field of view screen, wherein the first prompt information is used to prompt the camera to collect the recommended movement trajectory of the first object, The method according to claim 1, further comprising the step of performing the step of displaying the source image of the first object on the image acquisition interface in response to the completion operation of acquiring the source image.

6. Before the step of displaying the three-dimensional navigation vehicle logo of the first object, A step of displaying second prompt information in response to a three-dimensional reconstruction operation of the first object, wherein the second prompt information is used to prompt for the remaining creation time of the three-dimensional navigation vehicle logo, The method according to claim 1, further comprising the step of updating the second prompt information at each of the first time intervals until the creation of the three-dimensional navigation vehicle logo is completed, and displaying the updated second prompt information, if the remaining creation time is greater than the first time interval.

7. This method is The method according to claim 6, further comprising the step of displaying the second prompt information if the amount of data of the source image has reached an upper limit and the three-dimensional reconstruction operation of the first object has not been received.

8. After the step of displaying the source image of the first object in the image acquisition interface in response to the image acquisition operation, A step of displaying identifier information for the three-dimensional navigation vehicle logo in response to an operation to set identifier information, wherein the identifier information is used to uniquely identify the three-dimensional navigation vehicle logo. The method according to claim 1, further comprising the step of displaying the three-dimensional navigation vehicle logo of the first object if the identifier information of the three-dimensional navigation vehicle logo satisfies a naming convention and the source image satisfies a content convention.

9. A method for creating a 3D navigation vehicle logo executed by a computer device, wherein the method is: A step of obtaining a source image relating to a first object, wherein the source image includes images obtained by photographing the first object from different angles, and the first object is a three-dimensional entity object in a real environment. A step of recognizing keypoints in the source image and determining point cloud data of the first object, wherein the point cloud data describes the position and display form of the keypoints of the first object in the actual environment. A step of performing a three-dimensional reconstruction based on the point cloud data to determine the original surface texture of the first object, wherein the original surface texture reflects the surface material of the first object. A method comprising the steps of creating a three-dimensional navigation vehicle logo for the first object by texture mapping the point cloud data based on the surface texture of the first object, wherein the three-dimensional navigation vehicle logo is used for display in a navigation interface.

10. The step of recognizing keypoints in the source image and determining the point cloud data of the first object is: A step of recognizing keypoints in multiple images from the aforementioned source images and determining keypoint information for each of the aforementioned images, wherein the keypoint information includes a descriptor for the keypoint, and the descriptor represents the local structural features of the keypoint in the image. A step of determining camera parameters based on the keypoint information of the aforementioned image, wherein the camera parameters include internal camera parameters and external camera parameters used to capture the source image. The method according to claim 9, comprising the step of determining point cloud data of the first object based on the camera parameters.

11. The step of recognizing keypoints in multiple images from the aforementioned source images and determining keypoint information for each of the aforementioned images is: A step of obtaining a Gaussian image set by performing at least one blurring and downsampling process on each of the aforementioned multiple images, wherein the Gaussian image set includes a plurality of Gaussian image groups, and the Gaussian image groups include Gaussian images having different degrees of blurring. For each of the aforementioned Gaussian image groups, the step of performing a difference operation on two adjacent Gaussian images in the Gaussian image group to obtain a set of difference images, The steps include determining at least one extreme value point based on the trend of pixel value changes of pixel points in at least one difference image of the group of difference images, The steps include establishing an extreme point change curve based on the at least one extreme point and determining at least one key point of the first object, The method according to claim 10, comprising the step of determining keypoint information of the image based on the at least one keypoint and the Gaussian image set.

12. The step of determining camera parameters based on the keypoint information of the aforementioned image is: A step of determining at least one keypoint chain based on the keypoint information of the plurality of images, wherein the keypoint chain represents a change in the shooting position of the plurality of images, The steps include: estimating parameters based on the aforementioned at least one keypoint chain to determine initial parameters; The method according to claim 11, comprising the step of performing joint optimization on the at least one key point and the initial parameters to obtain the camera parameters.

13. The step of determining at least one keypoint chain based on the keypoint information of each image among the aforementioned source images is as follows: For each original image group in the source image, a similarity matching is performed on the keypoint information of the first image and the keypoint information of the second image in the original image group to obtain at least one pair of matching points, wherein the difference between the shooting angle of the first image and the shooting angle of the second image is less than or equal to a first threshold. The steps include removing noise from the aforementioned at least one pair of matching points to obtain at least one keypoint group, The method according to claim 12, comprising the step of performing similarity matching on keypoint groups comprising the source image to determine the at least one keypoint chain, wherein the keypoint groups comprising the source image include keypoint groups of each of the original image groups.

14. The point cloud data includes the position information and luminosity information of the key points, the position information of the key points is determined based on the camera parameters and the source image, and the luminosity information represents the display form of the key points. The step of determining the point cloud data of the first object based on the camera parameters is: The steps include generating a reconstructed image from a third image among the source images, based on the third image and the camera parameters via a scenario reconstruction network, The steps include adjusting the parameters of the scenario reconstruction network based on the difference between the reconstructed image and the third image to obtain the scenario reconstruction network after training, For each of the at least one keypoints, the steps include: predicting based on the location information of the keypoint via the trained scenario reconstruction network to generate luminosity information for the keypoint; The method according to claim 13, comprising the step of determining point cloud data of the first object based on the luminosity information of the key point and the position information of the key point.

15. After the step of recognizing keypoints in the source image and generating point cloud data of the first object, A step of performing plane fitting based on the point cloud data to recognize background points, wherein the background points are planar keypoints in three-dimensional space that are unrelated to the first object. A step of performing outlier recognition based on the point cloud data and determining at least one outlier, wherein the outlier is noise due to environmental factors when the first object is photographed. The process further includes the step of removing the background points and outliers from the point cloud data to obtain processed point cloud data, The method according to claim 9, wherein the point cloud data after processing is used to perform three-dimensional reconstruction.

16. A device for creating a logo for a 3D navigation vehicle, the device is A source acquisition module that displays a source image of a first object on an image acquisition interface in response to an image acquisition operation, wherein the source image includes images obtained by photographing the first object from different shooting angles, and the first object is a three-dimensional entity object in a real environment. A vehicle logo display module that displays a three-dimensional navigation vehicle logo for the first object, wherein the three-dimensional navigation vehicle logo is obtained by performing a three-dimensional reconstruction of the first object based on the source image, A vehicle logo adjustment module that displays an adjusted three-dimensional navigation vehicle logo in response to an adjustment operation of the display form of the three-dimensional navigation vehicle logo, the vehicle logo adjustment module being used to display the adjusted three-dimensional navigation vehicle logo on a navigation interface.

17. A device for creating a logo for a 3D navigation vehicle, the device is A source acquisition module that acquires source images relating to a first object, wherein the source images include images obtained by photographing the first object from different angles, and the first object is a three-dimensional entity object in a real environment. A data determination module that recognizes keypoints in the source image and determines point cloud data of the first object, wherein the point cloud data describes the position and display form of the keypoints of the first object in the actual environment. A three-dimensional reconstruction module that performs three-dimensional reconstruction based on the point cloud data to determine the surface texture of the first object, wherein the surface texture reflects the surface material of the first object. A vehicle logo creation module that creates a three-dimensional navigation vehicle logo for the first object by texture mapping the point cloud data based on the surface texture of the first object, wherein the three-dimensional navigation vehicle logo is used to be displayed on a navigation interface.

18. A computer device comprising a processor and memory, wherein a computer program is stored in the memory, and the computer program is read and executed by the processor, thereby realizing the method for creating a three-dimensional navigation vehicle logo according to any one of claims 1 to 8, or the method for creating a three-dimensional navigation vehicle logo according to any one of claims 9 to 15.

19. A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and the computer program is read and executed by a processor to realize the method for creating a three-dimensional navigation vehicle logo according to any one of claims 1 to 8, or the method for creating a three-dimensional navigation vehicle logo according to any one of claims 9 to 15.

20. A computer program, which, when executed by a processor, causes the processor to implement the method for creating a three-dimensional navigation vehicle logo according to any one of claims 1 to 8, or the method for creating a three-dimensional navigation vehicle logo according to any one of claims 9 to 15.