Three-dimensional navigation vehicle logo creating method and apparatus, device, medium, and program product

Abstract

A three-dimensional navigation vehicle logo creating method and apparatus, a device, and a storage medium, relating to the technical field of map navigation. The present method can be applied to scenarios such as cloud technology, intelligent transportation, and assisted driving. The method comprises: in response to an operation of acquiring images, displaying material images of a first object in an image acquisition interface, wherein the material images include images obtained by photographing the first object from different photographing angles, and the first object is a three-dimensional solid object in a real environment; displaying a three-dimensional navigation vehicle logo of the first object, wherein the three-dimensional navigation vehicle logo is obtained by performing three-dimensional reconstruction on the first object on the basis of the material images; and in response to an operation of adjusting the display style of the three-dimensional navigation vehicle logo, displaying the adjusted three-dimensional navigation vehicle logo, wherein the adjusted three-dimensional navigation vehicle logo is used for being displayed in a navigation interface. The method supports a user to provide a customized object so as to generate a three-dimensional navigation vehicle logo of the customized object, thereby enriching the types of three-dimensional navigation vehicle logos, and reducing the production costs of three-dimensional navigation vehicle logos.

Description

Method, device, equipment, medium and program product for creating three-dimensional navigation vehicle logo

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on November 10, 2023, with application number 2023115027754 and application name “Method, device, equipment and storage medium for creating three-dimensional navigation vehicle logos”, all contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of map navigation technology, and in particular to the creation of three-dimensional navigation vehicle logos. Background Art

[0003] The rise and development of navigation applications have made people's travel activities more convenient. When using navigation applications, in order to help users determine their location in the navigation interface, a positioning point needs to be displayed in the navigation interface.

[0004] To improve the ability to identify positioning points, navigation applications often provide users with a 3D skeleton car logo. This skeleton logo is then displayed as a positioning point within the navigation interface. During the creation process, a staff member uses 3D modeling software to create a dynamic 3D skeleton car logo. Once the 3D skeleton car logo is created, it is uploaded to the navigation application for user use.

[0005] However, the creation cycle of 3D skeleton car logos in related technologies is long, the production process of 3D skeleton car logos requires contact with multiple parties, and the development cost of 3D skeleton car logos is high.

[0006] Summary of the Invention

[0007] This application provides a method, device, equipment, storage medium, and program product for creating a three-dimensional navigation vehicle logo. The technical solution is as follows:

[0008] According to one aspect of an embodiment of the present application, a method for creating a three-dimensional navigation vehicle logo is provided, the method comprising:

[0009] In response to an image acquisition operation, displaying a material image of a first object in an image acquisition interface; wherein the material image includes images of the first object captured from different shooting angles, and the first object is a three-dimensional physical object in a real environment;

[0010] displaying a three-dimensional navigation vehicle logo of the first object, where the three-dimensional navigation vehicle logo is obtained by three-dimensionally reconstructing the first object based on the source image;

[0011] In response to an operation of adjusting the display style of the three-dimensional navigation vehicle logo, the adjusted three-dimensional navigation vehicle logo is displayed, and the adjusted three-dimensional navigation vehicle logo is used to be displayed in a navigation interface.

[0012] According to one aspect of an embodiment of the present application, a method for creating a three-dimensional navigation vehicle logo is provided, the method comprising:

[0013] Acquire a material image of a first object; wherein the material image includes images of the first object photographed from different angles, and the first object is a three-dimensional physical object in a real environment;

[0014] performing key point recognition on the material image to determine point cloud data of the first object, wherein the point cloud data is used to describe the position and display style of the key points of the first object in the real environment;

[0015] Performing three-dimensional reconstruction based on the point cloud data to determine an original surface texture of the first object, where the original surface texture is used to reflect a surface material of the first object;

[0016] Texture mapping is performed on the point cloud data according to the surface texture of the first object to create a three-dimensional navigation logo of the first object, and the three-dimensional navigation logo is used to be displayed in a navigation interface.

[0017] According to one aspect of an embodiment of the present application, a device for creating a three-dimensional navigation vehicle logo is provided, the device comprising:

[0018] a material acquisition module, configured to display a material image of a first object in an image acquisition interface in response to an operation of acquiring an image; wherein the material image includes images of the first object captured from different shooting angles, and the first object is a three-dimensional physical object in a real environment;

[0019] A vehicle logo display module, configured to display a three-dimensional navigation vehicle logo of the first object, the three-dimensional navigation vehicle logo being obtained by three-dimensionally reconstructing the first object based on the source image;

[0020] The vehicle logo adjustment module is used to display the adjusted three-dimensional navigation vehicle logo in response to an operation of adjusting the display style of the three-dimensional navigation vehicle logo, and the adjusted three-dimensional navigation vehicle logo is used to be displayed in the navigation interface.

[0021] According to one aspect of an embodiment of the present application, a device for creating a three-dimensional navigation vehicle logo is provided, the device comprising:

[0022] A material acquisition module, configured to acquire material images of a first object; wherein the material images include images of the first object captured from different angles, and the first object is a three-dimensional physical object in a real environment;

[0023] a data determination module, configured to perform key point recognition on the material image to determine point cloud data of the first object, wherein the point cloud data is used to describe the position and display style of the key points of the first object in the real environment;

[0024] a three-dimensional reconstruction module, configured to perform three-dimensional reconstruction based on the point cloud data and determine an original surface texture of the first object, wherein the original surface texture is used to reflect a surface material of the first object;

[0025] The vehicle logo creation module is used to perform texture mapping on the point cloud data according to the surface texture of the first object to create a three-dimensional navigation vehicle logo of the first object, and the three-dimensional navigation vehicle logo is used to be displayed in the navigation interface.

[0026] According to one aspect of an embodiment of the present application, a computer device is provided, which includes a processor and a memory, wherein a computer program is stored in the memory, and the computer program is loaded and executed by the processor to implement the method for creating a three-dimensional navigation vehicle logo as described above.

[0027] According to one aspect of an embodiment of the present application, a computer-readable storage medium is provided, in which a computer program is stored. The computer program is loaded and executed by a processor to implement the method for creating a three-dimensional navigation vehicle logo as described above.

[0028] According to one aspect of an embodiment of the present application, a computer program product is provided, which includes a computer program stored in a computer-readable storage medium. A processor reads and executes the computer program from the computer-readable storage medium to implement the method for creating a three-dimensional navigation vehicle logo as described above.

[0029] The beneficial effects of the technical solutions provided in the embodiments of the present application include at least:

[0030] Compared to the 3D skeleton logos generated in related technologies, this system generates and displays a 3D navigation logo by 3D reconstruction of the user-uploaded material image of the photographed object. This allows users to customize the 3D navigation logo displayed in the navigation interface, meeting their demand for customizable 3D navigation logos and enriching the variety of 3D navigation logos.

[0031] On the other hand, automatically generating static three-dimensional navigation logos can help reduce the production cost of three-dimensional navigation logos, shorten the generation cycle of three-dimensional navigation logos, make it more convenient and quick to obtain three-dimensional navigation logos, and help meet the update and iteration needs of three-dimensional navigation logos. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] FIG1 is a schematic diagram of an implementation environment of a solution provided by an exemplary embodiment of the present application;

[0033] FIG2 is a schematic diagram of the inventive concept of an embodiment of the present application;

[0034] FIG3 is a flow chart of a method for creating a three-dimensional navigation vehicle logo provided by an exemplary embodiment of the present application;

[0035] FIG4 is a schematic diagram of first prompt information provided by an exemplary embodiment of the present application;

[0036] FIG5 is a schematic diagram of uploading a material image provided by an exemplary embodiment of the present application;

[0037] FIG6 is a schematic diagram of second prompt information provided by an exemplary embodiment of the present application;

[0038] FIG7 is a schematic diagram of obtaining identification information provided by an exemplary embodiment of the present application;

[0039] FIG8 is a schematic diagram of an azimuth adjustment process provided by an exemplary embodiment of the present application;

[0040] FIG9 is a schematic diagram before entering the image acquisition interface provided by an exemplary embodiment of the present application;

[0041] FIG10 is a schematic diagram of a navigation interface provided by an exemplary embodiment of the present application;

[0042] FIG11 is a schematic diagram of a three-dimensional navigation vehicle logo display effect provided by an exemplary embodiment of the present application;

[0043] FIG12 is an interactive diagram of a vehicle logo application process provided by an exemplary embodiment of the present application;

[0044] FIG13 is a flowchart of a method for creating a three-dimensional navigation vehicle logo provided by another exemplary embodiment of the present application;

[0045] FIG14 is a block diagram of a device for creating a three-dimensional navigation vehicle logo provided by an exemplary embodiment of the present application;

[0046] FIG15 is a block diagram of a device for creating a three-dimensional navigation vehicle logo provided by another exemplary embodiment of the present application;

[0047] FIG16 is a structural block diagram of a computer device provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0048] In order to make the objectives, technical solutions and advantages of this application clearer, the implementation methods of this application will be further described in detail below with reference to the accompanying drawings.

[0049] Mid-trip scenario: This refers to the scenario that users enter after starting the navigation process using the navigation application. In other words, the mid-trip scenario is the application scenario from the beginning of the navigation application navigating the user to the completion of the navigation.

[0050] A 3D (three-dimensional) model is a representation of an object in 3D polygons. A 3D model of an object is used to recreate the object's appearance in a real environment to a certain extent. The "object" mentioned here can correspond to the object in a claim. The object can be real-world or fictional. 3D models are typically generated using 3D modeling tools.

[0051] 3D (Three Dimensional) navigation logo: Used to display the user's location on the navigation interface. When the user sets the starting and ending points in the navigation app and initiates navigation, a location dot appears on the navigation interface, indicating the user's location on the map. To make the location dot more vivid and enhance the navigation interface, a 3D navigation logo can be used to replace the location dot on the navigation interface. The 3D navigation logo is a 3D model.

[0052] OBJ (Object) files are a standard 3D model file format used for model exchange between 3D software. For example, after creating a 3D model in 3dsMax or LightWave, you can export the OBJ file and then import it into Maya for rendering or animation.

[0053] FIG1 is a schematic diagram of an implementation environment of a solution provided by an exemplary embodiment of the present application, which may include: a terminal device 10 , a server 20 , and a computer device 30 .

[0054] The terminal device 10 can be an electronic device such as a computer, tablet computer, mobile phone, wearable device, smart home appliance, vehicle-mounted terminal, aircraft, etc. A client of a target application runs on the terminal device 10. The target application can be a standalone application or a sub-application within a parent application. The target application is used to provide the function of creating a three-dimensional vehicle logo.

[0055] Exemplarily, the target application is a 3D model creation application. After a user creates a 3D navigation logo in the target application, the user imports the 3D navigation logo into the navigation application. The navigation application then displays the 3D navigation logo when navigating the user. Exemplarily, the target application is a navigation application that provides the ability to create a 3D navigation logo.

[0056] Optionally, the terminal device 10 is provided with a camera, or an image transmission path exists between the terminal device 10 and the camera. The terminal device 10 obtains a material image of the photographed object through the camera, and starts the process of creating the 3D navigation vehicle logo by transmitting the material image to the server, so as to obtain the 3D navigation vehicle logo.

[0057] The server 20 is used to provide background services for the client of the target application in the terminal device 10. For example, the server 20 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms, but is not limited to these. The server 20 has at least a data receiving function.

[0058] Computer devices 30 include but are not limited to mobile phones, desktop computers, tablet computers, laptops, vehicle-mounted terminals, servers, intelligent robots, smart TVs, multimedia playback devices and other electronic devices, or other electronic devices with strong computing capabilities, which are not limited in this application.

[0059] In the solution for creating a 3D navigation vehicle logo provided in this application, the computer device 30 performs the algorithm-side calculations, that is, the computer device 30 performs 3D reconstruction based on the source image to create a 3D navigation vehicle logo.

[0060] The computer device 30 can create a 3D navigation logo through the server 20 (i.e., the computer device 30 and the server 20 are the same device). Alternatively, the computer device 30 and the server 20 are two independent devices. After the computer device 30 creates the 3D navigation logo, it sends the 3D navigation logo to the server 20, which then feeds the 3D navigation logo back to the terminal device 10.

[0061] In one example, after receiving a source image uploaded by the terminal device 10 via a target application, the server 20 transmits the source image to the computer device 30. The computer device 30 performs 3D reconstruction based on the source image to determine a 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.

[0062] In another example, the computer device 30 obtains a material image through a network and creates a three-dimensional navigation vehicle logo based on the material image. The computer device 30 then stores the three-dimensional navigation vehicle logo or sends the three-dimensional navigation vehicle logo to the server 20.

[0063] In another example, the terminal device 10 directly sends the material image to the computer device 30 through the target application; after the computer device 30 generates a three-dimensional navigation vehicle logo based on the material image, it feeds the three-dimensional navigation vehicle logo back to the terminal device 10.

[0064] FIG2 is a schematic diagram of the inventive concept of an embodiment of the present application.

[0065] In the embodiments provided herein, a terminal device captures source images, enabling users to capture source images of the subject as needed. Subsequently, the terminal device transmits the source images to a computer for 3D reconstruction, resulting in a 3D navigation logo. During navigation using a navigation application on the terminal device, the 3D navigation logo can be displayed within the navigation interface. This approach reduces the cost of generating the 3D navigation logo and facilitates its creation on mobile devices.

[0066] Figure 3 is a flowchart of a method for creating a three-dimensional navigation vehicle logo, provided by an exemplary embodiment of the present application. For example, the method can be executed by the terminal device 10 in Figure 1 . Below, the method for creating a three-dimensional navigation vehicle logo will be described using the terminal device as the execution entity. As shown in Figure 3 , the method can include the following steps ( 310 - 330 ).

[0067] Step 310 : In response to the image acquisition operation, displaying a material image of the first object in the image acquisition interface; wherein the material image includes images of the first object captured from different shooting angles, and the first object is a three-dimensional physical object in a real environment.

[0068] In some embodiments, the first object refers to any three-dimensional physical object in a real environment. For example, the first object can be an object, person, building, etc. in a real environment. The first object can be user-defined. If the user needs to create a three-dimensional navigation vehicle logo corresponding to a certain object, the object is used as the first object, and the terminal device captures the material image of the first object. The first object can also be referred to as the photographed object.

[0069] In some embodiments, the material image is used to represent the form of the first object in a real environment. The type of the material image includes, but is not limited to, at least one of the following: a video, or a group of images. For example, if the material image is a video, the image included in the material image is a video frame in the video. For another example, if the material image is a group of images, the image included in the material image is any image in the group of images.

[0070] Optionally, the material image includes multiple images, each of which is captured from the first object. Exemplarily, the multiple images capture at least one of the following: the front, side, back, or top of the first object. The multiple images capture the first object from different angles. The shooting angles include at least one of the following: shooting height, shooting direction, and shooting distance.

[0071] The image capture interface is used to display a source image of a first object. In some embodiments, the image capture operation is used to obtain the source image. The image capture operation includes, but is not limited to, at least one of the following: a click operation, a key operation, a slide operation, and a long press operation. Exemplarily, an image capture control is displayed in the image capture interface, and the terminal device displays the source image in the image capture interface in response to the operation triggering the image capture control.

[0072] Exemplarily, the source of the material image of the first object includes, but is not limited to, at least one of the following: downloading from the internet, storing in a local database of the terminal device, and real-time acquisition by the terminal device. For example, the terminal device uses a camera in an image acquisition interface to photograph or record the first object in real time to obtain the material image of the first object. For example, the terminal device stores a generated image of the first object in a multimedia database, and when generating a 3D navigation vehicle logo, the terminal device uploads the material image of the first object in the image acquisition interface.

[0073] Step 320 : Displaying a three-dimensional navigation vehicle logo of the first object. The three-dimensional navigation vehicle logo is obtained by three-dimensionally reconstructing the first object based on the source image.

[0074] In some embodiments, the three-dimensional navigation logo of the first object refers to a 3D model with a similar spatial structure to the first object. The three-dimensional navigation logo of the first object is used to be displayed in the navigation interface as a positioning point during the navigation process. Optionally, during the navigation process, the display position and posture of the three-dimensional navigation logo on the navigation interface are related to the position and posture of the terminal device in the real environment. The three-dimensional navigation logo is displayed on the navigation interface to help users locate their current position on the navigation interface. By allowing users to customize and upload material images, users can be guaranteed to obtain personalized three-dimensional navigation logos.

[0075] Optionally, the 3D navigation logo is a static 3D model, meaning its shape and structure do not change during use. Generating a static 3D model of the 3D navigation logo not only improves the efficiency of the 3D navigation logo, but also reduces the display overhead of the 3D navigation logo in the navigation interface, thereby reducing power consumption of the terminal device.

[0076] In some embodiments, after the source image of the first object is displayed in the image acquisition interface, the process of creating the 3D navigation vehicle logo begins. Exemplarily, the terminal device begins creating the 3D navigation vehicle logo for the first object in response to the 3D reconstruction operation of the first object. Exemplarily, if the source image meets the creation conditions, the terminal device begins creating the 3D navigation vehicle logo for the first object.

[0077] Optionally, the process of creating a three-dimensional navigation logo is completed by a terminal device, or by a background device of the target application, which background device includes a computer device in the implementation environment described above. For example, after acquiring the material image of the first object, the terminal device sends the material image of the first object to the computer device, and the computer device creates a three-dimensional navigation logo of the first object based on the material image of the first object, and feeds back the three-dimensional navigation logo of the first object to the terminal device; then, the terminal device displays the three-dimensional navigation logo of the first object. Since the process of creating a three-dimensional navigation logo of the first object requires relatively high computing performance, creating a three-dimensional navigation logo of the first object through a background device in the target application helps to shorten the time of the creation process.

[0078] Step 330 : In response to the operation of adjusting the display style of the 3D navigation vehicle logo, the adjusted 3D navigation vehicle logo is displayed. The adjusted 3D navigation vehicle logo is used to be displayed in the navigation interface.

[0079] In some embodiments, the display style of the 3D navigation logo is used to control the display effect of the 3D navigation logo. Optionally, the display style of the 3D navigation logo includes at least one of the following: the surface texture of the 3D navigation logo, the display size of the 3D navigation logo, and the display orientation of the 3D navigation logo. The surface texture of the 3D navigation logo includes but is not limited to the display color, surface material, pattern, etc. of the 3D navigation logo. The display size of the 3D navigation logo refers to the size occupied by the 3D navigation logo. The display orientation of the 3D navigation logo is also called the orientation of the 3D navigation logo, which is used to represent the orientation of the 3D navigation logo.

[0080] Because the display style of the first object in the real environment may not fully meet the user's preferences, by adjusting the display style of the 3D navigation logo, the adjusted 3D navigation logo can be made more in line with the user's needs, facilitating the implementation of a customized 3D navigation logo. Furthermore, this method reduces the requirements for the source image by adjusting the display style of the 3D navigation logo later, thus simplifying the acquisition of source images.

[0081] Optionally, the operation of adjusting the display style of the 3D navigation logo includes but is not limited to at least one of the following: a click operation, a key operation, a slide operation, and a long press operation, etc. For details on adjusting the display style of the 3D navigation logo, please refer to the following embodiments.

[0082] In some embodiments, after adjusting the display style of the 3D navigation car logo, the terminal device saves the adjusted 3D navigation car logo. When the terminal device uses the navigation application to navigate, the terminal device displays the adjusted 3D navigation car logo in the navigation interface.

[0083] In one example, a first user account is logged into a target application on a terminal device. The first user account owns multiple three-dimensional navigation logos, and a server stores the ownership relationship between the first user account and the multiple navigation logos. In response to an operation to adjust the display style of a first navigation logo among the multiple three-dimensional navigation logos, the terminal device displays the adjusted first navigation logo and sends logo update information to the server. The server generates the adjusted first navigation logo based on the logo update information and establishes an ownership relationship between the first user account and the adjusted first navigation logo.

[0084] In summary, compared to the related art of generating 3D skeleton logos, this method generates and displays a 3D navigation logo by 3D reconstruction of the user-uploaded material image of the photographed object. This allows users to customize the 3D navigation logo displayed in the navigation interface, meeting their demand for customizable 3D navigation logos and enriching the variety of 3D navigation logos.

[0085] On the other hand, automatically generating static three-dimensional navigation logos can help reduce the production cost of three-dimensional navigation logos, shorten the generation cycle of three-dimensional navigation logos, make it more convenient and quick to obtain three-dimensional navigation logos, and help meet the update and iteration needs of three-dimensional navigation logos.

[0086] In some embodiments, an image acquisition control is displayed in the image acquisition interface; before the terminal device displays the material image of the first object in the image acquisition interface, it also includes: step 305 (not shown in the accompanying drawings), the terminal device responds to the operation of triggering the image acquisition control, and displays the field of view picture of the camera capturing the first object in the image acquisition interface, and the field of view picture corresponds to the image; the terminal device displays first prompt information on the upper layer of the field of view picture, and the first prompt information is used to prompt the camera to capture the recommended movement trajectory of the first object; the terminal device responds to the operation of completing the acquisition of the material image, and starts executing from the step of displaying the material image of the first object in the image acquisition interface.

[0087] Optionally, the source image is a video of the first object. During the recording of the video of the first object, the camera orbits around the first object and continuously captures the first object's shape from different shooting angles. Exemplarily, the video of the first object is recorded in real time in the image capture interface.

[0088] Optionally, the field of view image refers to a camera field of view image displayed in the terminal device during the process of photographing the first object. After the photographing is completed, the field of view image is the image included in the material image.

[0089] The image acquisition control is used to acquire a material image of the first object in real time. Optionally, operations that trigger the image acquisition control include but are not limited to: click operations, sliding operations, gesture operations, and key operations.

[0090] In some embodiments, the terminal device calls a camera component in response to triggering the operation of the image acquisition control, and the camera component is used to control the camera to capture the material image of the first object; the image acquisition control displays the field of view of the camera during the process of capturing the first object.

[0091] To ensure that the material image captured by the user contains details related to the first object's form, the multiple images included in the material image continuously change in shooting angle. While the camera is capturing the material image of the first object, the terminal device displays first prompt information on top of the field of view. Optionally, the first prompt information includes at least one of the following: a recommended movement trajectory of the first object captured by the camera, and a recommended position of the first object in the field of view.

[0092] Exemplarily, the recommended movement trajectory includes at least one of the following: photographing the first object 360 degrees clockwise, or photographing the first object 360 degrees counterclockwise. Exemplarily, the recommended position in the field of view belongs to the center area of ​​the field of view.

[0093] By displaying the first prompt information, the user is instructed to shoot the first object according to the recommended movement trajectory, and the first object is located at the recommended position in the field of view image.

[0094] Exemplarily, the type of the first prompt message includes, but is not limited to, at least one of the following: text, icon, and animation. For example, the first prompt message includes the text message "Please perform a 360° shot around the first object." In one example, the first prompt message is played in a loop through a page animation, prompting the user to rotate the object 360° to ensure the content integrity of the source image.

[0095] FIG4 is a schematic diagram of first prompt information provided by an exemplary embodiment of the present application.

[0096] As shown in FIG. 4 , the first prompt information 410 includes a cube animation information that continuously rotates horizontally, which is used to prompt the user to perform 360° shooting of the first object.

[0097] After completing the acquisition of the material image, the terminal device displays the material image in the image acquisition interface and uploads the material image to obtain the three-dimensional navigation vehicle logo of the first object created by the computer device.

[0098] FIG5 is a schematic diagram of uploading a material image provided by an exemplary embodiment of the present application.

[0099] As shown in FIG5 , after the terminal device completes collecting the material image, it uploads the material image.

[0100] In some embodiments, a capture completion control 510 is displayed in the image capture interface, and the operation of completing the capture of the material image refers to triggering the capture completion control 510 operation, such as clicking the capture completion control.

[0101] Optionally, the acquisition completion control and the image acquisition control are displayed in the same position in the image acquisition interface. After the terminal device displays a field of view of the camera acquiring the first object in the image acquisition interface in response to the operation triggering the image acquisition control, the terminal device displays the acquisition completion control in the position where the image acquisition control was displayed and removes the image acquisition control.

[0102] Acquiring the material image of the first object through real-time shooting and displaying prompt information in the field of view helps to ensure that the material image records the shooting direction of the photographed object, helps to improve the precision of the three-dimensional navigation vehicle logo generated based on the material image, and makes the three-dimensional navigation vehicle logo closer to the photographed object.

[0103] The following describes the process of uploading material images by a terminal device through several embodiments.

[0104] In some embodiments, before the terminal device displays the three-dimensional navigation logo of the first object, it also includes: step 313 (not shown in the accompanying drawings), the terminal device displays a second prompt message in response to the operation of three-dimensionally reconstructing the first object; wherein the second prompt message is used to prompt the remaining creation time of the three-dimensional navigation logo; if the remaining creation time is greater than the first time interval, the terminal device updates the second prompt message every first time interval, and displays the updated second prompt message until the three-dimensional navigation logo is created.

[0105] In some embodiments, the operation of 3D reconstructing the first object is used to control the terminal device to upload the material image of the first object. That is, the terminal device starts the process of creating a 3D navigation vehicle logo through the operation of 3D reconstructing the first object.

[0106] Optionally, the remaining creation time is used to represent the time required to wait before obtaining the three-dimensional navigation vehicle logo. The first time interval is preset, for example, the first time interval is equal to 30 seconds.

[0107] FIG6 is a schematic diagram of second prompt information provided by an exemplary embodiment of the present application. The display effect of the second prompt information is shown in 610 .

[0108] Optionally, in response to the operation of three-dimensionally reconstructing the first object, the terminal device sends a material 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 duration of the second prompt information. If the display duration of the second prompt information is equal to the first time interval, the terminal device obtains the updated second prompt information from the computer device; the terminal device displays the updated second prompt information and restarts the display duration of the second prompt information; the terminal device restarts from the step of "If the display duration of the second prompt information is equal to the first time interval, the terminal device obtains the updated second prompt information from the computer device for execution" until the computer device completes the creation of the three-dimensional navigation vehicle logo.

[0109] By polling, the remaining creation time is updated at regular intervals, which can provide users with relatively accurate remaining creation time and avoid the communication overhead caused by frequent updates of the remaining creation time.

[0110] Generating a 3D navigation model based on source images requires extensive computation, and computing power is limited. To avoid excessively large source images, which could result in the 3D navigation logo not being properly generated, a method is provided below for automatically triggering the creation of a 3D navigation logo using a terminal device, in addition to initiating the creation of a 3D navigation logo by the user performing a 3D reconstruction of the first object.

[0111] In some embodiments, the method for creating a three-dimensional navigation vehicle logo also includes: step 316 (not shown in the accompanying drawings), when the data volume of the material image reaches the upper limit value and no operation of three-dimensionally reconstructing the first object is received, the terminal device displays a second prompt message.

[0112] Optionally, the data volume of a material image measures the total number of images included in the material image. The greater the total number of images included in the material image, the greater the data volume of the material image; the smaller the total number of images included in the material image, the smaller the data volume of the material image. Optionally, the data volume upper limit refers to the maximum data volume that the material image can have. The data volume upper limit may be pre-set, such as 600 images.

[0113] 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 can be determined by the video duration. In this case, the data size upper limit refers to the maximum recording duration of the video. For example, the data size upper limit is 60 seconds.

[0114] Exemplarily, a fourth prompt is also displayed in the image capture interface, indicating the maximum remaining recording time of the video. If the maximum remaining recording time of the video is 0, indicating that the data volume of the material image has reached the upper limit, the terminal device sends the material image to the computer device and displays the second prompt.

[0115] Limiting the number of images included in the material image by using the upper limit of the data volume helps to reduce the computing pressure in the process of generating the three-dimensional navigation vehicle logo and shortens the waiting time for obtaining the three-dimensional navigation vehicle logo.

[0116] In some embodiments, after the terminal device displays the material image of the first object in the image acquisition interface in response to the operation of capturing an image, the method further includes: the terminal device displays the identification information of the three-dimensional navigation vehicle logo in response to the operation of setting identification information, and the identification information is used to uniquely identify the three-dimensional navigation vehicle logo; the terminal device executes the step of displaying the three-dimensional navigation vehicle logo of the first object when the identification information of the three-dimensional navigation vehicle logo complies with the naming rules and the material image complies with the content rules.

[0117] In some embodiments, the identification information of the 3D navigation vehicle logo includes, but is not limited to, the name and number of the 3D navigation vehicle logo. Optionally, the identification information of the 3D navigation vehicle logo can be user-defined. For example, in response to an operation of 3D reconstructing a first object, the terminal device sends a source image to the computer device and displays an identification input interface, wherein a name input control is displayed in the identification input interface. The operation of setting the identification information is an input operation for the name input control, and the terminal device obtains the identification information of the 3D navigation vehicle logo through the operation of setting the identification information.

[0118] Fig. 7 is a schematic diagram of obtaining identification information provided by an exemplary embodiment of the present application. As shown in Fig. 7 , a name input control 710 is displayed in an identification input interface 700 .

[0119] Optionally, after obtaining the identification information of the 3D navigation vehicle logo, the terminal device transmits the identification information to a server; the server performs a validity check on the identification information of the 3D navigation vehicle logo. If the identification information of the 3D navigation vehicle logo fails the validity check, the terminal device displays a fifth prompt message; the fifth prompt message prompts the user to re-enter the identification information of the 3D navigation vehicle logo. If the identification information of the 3D navigation vehicle logo passes the validity check, the terminal device displays a second prompt message.

[0120] By performing compliance checks on identification information and material images, abnormalities in the generated three-dimensional navigation logo and inappropriate naming and display can be avoided, thereby improving the generation accuracy and efficiency of the three-dimensional navigation logo.

[0121] The following describes the process of adjusting the display style of a 3D navigation logo through several examples. As can be seen from the above examples, the display style of a 3D navigation logo includes at least one of the following: the logo's surface texture, the logo's display size, and the logo's display orientation. After creating the 3D navigation logo, the user can choose whether to adjust the logo's display style based on actual needs. The following display adjustment examples can be implemented individually or combined freely.

[0122] Example 1: Adjust the position of the 3D navigation vehicle logo in the navigation interface.

[0123] In some embodiments, the display style includes: the position of the three-dimensional navigation vehicle logo in the navigation interface; step 330 can be implemented as the following steps.

[0124] In sub-step 331 - a , the terminal device rotates the orientation of the three-dimensional navigation vehicle logo in response to the operation of adjusting the posture of the three-dimensional navigation vehicle logo.

[0125] In some embodiments, the orientation of the 3D navigation vehicle logo in the navigation interface refers to the direction of the 3D navigation vehicle logo in the navigation interface. The orientation of the 3D navigation vehicle logo in the navigation interface can be understood as the main view direction of the 3D navigation vehicle logo.

[0126] In some embodiments, the operation of adjusting the posture of the 3D navigation logo is used to adjust the azimuth of the 3D navigation logo. By adjusting the azimuth of the 3D navigation logo, the orientation of the 3D navigation logo in the navigation interface is rotated. Operations for adjusting the posture of the 3D navigation logo include, but are not limited to, sliding, keystrokes, gestures, and voice commands.

[0127] Optionally, the operation for adjusting the posture of the 3D navigation vehicle logo is a sliding operation, and the terminal device responds to the operation for adjusting the posture of the 3D navigation vehicle logo by controlling the 3D navigation vehicle logo to rotate in a target rotation direction, thereby changing the orientation of the 3D navigation vehicle logo. The target rotation direction is the rotation corresponding to the sliding operation.

[0128] Exemplarily, the target rotation direction is related to the direction of the sliding operation. For example, the target rotation direction corresponding to the sliding operation in the up-down direction is used to adjust the pitch angle of the 3D navigation vehicle logo. The target rotation direction corresponding to the sliding operation in the left-right direction is used to adjust the yaw angle of the 3D navigation vehicle logo.

[0129] Exemplarily, the target rotation direction is related to the area where the sliding operation occurs. For example, a sliding operation in the upper 1 / 3 of the terminal device corresponds to a target rotation direction for adjusting the pitch angle of the 3D navigation vehicle logo; a sliding operation in the middle 1 / 3 of the terminal device corresponds to a target rotation direction for adjusting the yaw angle of the 3D navigation vehicle logo.

[0130] It should be noted that the specific implementation method of the operation of adjusting the posture of the three-dimensional navigation vehicle logo is set according to actual needs and is not limited in this application.

[0131] In some embodiments, after receiving an operation to adjust the posture of the three-dimensional navigation vehicle logo, the terminal device determines the target rotation direction; the terminal device rotates the three-dimensional navigation vehicle logo in response to the operation to adjust the posture of the three-dimensional navigation vehicle logo, so that the orientation of the three-dimensional navigation vehicle logo continues to change.

[0132] In sub-step 331 - b , in response to the completion of the operation of adjusting the posture of the three-dimensional navigation vehicle logo, the terminal device displays the adjusted three-dimensional navigation vehicle logo.

[0133] Optionally, the operation of ending the adjustment of the three-dimensional navigation vehicle logo posture includes but is not limited to at least one of the following: a sliding operation, a key operation, a gesture operation, and a voice operation.

[0134] For example, if the operation to adjust the posture of the 3D navigation vehicle logo is a sliding operation, the operation to end the adjustment of the posture of the 3D navigation vehicle logo may be when the sliding signal disappears. That is, the terminal device rotates the 3D navigation vehicle logo in response to the sliding signal of the sliding operation; when the sliding operation disappears, the terminal device displays the adjusted 3D navigation vehicle logo.

[0135] Fig. 8 is a schematic diagram of an orientation adjustment process provided by an exemplary embodiment of the present application. In the orientation adjustment interface 800, the orientation of the three-dimensional navigation vehicle logo can be adjusted.

[0136] Because the 3D navigation logo has a three-dimensional structure, the display effect of the 3D navigation logo in different orientations varies. By providing the ability to adjust the orientation of the 3D navigation logo, the display effect of the 3D navigation logo in the navigation interface is enriched, helping to meet user needs for navigation logos. This reduces the number of navigation logo creation times, helps reduce the number of 3D navigation logos that need to be maintained by the server, and reduces the server's data storage pressure.

[0137] Example 2: Adjust the surface texture of a 3D navigation car logo.

[0138] In some embodiments, the display style includes: the surface texture of the three-dimensional navigation vehicle logo; step 330 can be implemented as the following steps.

[0139] In sub-step 333 - a , the terminal device displays at least one candidate surface texture, where the candidate surface texture is generated based on the original surface texture of the three-dimensional navigation vehicle logo, and the original surface texture is used to reflect the surface material of the first object.

[0140] In some embodiments, the original surface texture is a surface texture determined based on the 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 is related to factors such as the surface material of the first object and the ambient light when the source image was captured.

[0141] The above-mentioned original surface texture and candidate surface textures are both types of surface textures. A surface texture can be understood as a triangular mesh, where each triangle in the triangular mesh corresponds to a local area on the surface of the first object. The display effect (e.g., color, reflective effect, pattern, etc.) of the triangle determines the display effect of the local area corresponding to the triangle on the surface of the first object. For example, a computer device can use the original surface texture to render point cloud data of the first object to generate a three-dimensional navigation vehicle logo.

[0142] The candidate surface texture is generated based on the original surface texture. Optionally, the triangular mesh corresponding to the candidate surface texture has the same morphology as the triangular mesh corresponding to the original surface texture. That is, for a 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 first triangle and the second triangle have the same shape, but the display effect of the first triangle is different from the display effect of the second triangle.

[0143] In one example, the terminal device displays a three-dimensional navigation logo and at least one candidate surface texture of the first object in the style adjustment interface.

[0144] In sub-step 333-b, the terminal device displays a three-dimensional navigation logo with the first surface texture as an adjusted three-dimensional navigation logo in response to the operation of selecting the first surface texture from at least one candidate surface texture; the adjusted three-dimensional navigation logo is generated by texture mapping the point cloud data of the first object based on the first surface texture.

[0145] Optionally, the operation of selecting the first surface texture from the at least one candidate surface texture is a click operation, a sliding operation, etc. on the first surface texture. For example, the operation of selecting the first surface texture from the at least one candidate surface texture is a click operation, and the terminal device displays the adjusted three-dimensional navigation vehicle logo in response to the click operation on the first surface texture.

[0146] Exemplarily, the adjusted three-dimensional navigation logo is generated by a computer device. After the terminal device obtains the operation of selecting the first surface texture, it sends a texture adjustment request to the computer device; the computer device generates and sends the adjusted three-dimensional navigation logo to the terminal device based on the texture adjustment request.

[0147] The texture adjustment request includes at least one of the following: an account identifier, a vehicle logo identifier, and a first texture identifier, wherein the account identifier is used to represent the first user account logged in to the terminal device, the vehicle logo identifier is used to indicate the three-dimensional navigation vehicle logo of the first object, and the first texture identifier is used to indicate the first surface texture.

[0148] Optionally, the computer device sends the adjusted 3D navigation vehicle logo to the server, and the server updates the 3D navigation vehicle logo owned by the first user account, and the server sends the 3D navigation vehicle logo to the terminal device.

[0149] The 3D navigation logo, generated through 3D reconstruction based on source images, has limited surface texture due to the actual material of the object being photographed. By adjusting the surface texture of the 3D navigation logo and generating a modified 3D navigation logo, the texture display effect of the 3D navigation logo is enriched.

[0150] Example 3: Adjust the display size of the 3D navigation car logo.

[0151] In some embodiments, the display style includes: the display size of the three-dimensional navigation vehicle logo in the navigation interface; step 330 can be implemented as the following sub-steps.

[0152] In sub-step 335 - a , the terminal device scales the display size of the three-dimensional navigation vehicle logo in response to the display size adjustment operation.

[0153] In some embodiments, the operation of adjusting the display size includes but is not limited to: a sliding operation, a key operation, a clicking operation, etc.

[0154] For example, the operation for adjusting the display size is to place two fingers in contact with the terminal device and slide the fingers so that the linear distance between the two fingers changes. If the linear distance between the two fingers increases, the terminal device enlarges the 3D navigation vehicle logo; if the linear distance between the two fingers decreases, the terminal device shrinks the 3D navigation vehicle logo.

[0155] In sub-step 335 - b , the terminal device displays the adjusted three-dimensional navigation vehicle logo in response to the completion of the operation of adjusting the display size.

[0156] Since the size of the user-selected subject varies, adjusting the display size of the 3D navigation logo can help reduce its impact on the navigation interface. While still providing a clear indication of the 3D navigation logo's position, it also helps prevent it from obscuring other navigation information on the navigation interface.

[0157] The following describes the post-processing process of the three-dimensional navigation vehicle logo through several embodiments.

[0158] In some embodiments, after the terminal device displays the three-dimensional navigation logo of the first object, it also includes: the terminal device displays a logo fusion interface, in which at least one decoration is displayed, and the three-dimensional model of the decoration is pre-set; the terminal device responds to the operation of selecting the first decoration among the at least one decoration, and displays the first decoration at the first position in the bounding box, and the bounding box refers to the virtual three-dimensional space surrounding the three-dimensional navigation logo; the terminal device responds to the operation of ending the logo fusion, and displays the fused three-dimensional navigation logo, and the fused three-dimensional navigation logo is obtained by fusing at least one three-dimensional model included in the bounding box; wherein the fused three-dimensional navigation logo is used to be displayed in the navigation interface.

[0159] In some embodiments, the vehicle logo fusion interface is used to integrate a 3D navigation vehicle logo with a decorative object. Optionally, the decorative object has a 3D structure, and the 3D model of the decorative object is known. Exemplarily, the 3D model of the decorative object is a dynamic 3D model, meaning that the display style of the decorative object changes.

[0160] Optionally, the type of decorative object includes, but is not limited to, at least one of the following: plants, animals, virtual vehicles, clothing, etc. Exemplarily, the type of decorative object 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, the at least one decorative object displayed in the vehicle logo fusion interface may include: a virtual vehicle, clothing, etc. For another example, if the first object is a stationary object, the at least one decorative object displayed in the vehicle logo fusion interface may include: a plant, an animal, etc.

[0161] After the computer device acquires the source image, it uses a category recognition model to identify the image within the source image and determine the type of the first object. After creating the three-dimensional navigation vehicle logo for the first object, the computer device sends the three-dimensional navigation vehicle logo and the type of the first object to a server. Based on the type of the first object, the server determines at least one decorative object. After the terminal device enters the vehicle logo fusion interface, the server sends decorative object information to the terminal device, which then displays the at least one decorative object in the vehicle logo fusion interface based on the decorative object information. The decorative object information includes the display style of the at least one decorative object.

[0162] In some embodiments, the bounding box is a three-dimensional spatial region centered on the three-dimensional navigation vehicle logo. The three-dimensional navigation vehicle logo is located within the bounding box. Optionally, the first position refers to any position within the bounding box. Exemplarily, the first position does not overlap with the position of the three-dimensional navigation vehicle logo within the bounding box.

[0163] Optionally, the operation of selecting the first decoration from the at least one decoration includes but is not limited to: a click operation, a slide operation, a key operation, a gesture operation, etc. The operation of selecting the first decoration from the at least one decoration is referred to as the operation of selecting the first decoration.

[0164] Exemplarily, in response to a click operation on the first decoration, the terminal device determines to select the first decoration to be merged with the three-dimensional navigation vehicle logo, the terminal device determines the position of the three-dimensional navigation vehicle logo in the bounding box, and determines the first position based on the position of the three-dimensional navigation vehicle logo in the bounding box, and the terminal device displays the first decoration at the first position in the bounding box.

[0165] In some embodiments, the operation of ending the vehicle logo fusion is used to notify the fusion of the first decorative object and the 3D navigation vehicle logo to generate a fused 3D navigation vehicle logo. Optionally, a fusion confirmation control is displayed in the vehicle logo fusion interface, and the operation of ending the vehicle logo fusion is an operation that triggers the fusion confirmation control. For example, clicking the fusion confirmation control.

[0166] In some embodiments, the fused 3D navigation logo includes the 3D navigation logo and the first decorative object. Optionally, during the display of the fused 3D navigation logo in the navigation interface, the relative distance between the 3D navigation logo and the first decorative object does not change.

[0167] The 3D navigation logo generated from the source image is a static 3D model. By fusing decorative elements with the 3D navigation logo, the logo becomes more dynamic, helping to improve the fused logo's prompting capabilities within the navigation interface. Furthermore, by first creating the 3D navigation logo and then generating the fused logo, this step-by-step approach helps reduce computing overhead compared to directly generating the 3D navigation logo all at once.

[0168] It should be noted that the embodiment of generating a fused three-dimensional navigation vehicle logo and the embodiment of adjusting the display style of the three-dimensional navigation vehicle logo can be freely combined.

[0169] For example, after displaying the three-dimensional navigation logo, the terminal device first adjusts the display style of the three-dimensional navigation logo to generate an adjusted three-dimensional navigation logo, and then merges the adjusted three-dimensional navigation logo with the first decoration to obtain a merged three-dimensional navigation logo.

[0170] For another example, after displaying the three-dimensional navigation logo, the terminal device first merges the three-dimensional navigation logo with the first decoration to obtain a merged three-dimensional navigation logo, and then adjusts the display style of the merged three-dimensional navigation logo to obtain an adjusted three-dimensional navigation logo.

[0171] In one example, the process of creating a three-dimensional navigation vehicle logo includes the following steps.

[0172] In step A10, the terminal device displays the material image of the first object in the image acquisition interface in response to the image acquisition operation. The terminal device displays the three-dimensional navigation vehicle logo of the first object.

[0173] In step A20, the terminal device displays at least one candidate surface texture, and in response to an operation of selecting a first surface texture from the at least one candidate surface texture, displays the adjusted three-dimensional navigation vehicle logo.

[0174] Optionally, after the style adjustment operation is completed, the terminal device displays a fusion start control.

[0175] In step A30, the terminal device displays a vehicle logo fusion interface, wherein the vehicle logo fusion interface displays at least one decorative object. Optionally, the terminal device displays the vehicle logo fusion interface in response to triggering a fusion start control operation.

[0176] In step A40 , in response to the operation of selecting the first decoration, the terminal device displays the first decoration at a first position in a bounding box, where the bounding box is a virtual three-dimensional space surrounding the adjusted three-dimensional navigation vehicle logo.

[0177] In step A50 , the terminal device displays a fused three-dimensional navigation logo in response to the operation of ending the vehicle logo fusion, where the fused three-dimensional navigation logo is obtained by fusing at least one three-dimensional model included in the bounding box.

[0178] Optionally, after obtaining the fused 3D navigation logo, the terminal device closes the entry for adjusting the display style of the fused 3D navigation logo. That is, after generating the fused 3D navigation logo, the user no longer adjusts the display style of the fused 3D navigation logo.

[0179] For details on each step in this embodiment, please refer to the previous embodiment and will not be repeated here. Compared to the fused 3D navigation logo, the 3D navigation logo is simpler in form. Therefore, by controlling the terminal device to adjust the display style first, and then perform the logo fusion, it helps to shorten the process time.

[0180] The following describes the use of a three-dimensional navigation vehicle logo through an embodiment.

[0181] In some embodiments, the use process of the three-dimensional navigation vehicle logo also includes: the terminal device displays the three-dimensional navigation vehicle logo in the navigation interface; the terminal device adjusts the position and posture of the three-dimensional navigation vehicle logo in the navigation interface according to the position and posture of the terminal device in the real environment.

[0182] Optionally, the posture of the terminal device in the real environment is used to represent the orientation of the terminal device in the real environment. For example, if the terminal device moves north, the orientation of the terminal device in the real environment is north. Optionally, the navigation interface displays a navigation map, and a three-dimensional navigation vehicle logo is displayed on the navigation map to reflect the position of the terminal device in the real environment.

[0183] The position of the 3D navigation vehicle logo in the navigation interface can 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.

[0184] The posture of the 3D navigation vehicle logo includes the orientation of the 3D navigation vehicle logo, and the posture of the 3D navigation vehicle logo is used to indicate the direction of change of the position of the 3D navigation vehicle logo in the navigation interface.

[0185] Optionally, the navigation interface supports displaying up to t three-dimensional navigation logos, where t is a positive integer. The t three-dimensional navigation logos correspond to different terminal devices, and for the i-th three-dimensional navigation logo among the t three-dimensional navigation logos, the position and posture of the i-th three-dimensional navigation logo in the navigation interface are related to the position and posture of the i-th terminal device corresponding to the i-th three-dimensional navigation logo in the real environment.

[0186] It should be noted that displaying 3D navigation vehicle logos corresponding to other devices in the navigation interface requires authorization from the user of the other device and can only be implemented in compliance with local laws and regulations. This feature is only intended for use in scenarios where the group is traveling to the same destination, such as following a vehicle in a convoy to prevent it from getting lost.

[0187] Optionally, only when t terminal devices respectively enter the same destination in the navigation application and the t terminal devices authorize each other, can t three-dimensional navigation car logos be displayed on the navigation interface. Exemplarily, in this case, a car logo sharing mark is displayed in the navigation interface, and the car logo sharing mark is used to prompt that the three-dimensional navigation car logo is displayed in the navigation interface of other terminal devices. Exemplarily, an authorization request is displayed in the navigation interface at every second time interval, and the terminal device responds to the operation of agreeing to the authorization request and allows other terminal devices to continue to display the three-dimensional navigation car logo corresponding to the terminal device in the navigation interface; the terminal device responds to the operation of rejecting the authorization request and sends a rejection prompt to the server, and the server no longer sends the position change information of the three-dimensional navigation car logo of the terminal device in the navigation interface to other devices according to the rejection prompt. This allows the function of sharing car logos in the navigation interface to be disabled in a timely manner according to actual needs.

[0188] The following describes a method for creating a three-dimensional navigation vehicle logo on a terminal device side through an overall embodiment. The execution subject of this embodiment is the terminal device, such as a target client in the terminal device. This embodiment may include the following steps.

[0189] Step B10, displaying an icon selection interface, in which a first acquisition entrance is displayed; wherein the icon selection interface is used to manage at least one three-dimensional navigation vehicle logo, and the first acquisition entrance is used to realize the acquisition of material images; in response to the operation of triggering the first acquisition entrance, an image acquisition interface is displayed.

[0190] Optionally, the first collection entrance may be implemented as a banner in the icon selection interface.

[0191] In some embodiments, in response to an operation triggering a first acquisition portal, the terminal device displays an image acquisition interface, including: displaying a vehicle logo creation interface in response to the operation triggering the first acquisition portal, wherein the vehicle logo creation interface displays a first control and a second control; and displaying an image acquisition interface in response to the operation triggering the second control. The first control is used to display a vehicle logo ownership interface, wherein the vehicle logo ownership interface is used to display a three-dimensional 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.

[0192] In some embodiments, before the terminal device displays the image capture interface, the terminal device further includes: displaying a sixth prompt message if the first user account meets the user conditions. The sixth prompt message requests the user to authorize the process of capturing the material image. Exemplarily, the sixth prompt message is displayed in the form of a pop-up window.

[0193] Optionally, the user condition includes: the first user account is accessing the image capture interface for the first time, or the first user account is not accessing the interface for the first time but has not granted the target application the permission to capture material images. If the first user account does not meet the user condition, the terminal device displays a sixth prompt message.

[0194] In some embodiments, before displaying the image acquisition interface, the method further includes: displaying seventh prompt information when the first user account meets the user conditions. The seventh prompt information is used to prompt a method for creating a three-dimensional navigation vehicle logo.

[0195] FIG9 is a schematic diagram before entering the image acquisition interface provided by an exemplary embodiment of the present application.

[0196] The terminal device enters the vehicle logo creation interface through a first capture portal 910. The vehicle logo creation interface displays a first control 920 and a second control 930. In response to triggering the second control 930, the terminal device displays an image capture interface. If the first user account meets the user requirements, a sixth prompt 940 and a seventh prompt 950 are displayed.

[0197] Step B20: An image acquisition control is displayed in the image acquisition interface; in response to the operation of triggering the image acquisition control, a field of view picture of the camera capturing the first object is displayed in the image acquisition interface.

[0198] Step B30: Displaying first prompt information on the upper layer of the field of view image. The first prompt information is used to prompt the camera to collect a recommended movement trajectory of the first object.

[0199] Step B40: In response to the image acquisition operation, display the material image of the first object in the image acquisition interface.

[0200] Step B50: Displaying a second prompt message in response to the operation of 3D reconstruction of the first object; or displaying a second prompt message when the data volume of the material image reaches the upper limit and the operation of 3D reconstruction of the first object is not received.

[0201] In step B55, in response to the operation of setting the identification information, the identification information of the 3D navigation vehicle logo is displayed. The identification information is used to uniquely identify the 3D navigation vehicle logo. If the identification information of the 3D navigation vehicle logo conforms to the naming rules and the material image conforms to the content rules, the step of displaying the 3D navigation vehicle logo of the first object (such as step 310) is executed.

[0202] Step B60: If the remaining creation time is longer than the first time interval, the second prompt information is updated every first time interval, and the updated second prompt information is displayed until the three-dimensional navigation vehicle logo is created.

[0203] Step B70: Display the three-dimensional navigation vehicle logo of the first object.

[0204] Step B80, displaying the car logo fusion interface, in which at least one decoration is displayed, and the three-dimensional model of the decoration is pre-set; in response to the operation of selecting the first decoration, the first decoration is displayed at the first position in the bounding box; in response to the operation of ending the car logo fusion, the fused three-dimensional navigation car logo is displayed.

[0205] Step B90: In response to the operation of adjusting the display style of the three-dimensional navigation vehicle logo, the adjusted three-dimensional navigation vehicle logo is displayed.

[0206] In step B100, the terminal device displays a three-dimensional navigation vehicle logo on the navigation interface; the terminal device adjusts the position and posture of the three-dimensional navigation vehicle logo on the navigation interface according to the position and posture of the terminal device in the real environment.

[0207] FIG10 is a schematic diagram of a navigation interface provided by an exemplary embodiment of the present application.

[0208] As shown in FIG10 , a three-dimensional navigation vehicle logo 1010 is displayed in the navigation interface 1000 .

[0209] For details not described in this embodiment, please refer to the above embodiments.

[0210] FIG11 is a schematic diagram of a three-dimensional navigation vehicle logo display effect provided by an exemplary embodiment of the present application.

[0211] When the 3D navigation vehicle logo is in a first position 1110, the 3D navigation vehicle logo is displayed in the navigation interface in the form 1100-a. When the 3D navigation vehicle logo is in a second position 1120, the 3D navigation vehicle logo is displayed in the navigation interface in the form 1100-b. When the 3D navigation vehicle logo is in a third position 1130, the 3D navigation vehicle logo is displayed in the navigation interface in the form 1100-c. When the 3D navigation vehicle logo is in a fourth position 1140, the 3D navigation vehicle logo is displayed in the navigation interface in the form 1100-d.

[0212] FIG12 is an interactive diagram of a vehicle logo application process provided by an exemplary embodiment of the present application.

[0213] In some examples, the method for creating a three-dimensional car logo provided in this application involves multiple platforms, mainly including a car logo management platform (also known as a theme square), a sub-application (also known as a target application), a parent application, a sharing page (H5) and a client, a server (including computer equipment), an Apollo configuration, etc.

[0214] The vehicle logo management platform is the main portal for creating 3D navigation vehicle logos and manages user accounts to own 3D navigation vehicle logos. The vehicle logo management platform is used to provide users with a first collection portal.

[0215] The sub-application refers to the target application in the above embodiments, used to acquire source images and create a customized 3D navigation logo. As described in the above embodiments, in response to triggering the first capture entry, the terminal device displays a logo creation interface, which includes a first control and a second control. To create a 3D navigation logo, the user triggers the second control.

[0216] In response to the operation of triggering 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 has entered the image acquisition interface for the first time. If this is the first time for the first user account to enter the image acquisition interface, the terminal device displays the sixth prompt information and the seventh prompt information (also known as the strategy page) in the form of a pop-up window.

[0217] If the first user account does not meet the user conditions, the terminal device displays an image capture interface and, in response to an operation on an image capture control, acquires a source image of the first object. If the source image is a video, real-time capture of the first object can be performed in the image capture interface. During the capture process, the terminal device displays a first prompt message in the field of view. The first prompt message indicates at least one of the following: a recommended capture trajectory for capturing the first object and a recommended position of the first object in the image.

[0218] Optionally, during the process of photographing the first object, a fourth prompt is further displayed in the image acquisition interface, the fourth prompt being used to indicate the maximum remaining photographing time. The fourth prompt may be a countdown from the start of photographing the first object to the maximum photographing time.

[0219] When the maximum remaining shooting time is equal to 0 or the user's operation of 3D reconstruction of the first object is obtained, the terminal device uses the captured video as the material image and sends the material image to the server for the server to conduct a compliance review of the material image.

[0220] Subsequently, the terminal device displays the identification information of the three-dimensional navigation vehicle logo in response to the operation of setting the identification information; the terminal device sends the identification information of the three-dimensional navigation vehicle logo to the server so that the server performs a compliance review on the identification information of the three-dimensional navigation vehicle logo.

[0221] If the identification information of the 3D navigation logo complies with the naming rules, the terminal device displays a failure prompt, prompting the user to re-enter the identification information of the 3D navigation logo. If the identification information of the 3D navigation logo complies with the naming rules and the source image complies with the content rules, the server sends the source image to the computer device so that the computer device can perform 3D reconstruction of the source image to generate the 3D navigation logo.

[0222] While the computer device is creating the 3D navigation logo, the terminal device displays a second prompt indicating the remaining creation time for the 3D navigation logo. The terminal device may update the second prompt at the first time interval. After the 3D navigation logo is created, the terminal device displays the 3D navigation logo.

[0223] After creating the three-dimensional navigation logo, the terminal device supports adjusting the display style of the three-dimensional navigation logo in response to user operations, and performing fusion processing on the three-dimensional navigation logo. For the specific content of this step, please refer to the above embodiment and will not be repeated here.

[0224] After the first user account creates a certain 3D navigation car logo, the first user account is supported to share the 3D navigation car logo on social networks. This function can be completed by the carrier sub-application and the parent application.

[0225] Parent application: Mainly responsible for logging in to the user account. In addition, the target application is also responsible for viewing the content of the 3D navigation car logo details page for the second time outside the terminal, and sharing the 3D navigation car logo between different accounts.

[0226] Server: Used for account information synchronization and compliance review. All footage captured and uploaded by the terminal device and the identification information for the 3D navigation vehicle logo must undergo compliance review to ensure compliance with laws and regulations before production can proceed.

[0227] In some embodiments, after the terminal device displays the three-dimensional navigation logo of the first object, the method for reconstructing the three-dimensional navigation logo also includes: in response to the operation of obtaining the first navigation logo and the second navigation logo, displaying the first navigation logo and the second navigation logo; wherein the first navigation logo belongs to the three-dimensional navigation logo, and the second navigation logo belongs to the three-dimensional navigation logo; in response to the logo combination operation, displaying the combined navigation logo; wherein the combined navigation logo is composed of the first navigation logo and the second navigation logo, and the combined navigation logo is used to be displayed in the navigation interface.

[0228] Optionally, the first navigation logo is created by the first user account logged in on the target application of the terminal device (referred to as the first terminal in this embodiment), and the second navigation logo is created by the first user account logged in on the target application of other terminal devices (referred to as the second terminal in this embodiment).

[0229] Optionally, the first terminal displays the first navigation vehicle logo and the second navigation vehicle logo in response to the operation of obtaining the first navigation vehicle logo and the second navigation vehicle logo, including: the first terminal receives vehicle logo provision information sent by the second terminal, and the vehicle logo provision information is used to authorize the first terminal to obtain the second navigation vehicle logo; the first terminal sends a vehicle logo acquisition request to the server according to the vehicle logo provision information; the terminal device receives the second navigation vehicle logo sent by the server according to the vehicle logo acquisition request.

[0230] The information provided by the vehicle logo includes: the second terminal logo and the identification information of the second navigation vehicle logo.

[0231] In some embodiments, the first terminal responds to the car logo combination operation and displays the combined navigation car logo, including: the first terminal generates and sends a car logo combination request to the server in response to the car logo combination operation, the car logo combination request including: the identification information of the first navigation car logo, the identification information of the second navigation car logo and the offset position of the first navigation car logo relative to the second navigation car logo, so that the server determines that the combination of the first navigation car logo and the second navigation car logo is allowed according to the car logo combination request, and sends a car logo combination indication to the computer device, and the computer device places the first navigation car logo and the second navigation car logo in the same virtual space according to the car logo combination indication to obtain the combined navigation car logo.

[0232] Exemplarily, the vehicle logo combination indication includes: identification information of the first navigation vehicle logo, identification information of the second navigation vehicle logo, and an offset position of the first navigation vehicle logo relative to the second navigation vehicle logo.

[0233] The server estimates the volume of the combined navigation logo based on the offset position of the first navigation logo relative to the second navigation logo. Optionally, if the volume of the combined navigation logo is less than or equal to an upper volume limit, the server determines that the combination of the first and second navigation logos is permitted; if the volume of the combined navigation logo is greater than the upper volume limit, the server determines that the combination of the first and second navigation logos is not permitted. The upper volume limit is pre-set and is used to control the volume of the combined navigation logo to prevent the combined navigation logo from being displayed in the navigation interface and obscuring the road condition information in the navigation interface.

[0234] For example, after receiving the vehicle logo information sent by the second terminal, the first terminal displays the second navigation vehicle logo in the navigation interface in response to an operation to apply the second navigation vehicle logo, that is, directly using the three-dimensional navigation vehicle logo created by the second terminal, so that different users can share the three-dimensional navigation vehicle logo.

[0235] 3D navigation logos are generated from source images, but different users may only be able to collect limited source images. The above method supports the synthesis of 3D navigation logos collected by multiple users. This allows for the ability to combine 3D navigation logos after creation, reducing the requirements for source images. Furthermore, using 3D navigation logos to generate combined navigation logos provides users with more available 3D navigation logos, helping to enhance the richness of 3D navigation logos.

[0236] Figure 13 is a flowchart of a method for creating a three-dimensional navigation vehicle logo, provided in another exemplary embodiment of the present application. For example, the method can be executed by the computer device 30 in Figure 1 . Below, the method for creating a three-dimensional navigation vehicle logo will be described using the computer device as the execution entity. As shown in Figure 2 , the method can include the following steps ( 1310 - 1340 ).

[0237] Step 1310 , obtaining a material image of a first object; wherein the material image includes images obtained by photographing the first object from different angles, and the first object is a three-dimensional physical object in a real environment.

[0238] In some embodiments, the material image is sent from the terminal device to the computer device. In other embodiments, the material image is searched and downloaded from the Internet by the computer device. For a detailed description of the material image and the first object, please refer to the terminal device side embodiment and will not be repeated here.

[0239] Step 1320 : perform key point recognition on the material image to generate point cloud data of the first object. The point cloud data is used to describe the position and display style of the key points of the first object in the real environment.

[0240] In some embodiments, key points are used to characterize the surface contour of a first object. In other words, key points are points on the surface of the first object. Optionally, key points include at least one of the following: an edge point of the first object's contour, or a point on a boundary within the first object's contour where significant fluctuations in color or shape occur. Key points are also referred to as feature points. For example, key points can be determined based on a region where pixel values ​​in an image change. For example, key points are extreme points where pixel values ​​in an image change.

[0241] In some embodiments, the point cloud data refers to a data set about key points, and the point cloud data is used to reconstruct the first object in a virtual three-dimensional space.

[0242] Optionally, the point cloud data includes position information of the key points and photometric information of the key points, wherein the position information is used to indicate the three-dimensional coordinates of the key points, and the photometric information is used to characterize the color of the key points and their ability to refract and reflect light.

[0243] Step 1330 : Perform three-dimensional reconstruction based on the point cloud data to determine the original surface texture of the first object, where the original surface texture is used to reflect the surface material of the first object.

[0244] In this embodiment, the original surface texture of the first object is the original surface texture mentioned in the above embodiment. For a detailed introduction to the original surface texture, please refer to the above embodiment, which will not be repeated here.

[0245] Step 1340 , texture mapping is performed on the point cloud data according to the surface texture of the first object to create a three-dimensional navigation logo of the first object, which is used to be displayed in the navigation interface.

[0246] In some embodiments, the computer device renders the point cloud data based on the surface texture to obtain a three-dimensional navigation logo of the first object. After generating the three-dimensional navigation logo of the first object, the computer device sends the three-dimensional navigation logo of the first object to the server, and the server forwards the three-dimensional navigation logo of the first object to the terminal device.

[0247] To sum up, compared with the related technology that requires technicians to generate 3D skeleton car logos, the embodiment of the present application uses computer equipment to perform three-dimensional reconstruction based on the material image of the photographed object to generate a three-dimensional navigation car logo of the photographed object, which helps to reduce the production cost of the three-dimensional navigation car logo, shorten the generation cycle of the three-dimensional navigation car logo, and make it more convenient and quick to obtain the three-dimensional navigation car logo, which helps to meet the update and iteration needs of the three-dimensional navigation car logo.

[0248] In addition, in this method, a three-dimensional navigation vehicle logo is created in the cloud through a computer device, so that the mobile terminal has the ability to generate a three-dimensional navigation vehicle logo, which helps to improve the convenience of the three-dimensional navigation vehicle logo creation process.

[0249] The process of determining point cloud data is described below through several embodiments.

[0250] In some embodiments, step 1320 , performing key point recognition on the material image to determine point cloud data of the first object, includes the following sub-steps.

[0251] In sub-step 1321 , the computer device performs key point recognition on multiple images in the material image, and determines the key point information of each image respectively; wherein the key point information includes a descriptor of the key point, and the descriptor is used to characterize the local structural features of the key point in the image.

[0252] In some embodiments, the multiple images in the source image are selected from the source image. For example, if the source image is a video, any two adjacent images in the multiple images are two video frames separated by k frames in the video, where k is a positive integer. Optionally, the computer device selects an image every k consecutive image frames in the video to obtain multiple images; the computer device performs 3D reconstruction based on the multiple images.

[0253] For images shot from consecutive angles, such as two consecutive frames in a video, the information contained in these two frames overlaps significantly. By selecting portions of the source image, the overlap is reduced. The computer then uses these portions of the image to participate in the 3D reconstruction process, helping to reduce the computational effort involved in generating the 3D navigation vehicle logo.

[0254] In some embodiments, a descriptor is used to characterize the visual features of the region to which a keypoint belongs in an image. Visual features include shape features and texture features in the region to which the keypoint belongs; shape features are used to characterize the shape of the local region surrounding the keypoint of the first object, and texture features are used to characterize the texture of the local region surrounding the keypoint of the first object. Optionally, the descriptor is represented in vector form. The vector dimensions of the descriptors of multiple keypoints included in the image are equal.

[0255] In some embodiments, a computer device performs key point identification on multiple images in a material image and determines the key point information of each image respectively, including: for each image in the multiple images, the computer device performs at least one blurring process and downsampling process on the image to obtain a Gaussian image set; wherein the Gaussian image set includes multiple Gaussian image groups, and the Gaussian image group includes Gaussian images with different degrees of blur; for each Gaussian image group, the computer device performs differential processing on each two adjacent Gaussian images in the Gaussian image group to obtain a differential image group; the computer device determines at least one extreme point based on a pixel value change trend of pixel points in at least one differential image of the differential image group; the computer device establishes an extreme point change curve based on the at least one extreme point to determine at least one key point of the first object, and the computer device determines the key point information of the image based on the at least one key point and the Gaussian image set.

[0256] In some embodiments, for any one of the multiple images, the computer device generates a Gaussian pyramid for the image. Blurring refers to processing pixels in the image using a Gaussian kernel. The Gaussian kernel is used to fuse (e.g., average) the pixel values ​​of pixels in a region to obtain a fused pixel value, such that the values ​​of each pixel in the region after fusion equal the fused pixel value.

[0257] Optionally, the Gaussian pyramid is called a Gaussian pyramid, and the multiple Gaussian image groups have a hierarchical structure in the Gaussian pyramid; wherein, the Gaussian images in the higher-level Gaussian image groups have smaller sizes and higher blur levels; the lowest-level Gaussian image groups include the image, or an upsampled image obtained by upsampling the image. Upsampling is used to enlarge the size of an image, and downsampling is used to reduce the size of an image.

[0258] Optionally, the difference image is obtained by performing difference processing on two Gaussian images with similar blur levels in the same Gaussian image group. The difference processing can be implemented by subtracting pixel values ​​at corresponding positions in the two Gaussian images.

[0259] Exemplarily, a computer device performs difference processing on two adjacent Gaussian images in the same Gaussian image group to obtain a differential image. Assume that, for a first Gaussian image group among multiple Gaussian image groups, the first Gaussian image group includes x Gaussian images, then the first differential image group determined based on the first Gaussian image group includes x-1 differential images, where x is a positive integer greater than 1.

[0260] In some embodiments, the computer device establishes an extreme point change curve based on at least one extreme point and determines at least one key point of the first object, including: the computer device performs Taylor expansion based on the at least one extreme point and fits to generate the extreme point change curve, the extreme point change curve includes the above-mentioned at least one extreme point; the computer device derives the extreme point curve to determine at least one continuous extreme point; the computer device uses the continuous extreme points as key points.

[0261] Since the pixel points in the image change discretely, determining the key points through the extreme point change curve helps to improve the accuracy of the key points identified from the image, and helps to improve the similarity between the generated three-dimensional navigation vehicle logo and the photographed object.

[0262] In some embodiments, a computer device determines key point information of an image based on at least one key point and a Gaussian image set, including: for each key point of the at least one key point, the computer device determines an associated area of ​​the key point from the Gaussian image corresponding to the key point; wherein the Gaussian image corresponding to the key point is a Gaussian image in the Gaussian image set whose blurriness is closest to the blurriness of the differential image corresponding to the key point, and the key point is the center point of the associated area; the computer device counts the gradient amplitude of each pixel point included in the associated area, and determines the direction with the largest gradient amplitude as the main direction of the key point; the computer device performs a coordinate system transformation on the Gaussian image corresponding to the key point based on the main direction of the key point to obtain an adjusted Gaussian image; in the adjusted Gaussian image, the computer device counts the gradient amplitude of the pixel points within a first radius area with the key point as the center to obtain a descriptor of the key point.

[0263] Optionally, the differential image corresponding to the key point refers to the differential image used to determine the key point.

[0264] Optionally, the computer device determines a descriptor of the key point based on a SIFT (Scale Invariant Feature Transform) algorithm, that is, obtains the key point information.

[0265] In sub-step 1323 , the computer device determines camera parameters based on the key point information of the image. The camera parameters include camera intrinsic parameters and camera extrinsic parameters used to capture the material image.

[0266] In some embodiments, the computer device determines camera parameters based on key point information of the image, including:

[0267] The computer device determines at least one key point chain based on key point information of multiple images, where the key point chain is used to characterize changes in shooting positions of the multiple images; the computer device performs parameter estimation based on the at least one key point chain to determine initial parameters; and the computer device jointly optimizes the at least one key point and the initial parameters to obtain camera parameters.

[0268] Optionally, the camera parameters include: camera intrinsic parameters and camera extrinsic parameters, the camera memory includes: focal length, principal point; the camera extrinsic parameters include camera position, camera rotation angle.

[0269] In some embodiments, a computer device determines at least one key point chain based on key point information of each image in the material image, including: for each original image group in the material image, the computer device performs similarity matching on the key point information of the first image and the key point information of the second image in the original image group to obtain at least one group of matching points, and 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 computer device deletes noise points from at least one group of matching points to obtain at least one key point group; the computer device performs similarity matching on the key point groups of the material image to determine at least one key point chain, and the key point groups of the material image include the key point groups of each original image group.

[0270] 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 remove noise points from the at least one matching point group using a RANSAC (Random Sampling Consensus) algorithm, fitting the noise points using a least squares method. Subsequently, the computer device performs continuous frame matching to generate and determine at least one keypoint chain.

[0271] Optionally, the computer device determines parameter estimation based on the keypoint chain to obtain initial parameters, and the computer device uses BA (Bundle Adjustment) to jointly optimize the keypoint position information and camera parameters. Specifically, the computer device estimates a reprojection error based on the initial parameters and the keypoint position information, calculates a residual based on the reprojection error, and constructs a system of linear equations based on the inverse of the residual for the camera parameters and the keypoint position information; and updates the camera parameters and the keypoint position information by incrementally solving the linear equations.

[0272] In sub-step 1325 , the computer device determines point cloud data of the first object based on the camera parameters.

[0273] In some embodiments, the point cloud data includes position information of key points and photometric information of key points, wherein the position information of key points is determined according to camera parameters and material images, and the photometric information is used to characterize the display style of key points; the computer device determines the point cloud data of the first object according to the camera parameters, including: for a third image in the material image, the computer device generates a reconstructed image based on the third image and camera parameters through a scene reconstruction network; the computer device adjusts the parameters of the scene reconstruction network according to the difference between the reconstructed image and the third image to obtain a trained scene reconstruction network; for each key point of at least one key point, the computer device predicts based on the position information of the key point through the trained scene reconstruction network to generate photometric information of the key point; the computer device determines the point cloud data of the first object based on the photometric information of the key point and the position information of the key point.

[0274] Optionally, the scene reconstruction network is used to construct 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 material image is captured.

[0275] In some embodiments, the scene reconstruction network is a NeRF (Neural Radiance Fields) network. Optionally, the scene reconstruction network generates a reconstructed image based on the third image and camera parameters, including: a computer device determining a viewpoint position and a line of sight direction according to the camera parameters, wherein the viewpoint position is used to simulate the position of the first object in real space when the camera photographs the first object in three-dimensional space, and the line of sight direction is used to simulate the direction of light reflection of the first object when the camera photographs the first object in three-dimensional space; the computer device calculates the integral of the photometric information of at least one point in the three-dimensional space passing through the line of sight direction to obtain the pixel value of the pixel point corresponding to the line of sight direction in the reconstructed image; when the pixel value of the pixel point corresponding to each line of sight direction in the reconstructed image is determined, the reconstructed image can be obtained from the pixel values ​​of the above-mentioned pixel points.

[0276] Optionally, the difference between the reconstructed image and the third image is calculated by a mean square error. The computer device adjusts the network parameters of the scene reconstruction network based on a gradient descent method.

[0277] In some embodiments, after key points of the material image are identified and the computer device generates point cloud data of the first object, the process also includes: the computer device performs plane fitting based on the point cloud data to identify background points, where background points refer to plane key points in three-dimensional space that are not related to the first object; the computer device performs outlier identification based on the point cloud data to determine at least one outlier point, where an outlier point is noise caused by environmental factors when photographing the first object; the computer device removes 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.

[0278] Optionally, the computer device fits and identifies planes in the point cloud data based on a random sampling consensus algorithm. This allows planar structures, such as the ground and walls, to be removed from the point cloud data. In addition, there may be some noise or outliers in the point cloud data, which may be caused by sensor errors, reflections, and the like. In order to improve the quality of the point cloud, these outliers need to be identified and removed. Commonly used methods include statistical outlier removal, density-based methods, and the like. Since the points in the point cloud data often represent multiple different objects or scene structures, in order to process or model these structures separately, it is necessary to use clustering based on Euclidean distance to segment the point cloud into multiple clusters or clusters.

[0279] In some embodiments, a computer device performs three-dimensional reconstruction based on point cloud data to determine the surface texture of a first object, including: performing Poisson reconstruction based on the point cloud data to generate first texture information; smoothing the first texture information to obtain second texture information, and simplifying the second texture information to obtain the surface texture of the first object.

[0280] Optionally, the computer device performs Poisson reconstruction based on the point cloud data to generate first texture information, including: establishing an octree structure according to the position information of the key points, the octree structure including at least one leaf node with the same depth, and the leaf node including at least one key point in the same three-dimensional space; the computer device establishes an implicit function corresponding to at least one leaf node; wherein the implicit function is used to calculate the normal vector of the key point included in the leaf node, and the normal vector of the key point is used to characterize the orientation of the key point on the local plane of the surface of the first object; solving the parameters of the implicit function based on the finite element method to obtain a Poisson expression; according to the Poisson expression, determining the isosurface of the first object, triangulating the isosurface of the first object, and generating the first texture information.

[0281] The following are device embodiments of the present application, which can be used to implement the method embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the method embodiments of the present application.

[0282] 14 shows a block diagram of a device for shooting and creating a 3D navigation vehicle logo according to an exemplary embodiment of the present application. The device 1400 may include: a material collection module 1410 , a vehicle logo display module 1420 , and a vehicle logo adjustment module 1430 .

[0283] The material acquisition module 1410 is used to display the material image of the first object in the image acquisition interface in response to the operation of acquiring an image; wherein the material image includes images obtained by photographing the first object from different shooting angles, and the first object is a three-dimensional physical object in a real environment.

[0284] The vehicle logo display module 1420 is configured to display a three-dimensional navigation vehicle logo of the first object, where the three-dimensional navigation vehicle logo is obtained by three-dimensionally reconstructing the first object based on the material image.

[0285] The vehicle logo adjustment module 1430 is configured to display the adjusted three-dimensional navigation vehicle logo in response to an operation of adjusting the display style of the three-dimensional navigation vehicle logo, wherein the adjusted three-dimensional navigation vehicle logo is configured to be displayed in the navigation interface.

[0286] In some embodiments, the display style includes: the position of the three-dimensional navigation logo in the navigation interface; a logo adjustment module 1430, which is used to rotate the position of the three-dimensional navigation logo in response to the operation of adjusting the posture of the three-dimensional navigation logo; and display the adjusted three-dimensional navigation logo in response to ending the operation of adjusting the posture of the three-dimensional navigation logo.

[0287] In some embodiments, the display style includes: the surface texture of the three-dimensional navigation logo; the logo adjustment module 1430, used to display at least one candidate surface texture, the candidate surface texture is generated based on the original surface texture of the three-dimensional navigation logo, and the original surface texture is used to reflect the surface material of the first object; in response to the operation of selecting the first surface texture among the at least one candidate surface texture, the three-dimensional navigation logo with the first surface texture is displayed as the adjusted three-dimensional navigation logo; the adjusted three-dimensional navigation logo is generated by texture mapping the point cloud data of the first object based on the first surface texture.

[0288] In some embodiments, the car logo adjustment module 1430 is also used to display a car logo fusion interface, in which at least one decoration is displayed, and the three-dimensional model of the decoration is pre-set; in response to the operation of selecting a first decoration among at least one decoration, the first decoration is displayed at a first position in a bounding box, and the bounding box refers to a virtual three-dimensional space surrounding the three-dimensional navigation car logo; in response to the operation of ending the car logo fusion, the fused three-dimensional navigation car logo is displayed, and the fused three-dimensional navigation car logo is obtained by fusion of at least one three-dimensional model included in the bounding box; wherein, the fused three-dimensional navigation car logo is used to be displayed in the navigation interface.

[0289] In some embodiments, the device 1400 also includes an image acquisition module, which is used to display a field of view picture of the camera acquiring the first object in the image acquisition interface in response to the operation of triggering the image acquisition control, and the field of view picture corresponds to the image; display first prompt information on the upper layer of the field of view picture, and the first prompt information is used to prompt the camera to acquire the recommended movement trajectory of the first object; in response to the operation of completing the acquisition of the material image, execution starts from the step of displaying the material image of the first object in the image acquisition interface.

[0290] In some embodiments, the device 1400 also includes an information display module for displaying a second prompt message in response to the operation of three-dimensionally reconstructing the first object; wherein, the second prompt message is used to prompt the remaining creation time of the three-dimensional navigation vehicle logo; if the remaining creation time is greater than the first time interval, the second prompt message is updated every first time interval, and the updated second prompt message is displayed until the creation of the three-dimensional navigation vehicle logo is completed.

[0291] In some embodiments, the information display module is further configured to display the second prompt information when the data volume of the material image reaches an upper limit and the operation of three-dimensionally reconstructing the first object is not received.

[0292] In some embodiments, the device 1400 also includes an identification determination module for displaying identification information of the three-dimensional navigation vehicle logo in response to an operation of setting identification information, wherein the identification information is used to uniquely identify the three-dimensional navigation vehicle logo; when the identification information of the three-dimensional navigation vehicle logo complies with the naming rules and the material image complies with the content rules, execution begins from the step of displaying the three-dimensional navigation vehicle logo of the first object.

[0293] 15 shows a block diagram of a device for creating a 3D navigation vehicle logo by shooting, according to an exemplary embodiment of the present application. The device 1500 may include: a material acquisition module 1510 , a data determination module 1520 , a 3D reconstruction module 1530 , and a vehicle logo creation module 1540 .

[0294] The material acquisition module 1510 is configured to acquire material images of a first object. The material images include images of the first object captured from different angles. The first object is a three-dimensional entity in a real environment.

[0295] The data determination module 1520 is configured to perform key point recognition on the material image to determine point cloud data of the first object, where the point cloud data is used to describe the position and display style of the key points of the first object in the real environment.

[0296] The three-dimensional reconstruction module 1530 is configured to perform three-dimensional reconstruction based on the point cloud data to determine an original surface texture of the first object, where the original surface texture is used to reflect a surface material of the first object.

[0297] The vehicle logo creation module 1540 is used to perform texture mapping on the point cloud data according to the surface texture of the first object to create a three-dimensional navigation vehicle logo of the first object, and the three-dimensional navigation vehicle logo is used to be displayed in the navigation interface.

[0298] In some embodiments, the data determination module 1520 includes: a key point determination unit, used to perform key point recognition on multiple images in the material image, and determine the key point information of each image respectively; wherein the key point information includes a descriptor of the key point, and the descriptor is used to characterize the local structural features of the key point in the image; a parameter determination unit, used to determine the camera parameters based on the key point information of the image, and the camera parameters include the camera intrinsic parameters and camera extrinsic parameters used to shoot the material image; a data determination unit, used to determine the point cloud data of the first object based on the camera parameters.

[0299] In some embodiments, the key point determination unit is used to perform at least one blurring and downsampling process on each of the multiple images to obtain a Gaussian image set; wherein the Gaussian image set includes multiple Gaussian image groups, and the Gaussian image group includes Gaussian images with different degrees of blurring; for each of the Gaussian image groups, each two adjacent Gaussian images in the Gaussian image group are respectively subjected to differential processing to obtain a differential image group; based on the pixel value change trend of pixel points in at least one differential image of the differential image group, at least one extreme point is determined; based on the at least one extreme point, an extreme point change curve is established to determine at least one key point of the first object, and according to the at least one key point and the Gaussian image set, the key point information of the image is determined.

[0300] In some embodiments, the parameter determination unit includes a key point connection subunit, which is used to determine at least one key point chain based on the key point information of the multiple images, and the key point chain is used to characterize the changes in the shooting positions of the multiple images; a parameter estimation subunit, which performs parameter estimation based on the at least one key point chain to determine initial parameters; and a parameter optimization subunit, which is used to jointly optimize the at least one key point and the initial parameters to obtain the camera parameters.

[0301] In some embodiments, the key point connection subunit is used to perform similarity matching on the key point information of the first image and the key point information of the second image in each original image group in the material image to obtain at least one group of matching points, and 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; delete noise points from the at least one group of matching points to obtain at least one key point group; perform similarity matching on the key point groups of the material image to determine the at least one key point chain, and the key point groups of the material image include the key point groups of each of the original image groups.

[0302] In some embodiments, the point cloud data includes position information of the key points and photometric information of the key points, wherein the position information of the key points is determined according to the camera parameters and the material image, and the photometric information is used to characterize the display style of the key points; a data determination unit is used to generate a reconstructed image for a third image in the material image based on the third image and the camera parameters through a scene reconstruction network; according to the difference between the reconstructed image and the third image, the parameters of the scene reconstruction network are adjusted to obtain a trained scene reconstruction network; for each of the at least one key point, the trained scene reconstruction network is used to predict the key point based on the position information of the key point to generate the photometric information of the key point; based on the photometric information of the key point and the position information of the key point, the point cloud data of the first object is determined.

[0303] In some embodiments, the device 1500 further includes: a data optimization module, used to perform plane fitting based on the point cloud data and identify background points, wherein the background points refer to plane key points in the three-dimensional space that are not related to the first object; perform outlier identification based on the point cloud data and determine at least one outlier point, wherein the outlier point is noise caused by environmental factors when photographing the first object; remove the background points and the outlier points from the point cloud data to obtain processed point cloud data; wherein the processed point cloud data is used for three-dimensional reconstruction.

[0304] It should be noted that the device provided in the above embodiment, when implementing its functions, only uses the division of the above functional modules as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the content structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiment belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here. For the beneficial effects of the device provided in the above embodiment, please refer to the description of the method side embodiment, which will not be repeated here.

[0305] Figure 16 shows a block diagram of a computer device provided by an exemplary embodiment of the present application. The device 1600 for creating a three-dimensional navigation vehicle logo can be the computer device described above.

[0306] Typically, the computer device 1600 includes a processor 1601 and a memory 1602 .

[0307] The processor 1601 may include one or more processing cores, such as a 4-core processor, a 16-core processor, etc. In some embodiments, the processor 1601 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0308] Memory 1602 may include one or more computer-readable storage media, which may be tangible and non-transitory. Memory 1602 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices and flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in memory 1602 stores at least one program, which is loaded and executed by processor 1601 to implement the method for creating a three-dimensional navigation vehicle logo provided by the above-mentioned method embodiments.

[0309] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. The computer program is loaded and executed by a processor to implement the method for creating a three-dimensional navigation vehicle logo provided by the above-mentioned method embodiments.

[0310] The computer-readable media may include computer storage media and communication media. Computer storage media include volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules or other data.

[0311] An embodiment of the present application also provides a computer program product, which includes a computer program stored in a computer-readable storage medium. A processor reads and executes the computer program from the computer-readable storage medium to implement the method for creating a three-dimensional navigation vehicle logo provided in the above-mentioned method embodiments.

[0312] It should be understood that the term "plurality" used herein refers to two or more. "And / or" describes a relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can mean: A exists alone, A and B exist simultaneously, or B exists alone. The character " / " generally indicates an "or" relationship between the associated objects.

[0313] It should be noted that this application can display a prompt interface, pop-up window or output voice prompt information before collecting the user's relevant data and during the process of collecting the user's relevant data. The prompt interface, pop-up window or voice prompt information is used to remind the user that its relevant data is currently being collected, so that this application only starts to execute the relevant steps of obtaining the user's relevant data after obtaining the user's confirmation operation on the prompt interface or pop-up window. Otherwise (that is, when the user's confirmation operation on the prompt interface or pop-up window is not obtained), the relevant steps of obtaining the user's relevant data are terminated, that is, the user's relevant data is not obtained. In other words, the collection of material images in this application, in accordance with the requirements of relevant national laws and regulations, obtains the informed consent or separate consent of the personal information subject and is collected with the user's consent and authorization, and carries out subsequent data use and processing within the scope of authorization of laws and regulations and the personal information subject, and the collection, use and processing of relevant user data must comply with the relevant laws, regulations and standards of relevant countries and regions.

[0314] The above description is merely an optional embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent switches, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for creating a three-dimensional navigation vehicle logo, the method being executed by a terminal device, the method comprising: In response to the operation of capturing an image, a material image of a first object is displayed in an image capturing interface; wherein the material image includes images obtained by capturing the first object from different shooting angles, and the first object is a three-dimensional entity object in a real environment; Displaying a three-dimensional navigation vehicle logo of the first object, where the three-dimensional navigation vehicle logo is obtained by three-dimensionally reconstructing the first object based on the material image; In response to an operation of adjusting the display style of the three-dimensional navigation vehicle logo, the adjusted three-dimensional navigation vehicle logo is displayed, and the adjusted three-dimensional navigation vehicle logo is used to be displayed in the navigation interface.

2. According to the method of claim 1, the display style comprises: The position of the three-dimensional navigation vehicle mark in the navigation interface; In response to the operation of adjusting the display style of the three-dimensional navigation vehicle logo, displaying the adjusted three-dimensional navigation vehicle logo includes: In response to the operation of adjusting the posture of the three-dimensional navigation vehicle logo, rotating the orientation of the three-dimensional navigation vehicle logo; In response to finishing the operation of adjusting the posture of the three-dimensional navigation vehicle logo, displaying the adjusted three-dimensional navigation vehicle logo.

3. According to the method of claim 1, the display style comprises: The surface texture of the three-dimensional navigation vehicle logo; In response to the operation of adjusting the display style of the three-dimensional navigation vehicle logo, displaying the adjusted three-dimensional navigation vehicle logo includes: Display at least one candidate surface texture, where the candidate surface texture is generated based on an original surface texture of the three-dimensional navigation vehicle logo, and the original surface texture is used to reflect the surface material of the first object; In response to an operation of selecting a first surface texture from at least one candidate surface texture, a three-dimensional navigation vehicle logo having the first surface texture is displayed as the adjusted three-dimensional navigation vehicle logo; the adjusted three-dimensional navigation vehicle logo is generated by texture mapping the point cloud data of the first object based on the first surface texture.

4. The method according to claim 1, after displaying the three-dimensional navigation vehicle logo of the first object, further comprising: Displaying a car logo fusion interface, wherein at least one decoration is displayed in the car logo fusion interface, and the three-dimensional model of the decoration is preset; In response to an operation of selecting a first decoration among the at least one decoration, displaying the first decoration at a first position in a bounding box, wherein the bounding box refers to a virtual three-dimensional space surrounding the three-dimensional navigation vehicle logo; In response to the operation of ending the vehicle logo fusion, displaying a fused three-dimensional navigation vehicle logo, wherein the fused three-dimensional navigation vehicle logo is obtained by fusion of at least one three-dimensional model included in the bounding box; Wherein, the fused three-dimensional navigation vehicle logo is used to be displayed in the navigation interface.

5. The method according to claim 1, wherein an image acquisition control is displayed in the image acquisition interface; Before displaying the material image of the first object in the image acquisition interface, the method further includes: In response to the operation of triggering the image acquisition control, displaying a field of view picture of a process in which a camera acquires the first object in the image acquisition interface, the field of view picture corresponding to the image; Displaying first prompt information on an upper layer of the field of view screen, where the first prompt information is used to prompt the camera to collect a recommended moving trajectory of the first object; In response to the operation of completing the acquisition of the material image, the step of displaying the material image of the first object in the image acquisition interface is performed.

6. The method according to claim 1, before displaying the three-dimensional navigation vehicle logo of the first object, further comprising: In response to the operation of three-dimensionally reconstructing the first object, displaying second prompt information; wherein the second prompt information is used to prompt the remaining creation time of the three-dimensional navigation vehicle logo; If the remaining creation time is longer than the first time interval, the second prompt information is updated every the first time interval, and the updated second prompt information is displayed until the three-dimensional navigation vehicle logo is created.

7. The method according to claim 6, further comprising: When the data volume of the material image reaches the upper limit value and the operation of three-dimensionally reconstructing the first object is not received, the second prompt information is displayed.

8. The method according to claim 1, after displaying the material image of the first object in the image acquisition interface in response to the operation of acquiring the image, further comprising: In response to the operation of setting identification information, displaying identification information of the three-dimensional navigation vehicle logo, wherein the identification information is used to uniquely identify the three-dimensional navigation vehicle logo; When the identification information of the three-dimensional navigation vehicle logo complies with the naming rule and the material image complies with the content rule, the step of displaying the three-dimensional navigation vehicle logo of the first object is performed.

9. A method for creating a three-dimensional navigation vehicle logo, the method being executed by a computer device, the method comprising: Acquire a material image about a first object; wherein the material 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; Performing key point recognition on the material image to determine point cloud data of the first object, wherein the point cloud data is used to describe the position and display style of the key points of the first object in the real environment; Performing three-dimensional reconstruction based on the point cloud data to determine an original surface texture of the first object, where the original surface texture is used to reflect a surface material of the first object; Texture mapping is performed on the point cloud data according to the surface texture of the first object to create a three-dimensional navigation logo of the first object, and the three-dimensional navigation logo is used to be displayed in a navigation interface.

10. The method according to claim 9, wherein the step of performing key point recognition on the material image to determine the point cloud data of the first object comprises: Performing key point recognition on multiple images in the material image, and determining key point information of each of the images respectively; wherein the key point information includes a descriptor of the key point, and the descriptor is used to characterize the local structural features of the key point in the image; Determining camera parameters according to key point information of the image, wherein the camera parameters include camera intrinsic parameters and camera extrinsic parameters used to shoot the material image; Point cloud data of the first object is determined according to the camera parameters.

11. The method according to claim 10, wherein the step of performing key point recognition on a plurality of images in the material image and determining key point information of each of the images comprises: For each of the multiple images, blur processing and downsampling processing are performed on the image at least once to obtain a Gaussian image set; wherein the Gaussian image set includes multiple Gaussian image groups, and the Gaussian image group includes Gaussian images with different blur levels; For each of the Gaussian image groups, performing difference processing on each two adjacent Gaussian images in the Gaussian image group to obtain a difference image group; Determining at least one extreme point based on a pixel value variation trend of a pixel point in at least one differential image of the differential image group; Establishing an extreme point variation curve based on the at least one extreme point, and determining at least one key point of the first object; Key point information of the image is determined according to the at least one key point and the Gaussian image set.

12. The method according to claim 10, wherein determining the camera parameters according to the key point information of the image comprises: Determining at least one key point chain according to the key point information of the multiple images, wherein the key point chain is used to characterize changes in shooting positions of the multiple images; Perform parameter estimation according to the at least one key point chain to determine initial parameters; The at least one key point and the initial parameters are jointly optimized to obtain the camera parameters.

13. The method according to claim 12, wherein determining at least one key point chain according to the key point information of each image in the material images comprises: For each original image group in the material images, similarity matching is performed on key point information of a first image and key point information of a second image in the original image group to obtain at least one set of matching points, wherein a difference between a shooting angle of the first image and a shooting angle of the second image is less than or equal to a first threshold; Deleting noise points from the at least one group of matching points to obtain at least one key point group; Similarity matching is performed on the key point groups of the material image to determine the at least one key point chain, wherein the key point groups of the material image include the key point groups of each of the original image groups.

14. The method according to claim 13, wherein the point cloud data includes the position information of the key points and the photometric information of the key points, wherein: The position information of the key point is determined according to the camera parameters and the material image, and the photometric information is used to characterize the display style of the key point; The step of determining the point cloud data of the first object according to the camera parameters includes: For a third image in the material image, generating a reconstructed image based on the third image and the camera parameters by a scene reconstruction network; According to the difference between the reconstructed image and the third image, adjusting the parameters of the scene reconstruction network to obtain a trained scene reconstruction network; For each of the at least one key point, predicting based on the position information of the key point by the trained scene reconstruction network to generate photometric information of the key point; Based on the photometric information of the key points and the position information of the key points, point cloud data of the first object is determined.

15. The method according to claim 9, after performing key point recognition on the material image to generate point cloud data of the first object, further comprising: Performing plane fitting based on the point cloud data to identify background points, where the background points refer to plane key points in the three-dimensional space that are unrelated to the first object; Based on the point cloud data, outlier identification is performed to determine at least one outlier point, wherein the outlier point is a point in the image of the first The object is the noise caused by environmental factors; Eliminating the background points and the outlier points from the point cloud data to obtain processed point cloud data; The processed point cloud data is used for three-dimensional reconstruction.

16. A device for creating a three-dimensional navigation vehicle logo, comprising: A material acquisition module, configured to display a material image of a first object in an image acquisition interface in response to an operation of acquiring an image; wherein the material 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, configured to display a three-dimensional navigation vehicle logo of the first object, wherein the three-dimensional navigation vehicle logo is obtained by three-dimensionally reconstructing the first object based on the material image; The vehicle logo adjustment module is used to display the adjusted three-dimensional navigation vehicle logo in response to the operation of adjusting the display style of the three-dimensional navigation vehicle logo, and the adjusted three-dimensional navigation vehicle logo is used to be displayed in the navigation interface.

17. A device for creating a three-dimensional navigation vehicle logo, the device comprising: A material acquisition module, configured to acquire material images of a first object; wherein the material 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, used to identify key points of the material image and determine point cloud data of the first object, wherein the point cloud data is used to describe the position and display style of the key points of the first object in the real environment; a three-dimensional reconstruction module, configured to perform three-dimensional reconstruction based on the point cloud data, and determine a surface texture of the first object, wherein the surface texture is used to reflect a surface material of the first object; The vehicle logo creation module is used to perform texture mapping on the point cloud data according to the surface texture of the first object to create a three-dimensional navigation vehicle logo of the first object, and the three-dimensional navigation vehicle logo is used to be displayed in the navigation interface.

18. A computer device, comprising a processor and a memory, wherein the memory stores a computer program, and the computer program is loaded and executed by the processor to implement the method for creating a three-dimensional navigation vehicle logo as described in any one of claims 1 to 8, or to implement the method for creating a three-dimensional navigation vehicle logo as described in any one of claims 9 to 15.

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

20. A computer program product, comprising a computer program, wherein the computer program is stored in a computer-readable storage medium, and a processor reads and executes the computer program from the computer-readable storage medium to implement the method for creating a three-dimensional navigation vehicle logo as described in any one of claims 1 to 8, or to implement the method for creating a three-dimensional navigation vehicle logo as described in any one of claims 9 to 15.

Images