Three-dimensional entity positioning method and device, electronic equipment and readable medium

Abstract

The embodiment of the invention discloses a three-dimensional entity positioning method and device, electronic equipment and a readable medium. One specific embodiment of the method comprises the following steps: performing image rendering processing under each pose on each three-dimensional entity in at least one three-dimensional entity in a pre-created neural radiation field scene model to obtain a pose image data pair set; storing each obtained pose image data pair set in a preset database; in response to a received to-be-positioned entity image sent by the preset terminal device, generating positioning pose information corresponding to the to-be-positioned entity image based on the to-be-positioned entity image and each pose image data pair set stored in the preset database; and based on the positioning pose information and the neural radiation field scene model, displaying positioning entity state information of a three-dimensional entity corresponding to the to-be-positioned entity image in the neural radiation field scene model in a preset terminal device. According to the embodiment, the waste of computing power resources is reduced.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technology, and more particularly to a three-dimensional entity positioning method, apparatus, electronic device, and computer-readable medium. Background Art

[0002] With the rise of virtual reality technology, visual positioning technology has further developed. Three-dimensional entity positioning is a technology for locating three-dimensional entities. Currently, the common method for locating three-dimensional entities is to place virtual entities on a pre-built map and then display the located three-dimensional entities on the map displayed on a display (for example, AR glasses or other electronic devices) to achieve visual positioning of the three-dimensional entities.

[0003] However, when using the above method to locate a three-dimensional entity, the following technical problems often occur:

[0004] Virtual entities are placed on a pre-built map, and the three-dimensional entities are displayed and positioned on the map displayed on the display end (for example, AR glasses or other electronic devices) to achieve visual positioning of the three-dimensional entities. Since virtual entities are placed on a pre-built map, the operator who builds the map and the operator who places the virtual objects are usually not the same person. There is a deviation between the position of the virtual object on the map and the position of the entity corresponding to the virtual object in the real three-dimensional space, resulting in low accuracy of the three-dimensional entity positioning and the need for repositioning. At the same time, during the map digitization process, it is easy to miss some entities or repeat the entry of some entities, resulting in omissions or duplications in the placement of virtual entities on the map, resulting in an increase in the number of positioning failures, and the need to re-enter the entities on the map and re-position the entities, resulting in a waste of computing resources.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the Invention

[0006] The content of this disclosure is used to briefly introduce concepts that will be described in detail in the detailed description section below. The content of this disclosure is not intended to identify key features or essential features of the claimed technical solution, nor is it intended to limit the scope of the claimed technical solution.

[0007] Some embodiments of the present disclosure provide a three-dimensional entity positioning method, apparatus, electronic device, and computer-readable medium to solve one or more of the technical problems mentioned in the above background technology section.

[0008] In a first aspect, some embodiments of the present disclosure provide a three-dimensional entity positioning method, the method comprising: performing image rendering processing in various postures on each three-dimensional entity of at least one three-dimensional entity in a pre-created neural radiation field scene model to obtain a posture image data pair set; storing the obtained posture image data pair sets in a preset database; in response to receiving an entity image to be positioned sent by a preset terminal device, generating positioning posture information corresponding to the entity image to be positioned based on the entity image to be positioned and the posture image data pair sets stored in the preset database; based on the positioning posture information and the neural radiation field scene model, displaying the positioning entity status information of the three-dimensional entity corresponding to the entity image to be positioned in the neural radiation field scene model in the preset terminal device.

[0009] In a second aspect, some embodiments of the present disclosure provide a three-dimensional entity positioning device, the device comprising: an image rendering unit, configured to perform image rendering processing in various postures on each three-dimensional entity in at least one three-dimensional entity in a pre-created neural radiation field scene model to obtain a posture image data pair set; a storage unit, configured to store the obtained posture image data pair sets in a preset database; a generation unit, configured to, in response to receiving an entity image to be positioned sent by a preset terminal device, generate positioning posture information corresponding to the entity image to be positioned based on the entity image to be positioned and the posture image data pair sets stored in the preset database; a display unit, configured to display the positioning entity status information of the three-dimensional entity corresponding to the entity image to be positioned in the neural radiation field scene model in the preset terminal device based on the positioning posture information and the neural radiation field scene model.

[0010] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by one or more processors, the one or more processors implement the method described in any implementation of the first aspect above.

[0011] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation of the first aspect is implemented.

[0012] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the three-dimensional entity positioning method of some embodiments of the present disclosure, the accuracy of three-dimensional entity positioning is improved. Specifically, the reason for the waste of computing power resources is that: virtual entities are placed on a pre-constructed map, and the three-dimensional entities are displayed and positioned on the map displayed by the display end (for example, AR glasses or other electronic devices) to achieve visual positioning of the three-dimensional entities. Since the virtual entities are placed on the pre-constructed map, the operator who constructs the map and the operator who places the virtual objects are usually not the same person. There is a deviation between the position of the virtual object on the map and the position of the entity corresponding to the virtual object in the real three-dimensional space, resulting in low accuracy of three-dimensional entity positioning and the need for repositioning. At the same time, in the process of map digitization, it is easy to miss some entities or repeat some entities, resulting in omissions or duplications in the placement of virtual entities on the map, resulting in an increase in the number of positioning failures, and the need to re-enter the entities on the map and re-position the entities, resulting in a waste of computing power resources. Based on this, the three-dimensional entity positioning method of some embodiments of the present disclosure, first, performs image rendering processing on each three-dimensional entity in at least one three-dimensional entity in a pre-created neural radiation field scene model in each posture to obtain a set of posture image data pairs. Thus, a set of pose image data pairs for each three-dimensional entity is obtained using the pre-constructed neural radiation field scene model. Because the neural radiation field scene model can more accurately represent the real-world three-dimensional scene and align virtual entities with the real-world three-dimensional scene, it reduces positional deviations caused by different operators constructing maps and placing virtual entities, and reduces the possibility of missing or duplicating virtual entities. The obtained sets of pose image data pairs are then stored in a preset database. Thus, the sets of pose image data pairs for each three-dimensional entity in the neural radiation field scene model can be stored in the preset database. Next, in response to receiving an image of the entity to be located from a preset terminal device, positioning pose information corresponding to the image of the entity to be located is generated based on the image of the entity to be located and the sets of pose image data pairs stored in the preset database. Thus, the positioning pose information of the entity to be located is obtained. Then, based on the positioning pose information and the neural radiation field scene model, positioning entity status information of the three-dimensional entity corresponding to the image of the entity to be located in the neural radiation field scene model is displayed on the preset terminal device. Thus, positioning status information representing the positioning entity in the real-world three-dimensional scene can be displayed on the preset terminal. Also, because the three-dimensional entity is positioned through the pre-built neural radiation field scene model, the positioning state information representing the positioned entity in the real-world three-dimensional scene is generated.The pre-built neural radiation field scene model can align virtual entities with real-world three-dimensional scenes, reducing the positional deviation between virtual entities and three-dimensional entities in real three-dimensional scenes, reducing the possibility of omission or duplication of virtual entities, and reducing the waste of computing resources due to positioning failure and re-positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0014] Figure 1 is a flow chart of some embodiments of the three-dimensional entity positioning method according to the present disclosure;

[0015] Figure 2 is a schematic structural diagram of other embodiments of the three-dimensional entity positioning method according to the present disclosure;

[0016] Figure 3 is a schematic structural diagram of some embodiments of the three-dimensional entity positioning device according to the present disclosure;

[0017] Figure 4 is a schematic structural diagram of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0018] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0019] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure may be combined with each other.

[0020] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0021] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0022] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0023] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0024] Figure 1 A process 100 of some embodiments of a three-dimensional entity positioning method according to the present disclosure is shown. The three-dimensional entity positioning method includes the following steps:

[0025] Step 101 : performing image rendering processing at various postures on each three-dimensional entity in at least one three-dimensional entity in a pre-created neural radiation field scene model to obtain a posture image data pair set.

[0026] In some embodiments, the execution entity (e.g., a server) of the three-dimensional entity positioning method can perform image rendering processing at various poses for each three-dimensional entity in at least one three-dimensional entity in a pre-created neural radiation field scene model, thereby obtaining a set of pose-image data pairs. The execution entity can be a server that locates the entity in the image of the entity to be positioned based on the image of the entity to be positioned. The pre-constructed neural radiation field scene model can be a three-dimensional reconstruction model. In practice, the execution entity can obtain each sample pose information and a sample scene graph corresponding to each sample pose information in the sample pose information. Then, each sample pose information in the sample pose information is used as the input of the initial neural network, and the sample scene graph corresponding to each sample pose information in the sample pose information is used as the expected output of the initial neural network to train a neural radiation field model. Thereafter, the execution entity can use the neural radiation field model to render each image from each perspective. Then, the execution entity can construct a neural radiation field scene model based on each image from each perspective using three-dimensional reconstruction technology (e.g., Instant NeRF technology). The sample scene graph can be an image of the three-dimensional scene in which the three-dimensional entity to be positioned resides. The above-mentioned initial neural network can be a multilayer perceptron neural network (Multilayer Perceptron, MLP). Each sample pose information in the above-mentioned sample pose information can represent the position and orientation of the camera that collects the sample scene graph in three-dimensional space. The above-mentioned three-dimensional entity can be a three-dimensional object in a three-dimensional scene or a partial scene in a three-dimensional scene. In practice, the above-mentioned execution subject can use three-dimensional rendering technology to render the three-dimensional entity under the above-mentioned pose information according to each pose information in the preset pose information set to obtain a rendered image. Then, the above-mentioned execution subject can determine the above-mentioned pose information and the above-mentioned rendered image as a pose image data pair. Finally, the above-mentioned execution subject can determine the obtained pose image data pairs as a pose image data pair set. Among them, the above-mentioned pose information can represent the pose for rendering the three-dimensional entity.

[0027] In some optional implementations of some embodiments, the neural radiation field scene model is created by the following steps:

[0028] The first step is to obtain scene point cloud data. In practice, the execution entity can obtain scene point cloud data from a preset database. Alternatively, the execution entity can obtain scene point cloud data by scanning the 3D scene where the 3D entity is located using a laser radar.

[0029] The second step is to create an initial neural radiation field scene model based on the above scene point cloud data. In practice, the above execution entity can use 3DGS (3D Gaussian Splatting) technology to create a three-dimensional model as the initial neural radiation field scene model based on the above scene point cloud data. The above scene point cloud data can be the point cloud data of the three-dimensional scene where the three-dimensional entity to be located is located (for example, laser radar (LiDAR) point cloud data).

[0030] The third step is to perform scene editing processing on the above-mentioned initial neural radiation field scene model to obtain an augmented reality scene model. In practice, first, the above-mentioned execution subject can call the preset scene editing interface to add the pre-created three-dimensional object model (for example, virtual furniture, virtual decorations) into the above-mentioned initial neural radiation field scene model. Then, the above-mentioned execution subject can determine the initial neural radiation field scene model with the added three-dimensional object model as the augmented reality scene model. Among them, the above-mentioned preset scene editing interface can be an interface for adding a three-dimensional model to a three-dimensional scene model (for example, a Unity3D interface).

[0031] The fourth step is to determine the above-mentioned augmented reality scene model as a neural radiation field scene model.

[0032] In some optional implementations of some embodiments, the execution entity may perform image rendering processing on the three-dimensional entity at various postures through the following steps to obtain a set of posture image data pairs:

[0033] The first step is to establish a three-dimensional space coordinate system with the center point of the above three-dimensional entity as the coordinate origin.

[0034] In the second step, based on the preset step parameter information and the three-dimensional spatial coordinate system, image rendering processing is performed on the three-dimensional entity at various poses to obtain a set of pose image data pairs. The preset step parameter information includes starting rendering pose information, horizontal angle interval information, pitch angle interval information, and sphere radius information. Each pose image data pair in the pose image data pair set includes rendering pose information and a rendered image. The starting rendering pose information may indicate the pose at which the three-dimensional entity is rendered. For example, the starting rendering pose information may be "horizontal angle 0 degrees, pitch angle 0 degrees, distance from the coordinate origin 10 meters." The horizontal angle interval information may indicate the horizontal interval angle for rendering the three-dimensional entity in the horizontal direction, for example, "5 degrees." The pitch angle interval information may indicate the vertical interval angle for rendering the three-dimensional entity in the vertical direction, for example, "5 degrees."

[0035] When generating a pose image data pair set for a three-dimensional entity, it is usually performed directly using various preset rendering poses within a rotation range around the y-axis (vertical axis) where the center point of the three-dimensional entity is located and the pitch angle is a preset value (for example, 0 degrees) to obtain a pose image data pair set of different sides of the three-dimensional entity during the horizontal rotation process. Only the pose image data pair sets of different sides of the three-dimensional entity during the horizontal rotation process are considered. When the collected image of the entity to be positioned is not a side image of the three-dimensional entity during the horizontal rotation process (for example, a view directly above or directly below the three-dimensional entity), it may result in a failure to match the pose image data pair corresponding to the image of the entity to be positioned, thereby increasing the number of failures in three-dimensional entity positioning, the number of times the three-dimensional entity is re-positioned, and the waste of computer computing resources.

[0036] Faced with the above technical problems, we decided to adopt the following solutions:

[0037] In some optional implementations of some embodiments, the execution entity may perform image rendering processing on the three-dimensional entity at various postures based on preset step parameter information and the three-dimensional space coordinate system through the following steps to obtain a set of posture image data pairs:

[0038] The first step is to determine the starting point rendering posture information included in the preset step parameter information, wherein the starting point rendering posture information includes: the starting point horizontal angle and the starting point pitch angle.

[0039] The second step is to determine the above starting point horizontal angle as the initial horizontal angle.

[0040] The third step is to perform the following traversal steps based on the above initial horizontal angle:

[0041] In the first sub-step, the starting pitch angle is determined as the initial pitch angle.

[0042] The second sub-step, based on the initial pitch angle, performs the following generation steps:

[0043] In sub-step one, the sphere radius corresponding to the sphere radius information is determined as the observation distance.

[0044] Sub-step 2: generating a pair of pose image data corresponding to the three-dimensional entity based on the initial horizontal angle, the initial pitch angle and the observation distance.

[0045] Sub-step three: generating an updated pitch angle based on the initial pitch angle and the pitch angle interval information. In practice, the execution entity may determine the updated pitch angle as the sum of the initial pitch angle and the vertical interval angle represented by the pitch angle interval information.

[0046] In sub-step four, the updated pitch angle is determined as the initial pitch angle to update the initial pitch angle.

[0047] Sub-step 5: In response to the updated initial pitch angle being less than or equal to the first preset angle, the generating step is performed again based on the updated initial pitch angle. The first preset angle may be 90 degrees. The initial pitch angle may range from -90 degrees to 90 degrees.

[0048] Sub-step six: In response to determining that the updated initial pitch angle is greater than the first preset angle, generating an updated horizontal angle based on the initial horizontal angle and the horizontal angle interval information. In practice, the execution entity may determine the updated horizontal angle as the sum of the initial horizontal angle and the horizontal angle interval corresponding to the horizontal angle interval information. The updated horizontal angle may range from 0 degrees to 360 degrees.

[0049] In a third sub-step, in response to determining that the updated horizontal angle is less than or equal to a second preset angle, the updated horizontal angle is updated to the initial horizontal angle, and the traversal step is performed again based on the updated initial horizontal angle. The second preset angle may be 360 ​​degrees.

[0050] In the fourth step, in response to determining that the updated horizontal angle is greater than the second preset angle, the generated pose image data pairs are determined as a pose image data pair set.

[0051] The above technical solution and its related contents, as an inventive point of an embodiment of the present disclosure, solve the technical problem of "increased waste of computer computing resources". The factors that lead to the increase of computer computing resources are often as follows: when generating a set of pose image data pairs for a three-dimensional entity, it is usually directly rendered with various preset rendering poses within a rotation range of the y-axis (vertical axis) around the center point of the three-dimensional entity and a pitch angle of a preset value (for example, 0 degrees), to obtain a set of pose image data pairs of different sides of the three-dimensional entity during the horizontal rotation process. Only the pose image data pairs of different sides of the three-dimensional entity during the horizontal rotation process are considered. When the collected image of the entity to be positioned is not a side image of the three-dimensional entity during the horizontal rotation process (for example, a view directly above or directly below the three-dimensional entity), it may result in a failure to match the pose image data pair corresponding to the image of the entity to be positioned, thereby increasing the number of failures in three-dimensional entity positioning, the number of times the three-dimensional entity is re-positioned, and the waste of computer computing resources. If the above factors are solved, the effect of reducing the increase in computer computing resources can be achieved. To achieve this effect, first, the starting rendering pose information included in the above-mentioned preset step parameter information is determined. The starting rendering pose information includes: a starting horizontal angle and a starting pitch angle. The starting horizontal angle is then determined as the initial horizontal angle. This yields the initial horizontal angle used for traversal. The following traversal steps are then performed based on the initial horizontal angle: First, the starting pitch angle is determined as the initial pitch angle. This yields the initial pitch angle used to determine the rendering pose information. Second, based on the initial pitch angle, the following generation steps are performed: Sub-step 1: The radius of the sphere corresponding to the sphere radius information is determined as the observation distance. Sub-step 2: Based on the initial horizontal angle, the initial pitch angle, and the observation distance, a pair of pose image data corresponding to the three-dimensional entity is generated. This yields a pair of pose image data for the three-dimensional entity on the side of the rendering pose information. Based on the initial pitch angle and the pitch angle interval information, an updated pitch angle is generated. This yields an updated pitch angle used to repeat the generation step. The updated pitch angle is determined as the initial pitch angle to update the initial pitch angle. In response to the updated initial pitch angle being less than or equal to the first preset angle, the generating step is performed again based on the updated initial pitch angle. In response to determining that the updated initial pitch angle is greater than the first preset angle, an updated horizontal angle is generated based on the initial horizontal angle and the horizontal angle interval information. Thus, an updated horizontal angle can be generated when the updated initial pitch angle is greater than the first preset angle. In response to determining that the updated horizontal angle is less than or equal to the second preset angle, the updated horizontal angle is updated to the initial horizontal angle, and the traversing step is performed again based on the updated initial horizontal angle. Thus, the initial horizontal angle can be updated and the traversing step can be performed again.In response to determining that the updated horizontal angle is greater than the second preset angle, the generated pose image data pairs are determined as pose image data pair sets. Thus, pose image data pairs covering different sides of the three-dimensional entity during horizontal rotation in three-dimensional space and at different pitch angles are generated. These pose image pairs show comprehensive views of the three-dimensional entity from top to bottom and at different tilt angles, and are not limited to pose images of different sides of the three-dimensional entity during horizontal rotation, thereby improving the comprehensiveness of pose coverage. Even if the collected image of the entity to be positioned is not a side image of the three-dimensional entity during horizontal rotation (for example, a view directly above or directly below the three-dimensional entity), it is possible to match the pose image data pair corresponding to the image of the entity to be positioned through a pose image data pair set that covers the three-dimensional entity from top to bottom and at different tilt angles with a more comprehensive pose coverage. The number of failed three-dimensional entity positioning is reduced, the number of three-dimensional entity positioning operations is reduced, and the waste of computer computing resources is reduced.

[0052] In some optional implementations of some embodiments, the execution entity may generate a pair of pose image data corresponding to the three-dimensional entity based on the initial horizontal angle, the initial pitch angle, and the observation distance through the following steps:

[0053] The first step is to generate the coordinate information of the observation point in the three-dimensional space coordinate system based on the initial horizontal angle, the initial pitch angle, and the observation distance. In practice, the execution entity may determine the cosine value of the initial pitch angle as the first value, the cosine value of the initial horizontal angle as the second value, the product of the observation distance and the first value as the first product, and the product of the first product and the second value as the horizontal coordinate value. The execution entity may determine the sine value of the initial horizontal angle as the third value, and the product of the first product and the third value as the vertical coordinate value. The execution entity may determine the sine value of the initial pitch angle as the fourth value, and the product of the observation distance and the fourth value as the vertical coordinate value. Then, the execution entity may determine the horizontal coordinate value, the vertical coordinate, and the vertical coordinate as the coordinate information of the observation point in the three-dimensional space coordinate system. The observation point may be a rendering point (i.e., the point where the center of the virtual camera lens is located when rendering (equivalent to shooting or observation)).

[0054] In the second step, the coordinate information, initial pitch angle, and initial horizontal angle are determined as rendering pose information.

[0055] The third step is to render the 3D entity based on the rendering pose information to obtain a rendered image. In practice, the execution subject can render the 3D entity using 3D rendering technology to obtain a 2D image of the 3D entity in the pose corresponding to the rendering pose information as the rendered image.

[0056] In the fourth step, the rendering pose information and the rendered image are determined as a pose-image data pair.

[0057] Step 102: storing the obtained pose image data pairs into a preset database.

[0058] In some embodiments, the execution entity may store the obtained pose image data pairs in a preset database, for example, a MySQL database, a NoSQL database, etc.

[0059] Step 103 : In response to receiving the image of the entity to be located sent by the preset terminal device, generating positioning posture information corresponding to the image of the entity to be located based on the image of the entity to be located and each posture image data pair set stored in the preset database.

[0060] In some embodiments, the execution entity may, in response to receiving an image of the entity to be located from a preset terminal device, generate positioning pose information corresponding to the image of the entity to be located based on the image of the entity to be located and the various pose image data pairs stored in the preset database. In practice, the execution entity may determine the various rendered images included in the various pose image data pairs as the various rendered images to be matched. The execution entity may then use an image feature extraction algorithm (e.g., a HOG feature extraction algorithm) to extract the various image feature information of the rendered images to be matched as the various rendered image feature information to be matched. Thereafter, the execution entity may use an image feature extraction algorithm to extract the image feature information of the entity to be located as the various image feature information to be matched. The execution entity may then determine the similarity between the image feature information of the entity to be located and the various rendered image feature information to be matched as the various matching similarities. The execution entity may then determine the matching similarity with the greatest similarity value among the various matching similarities as the target matching similarity. Thereafter, the execution entity may determine the pose image data pair corresponding to the rendered image to be matched corresponding to the target matching similarity as the target pose image data pair. Finally, the above-mentioned execution entity can determine the rendering pose information included in the above-mentioned target pose image data pair as the positioning pose information corresponding to the above-mentioned entity image to be positioned. Among them, the above-mentioned entity image feature information to be positioned can be represented by a feature vector (for example, a HOG feature vector). Each of the above-mentioned rendering image feature information to be matched can be represented by a feature vector. The above-mentioned preset terminal device can be a mobile terminal (such as a head-mounted display device, a mobile phone, a tablet, etc.). The above-mentioned head-mounted display device can include but is not limited to one of the following: AR glasses, VR glasses, and MR glasses.

[0061] In some optional implementations of some embodiments, the execution entity may generate positioning pose information corresponding to the image of the entity to be positioned based on the image of the entity to be positioned and each pose image data pair set stored in the preset database through the following steps:

[0062] The first step is to match the pose image data pair corresponding to the above-mentioned entity image to be located from the above-mentioned pose image data pair sets as the matching pose image data pair. In practice, the above-mentioned execution entity can determine the entity image to be located as the template image. Then, the above-mentioned execution entity can use the template matching technology to compare the various rendered images included in the above-mentioned pose image data pair sets with the above-mentioned template image, and determine the rendered image that is most similar to the template image among the various rendered images as the target rendered image. Then, the above-mentioned execution entity can determine the pose image data pair containing the above-mentioned target rendered image in the various pose image data pair sets as the target pose image data pair. Afterwards, the above-mentioned execution entity can determine the above-mentioned target pose image data pair as the matching pose image data pair.

[0063] In the second step, the rendered image included in the matching pose image data is positioned to obtain the rendered image.

[0064] In the third step, in response to determining that there is no corresponding scene point cloud data for the three-dimensional entity corresponding to the above-mentioned positioning rendering image, the rendering pose information included in the above-mentioned matching pose image data pair is determined as the positioning pose information.

[0065] In some optional implementations of some embodiments, the above execution entity may further perform the following steps:

[0066] In response to determining that scene point cloud data corresponding to the three-dimensional entity corresponding to the positioning rendered image exists, positioning pose information is generated based on the image of the entity to be positioned and the scene point cloud data. In practice, the execution entity may perform feature point extraction processing on the image of the entity to be positioned using a SIFT algorithm to obtain an image feature point information set. The image feature point information in the image feature point information set may represent image feature points in the image of the entity to be positioned. The image feature point information may include, but is not limited to, the following: two-dimensional coordinates and intensity information. The intensity information may represent the color value of the image feature point. The execution entity may perform point cloud feature point extraction processing on the scene point cloud data using a key point extraction algorithm (e.g., SIFT (Scale-Invariant Feature Transform) key point detection, SUSAN (Smallest Univalue Segment Assimilating Nucleus) key point detection, etc.) to obtain a point cloud feature point information set. Each point cloud feature point information in the point cloud feature point information set may represent a feature point at a respective spatial point corresponding to the scene point cloud data. The point cloud feature point information may include, but is not limited to, the following: three-dimensional coordinates, texture information, and color value information. The execution entity may then input the image feature point information group and the point cloud feature point information set into a pre-trained feature point matching model to obtain matching feature point information groups. Each of the matching feature point information groups includes one image feature point and one point cloud feature point. The feature point matching model may be a feature matching network SuperGlue model. For each of the matching feature point information groups, the execution entity may determine the two-dimensional and three-dimensional coordinates included in the matching feature point information group as position correspondence information. The execution entity may then generate positioning pose information for the image of the entity to be located based on the obtained position correspondence information using a PnP algorithm. The positioning pose information may indicate the position and orientation of the acquisition device used to acquire the image of the entity to be located in three-dimensional space when acquiring the image of the entity to be located. The color value information may indicate the color value of the spatial point corresponding to the point cloud feature point information.

[0067] Therefore, when the three-dimensional entity corresponding to the positioning rendering image has corresponding scene point cloud data, the positioning pose information of the image of the entity to be positioned with higher accuracy can be generated by the image of the entity to be positioned and the scene point cloud data.

[0068] Step 104 : Based on the positioning posture information and the neural radiation field scene model, the positioning entity state information of the three-dimensional entity corresponding to the entity image to be positioned in the neural radiation field scene model is displayed in a preset terminal device.

[0069] In some embodiments, the above-mentioned execution entity can display the positioning entity status information of the three-dimensional entity corresponding to the above-mentioned entity image to be positioned in the above-mentioned neural radiation field scene model in the above-mentioned preset terminal device based on the above-mentioned positioning posture information and the above-mentioned neural radiation field scene model.

[0070] In some optional implementations of some embodiments, the execution entity may display, on the preset terminal device, positioning entity state information of the three-dimensional entity corresponding to the entity image to be positioned in the neural radiation field scene model based on the positioning posture information and the neural radiation field scene model through the following steps:

[0071] The first step is to determine the pose image data pair corresponding to the above positioning pose information.

[0072] In the second step, the three-dimensional entity corresponding to the above-mentioned posture image data pair in the above-mentioned neural radiation field scene model is determined as the positioning three-dimensional entity.

[0073] The third step is to determine the model data of the located three-dimensional entity as the model data to be sent.

[0074] In the fourth step, the model data to be sent, the positioning posture information, and the preset posture floating range information are sent to the preset terminal device, so that the preset terminal device can display the positioning entity state information of the three-dimensional entity corresponding to the above-mentioned entity image to be positioned in the above-mentioned neural radiation field scene model. The positioning entity state information can be a display representing the positioning entity (i.e., the three-dimensional object or scene in the model) within the preset posture range. The preset posture range can be a floating posture range that includes the posture corresponding to the positioning posture information. As an example, the positioning posture information can be "x coordinate is 10m, y coordinate is 0m, z coordinate is 0m, horizontal angle is 0 degrees, pitch angle: 0 degrees". The floating posture range can be a range of ±2° left and right floating range of the horizontal angle and ±1° floating range of the pitch angle at the spatial point (x coordinate is 10m, y coordinate is 0m, z coordinate is 0m).

[0075] Thus, the positioning entity (ie, the three-dimensional object or scene in the model) within the preset posture range can be displayed in the preset terminal device.

[0076] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the three-dimensional entity positioning method of some embodiments of the present disclosure, the accuracy of three-dimensional entity positioning is improved. Specifically, the reason for the waste of computing power resources is that: virtual entities are placed on a pre-constructed map, and the three-dimensional entities are displayed and positioned on the map displayed by the display end (for example, AR glasses or other electronic devices) to achieve visual positioning of the three-dimensional entities. Since the virtual entities are placed on the pre-constructed map, the operator who constructs the map and the operator who places the virtual objects are usually not the same person. There is a deviation between the position of the virtual object on the map and the position of the entity corresponding to the virtual object in the real three-dimensional space, resulting in low accuracy of three-dimensional entity positioning and the need for repositioning. At the same time, in the process of map digitization, it is easy to miss some entities or repeat some entities, resulting in omissions or duplications in the placement of virtual entities on the map, resulting in an increase in the number of positioning failures, and the need to re-enter the entities on the map and re-position the entities, resulting in a waste of computing power resources. Based on this, the three-dimensional entity positioning method of some embodiments of the present disclosure, first, performs image rendering processing on each three-dimensional entity in at least one three-dimensional entity in a pre-created neural radiation field scene model in each posture to obtain a set of posture image data pairs. Thus, a set of pose image data pairs for each three-dimensional entity is obtained using the pre-constructed neural radiation field scene model. Because the neural radiation field scene model can more accurately represent the real-world three-dimensional scene and align virtual entities with the real-world three-dimensional scene, it reduces positional deviations caused by different operators constructing maps and placing virtual entities, and reduces the possibility of missing or duplicating virtual entities. The obtained sets of pose image data pairs are then stored in a preset database. Thus, the sets of pose image data pairs for each three-dimensional entity in the neural radiation field scene model can be stored in the preset database. Next, in response to receiving an image of the entity to be located from a preset terminal device, positioning pose information corresponding to the image of the entity to be located is generated based on the image of the entity to be located and the sets of pose image data pairs stored in the preset database. Thus, the positioning pose information of the entity to be located is obtained. Then, based on the positioning pose information and the neural radiation field scene model, positioning entity status information of the three-dimensional entity corresponding to the image of the entity to be located in the neural radiation field scene model is displayed on the preset terminal device. Thus, positioning status information representing the positioning entity in the real-world three-dimensional scene can be displayed on the preset terminal. Also, because the three-dimensional entity is positioned through the pre-built neural radiation field scene model, the positioning state information representing the positioned entity in the real-world three-dimensional scene is generated.The pre-built neural radiation field scene model can align virtual entities with real-world three-dimensional scenes, reducing the positional deviation between virtual entities and three-dimensional entities in real three-dimensional scenes, reducing the possibility of omission or duplication of virtual entities, and reducing the waste of computing resources due to positioning failure and re-positioning.

[0077] Further references Figure 2 , which shows a process 200 of another embodiment of a virtual item distribution method. The process 200 of the three-dimensional entity positioning method includes the following steps:

[0078] Step 201: Acquire scene point cloud data.

[0079] In some embodiments, the above-mentioned execution entity can obtain scene point cloud data.

[0080] Step 202: Create an initial neural radiation field scene model based on the scene point cloud data.

[0081] In some embodiments, the execution entity may create an initial neural radiation field scene model based on the scene point cloud data.

[0082] Step 203: Perform scene editing processing on the initial neural radiation field scene model to obtain an augmented reality scene model.

[0083] In some embodiments, the execution entity may perform scene editing processing on the initial neural radiation field scene model to obtain an augmented reality scene model.

[0084] Step 204: Determine the augmented reality scene model as a neural radiation field scene model.

[0085] In some embodiments, the execution entity may determine the augmented reality scene model as a neural radiation field scene model.

[0086] Step 205 : performing image rendering processing at various postures on each of at least one three-dimensional entity in the pre-created neural radiation field scene model to obtain a posture image data pair set.

[0087] Step 206: Store the obtained pose image data pairs into a preset database.

[0088] Step 207 : In response to receiving the image of the entity to be located sent by the preset terminal device, generating positioning posture information corresponding to the image of the entity to be located based on the image of the entity to be located and each posture image data pair set stored in the preset database.

[0089] Step 208 : Based on the positioning posture information and the neural radiation field scene model, the positioning entity state information of the three-dimensional entity corresponding to the entity image to be positioned in the neural radiation field scene model is displayed in a preset terminal device.

[0090] In from Figure 2 It can be seen that Figure 1 Compared with the description of some corresponding embodiments, Figure 2 The process 200 of the three-dimensional entity positioning method in some corresponding embodiments reflects the creation of an initial neural radiation field scene model through scene point cloud data. The initial neural radiation field scene model is subjected to scene editing processing to obtain an augmented reality scene model as a neural radiation field scene model. By performing scene editing processing on the initial neural radiation field scene model, various virtual objects, such as virtual furniture, virtual decorations, etc., can be added to the initial neural radiation field scene model, thereby enhancing the interactivity and realism of the neural radiation field scene model. Users can place specific virtual objects in the initial neural radiation field scene model according to their needs, and superimpose the virtual scene on the real scene, thereby achieving an augmented reality effect.

[0091] In some embodiments, the specific implementation of steps 205-208 and the resulting technical effects can be referred to Figure 1 The corresponding steps 101-104 in the embodiments are not described in detail here.

[0092] Further references Figure 3 As an implementation of the methods shown in the figures, the present disclosure provides some embodiments of a three-dimensional entity positioning device. These device embodiments are similar to Figure 1 Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.

[0093] like Figure 3As shown, in some embodiments, the three-dimensional entity positioning device 300 includes: an image rendering unit 301, a storage unit 302, a generation unit 303, and a display unit 304. The image rendering unit 301 is configured to perform image rendering processing on each three-dimensional entity in at least one three-dimensional entity in a pre-created neural radiation field scene model in various postures to obtain a posture image data pair set; the storage unit 302 is configured to store the obtained posture image data pair sets in a preset database; the generation unit 303 is configured to, in response to receiving an image of an entity to be positioned sent by a preset terminal device, generate positioning posture information corresponding to the image of the entity to be positioned based on the image of the entity to be positioned and the posture image data pair sets stored in the preset database; the display unit 304 is configured to display, on the preset terminal device, positioning entity state information of the three-dimensional entity corresponding to the image of the entity to be positioned in the neural radiation field scene model based on the positioning posture information and the neural radiation field scene model.

[0094] It is understood that the units described in the device 300 are similar to those in the reference Figure 1 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the device 300 and the units included therein, and will not be repeated here.

[0095] Reference below Figure 4 , which shows a structural diagram of an electronic device 400 suitable for implementing some embodiments of the present disclosure. Figure 4 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0096] like Figure 4 As shown, the electronic device 400 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 401, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 402 or a program loaded from a storage device 408 into a random access memory (RAM) 403. Various programs and data required for the operation of the electronic device 400 are also stored in the RAM 403. The processing device 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0097] Typically, the following devices may be connected to the I / O interface 405: an input device 406 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 407 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 408 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 409. The communication device 409 may allow the electronic device 400 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 4 The electronic device 400 is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead. Figure 4 Each block shown in the figure may represent one device, or may represent multiple devices as needed.

[0098] In particular, according to some embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, some embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from a network via the communication device 409, or installed from the storage device 408, or installed from the ROM 402. When the computer program is executed by the processing device 401, the functions defined in the methods of some embodiments of the present disclosure are performed.

[0099] It should be noted that the computer-readable medium described in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In some embodiments of the present disclosure, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or device. In some embodiments of the present disclosure, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0100] In some embodiments, the client and server can communicate using any currently known or future developed network protocol, such as HTTP (HyperText Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0101] The computer-readable medium may be included in an electronic device, or may exist independently without being incorporated into the electronic device. The computer-readable medium carries one or more programs, and when the one or more programs are executed by the electronic device, the electronic device is caused to: perform image rendering processing on each of at least one three-dimensional entity in a pre-created neural radiation field scene model in various postures to obtain a set of posture image data pairs; store the obtained sets of posture image data pairs in a preset database; in response to receiving an image of an entity to be positioned sent by a preset terminal device, generate positioning posture information corresponding to the image of the entity to be positioned based on the image of the entity to be positioned and the sets of posture image data pairs stored in the preset database; and based on the positioning posture information and the neural radiation field scene model, display positioning entity status information of the three-dimensional entity corresponding to the image of the entity to be positioned in the neural radiation field scene model on the preset terminal device.

[0102] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0103] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0104] The units described in some embodiments of the present disclosure may be implemented in software or hardware. The units described may also be provided in a processor. For example, they may be described as follows: a processor including an image rendering unit, a storage unit, a generation unit, and a display unit. The names of these units do not, in some cases, constitute limitations on the units themselves. For example, the storage unit may also be described as "storing the obtained sets of pose image data pairs into a preset database."

[0105] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0106] The above descriptions are merely some preferred embodiments of the present disclosure and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of technical features, but should also encompass other technical solutions formed by any combination of technical features or their equivalents without departing from the inventive concept. For example, a technical solution formed by replacing a feature with a technical feature having similar functions as disclosed in the embodiments of the present disclosure (but not limited to) can be formed.

Claims

1. A three-dimensional entity positioning method, comprising: Performing image rendering processing at various positions on each three-dimensional entity of at least one three-dimensional entity in a pre-created neural radiation field scene model to obtain a position image data pair set; The obtained sets of each pose image data pair are stored in a preset database; In response to receiving an image of an entity to be located sent by a preset terminal device, generating positioning posture information corresponding to the image of the entity to be located based on the image of the entity to be located and each pose image data pair set stored in the preset database; Based on the positioning posture information and the neural radiation field scene model, the positioning entity state information of the three-dimensional entity corresponding to the entity image to be positioned in the neural radiation field scene model is displayed in the preset terminal device.

2. The method according to claim 1, wherein: The method further comprises: Get scene point cloud data; Based on the scene point cloud data, creating an initial neural radiation field scene model; Performing scene editing processing on the initial neural radiation field scene model to obtain an augmented reality scene model; The augmented reality scene model is determined as a neural radiation field scene model.

3. The method according to claim 1, wherein: The step of performing image rendering processing at various positions on each of at least one three-dimensional entity in the pre-created neural radiation field scene model to obtain a set of position image data pairs includes: Establishing a three-dimensional space coordinate system with the center point of the three-dimensional entity as the coordinate origin; Based on the preset step parameter information and the three-dimensional space coordinate system, image rendering processing is performed on the three-dimensional entity in various postures to obtain a posture image data pair set, wherein each posture image data pair in the posture image data pair set includes rendering posture information and a rendered image.

4. The method according to claim 3, wherein: The preset step parameter information includes: starting point rendering posture information, horizontal angle interval information, pitch angle interval information, and sphere radius information. Based on the preset step parameter information and the three-dimensional space coordinate system, the three-dimensional entity is subjected to image rendering processing in each posture to obtain a posture image data pair set, including: Determine the starting point rendering posture information included in the preset step parameter information, wherein the starting point rendering posture information includes: a starting point horizontal angle and a starting point pitch angle; Determine the starting point horizontal angle as the initial horizontal angle; Based on the initial horizontal angle, the following traversal steps are performed: The starting pitch angle is determined as the initial pitch angle; Based on the initial pitch angle, the following generation steps are performed: The sphere radius corresponding to the sphere radius information is determined as the observation distance; Based on the initial horizontal angle, the initial pitch angle and the observation distance, a pose image data pair corresponding to the three-dimensional entity is generated; Based on the initial pitch angle and the pitch angle interval information, an updated pitch angle is generated; Determine the updated pitch angle as the initial pitch angle to update the initial pitch angle; In response to the updated initial pitch angle being less than or equal to the first preset angle, executing the generating step again according to the updated initial pitch angle; In response to determining that the updated initial pitch angle is greater than the first preset angle, generating an updated horizontal angle based on the initial horizontal angle and the horizontal angle interval information; In response to determining that the updated horizontal angle is less than or equal to the second preset angle, updating the updated horizontal angle to the initial horizontal angle, and performing the traversal step again according to the updated initial horizontal angle; In response to determining that the updated horizontal angle is greater than the second preset angle, the generated pose image data pairs are determined as a pose image data pair set.

5. The method according to claim 1, wherein: The method of generating a pair of posture image data corresponding to a three-dimensional entity based on an initial horizontal angle, an initial pitch angle and an observation distance comprises: Generate the coordinate information of the observation point in the three-dimensional space coordinate system based on the initial horizontal angle, initial pitch angle and observation distance Determine the coordinate information, initial pitch angle, and initial horizontal angle as rendering pose information; Based on the rendering posture information, the three-dimensional entity is rendered to obtain a rendered image; The rendering pose information and the rendered image are determined as a pose-image data pair.

6. The method according to claim 1, wherein: The generating, based on the entity image to be located and each pose image data pair set stored in the preset database, positioning pose information corresponding to the entity image to be located comprises: Matching a pose image data pair corresponding to the to-be-located entity image from each pose image data pair set as a matching pose image data pair; Determine a positioning rendering image from the rendering image included in the matching pose image data pair; In response to determining that there is no scene point cloud data corresponding to the three-dimensional entity corresponding to the positioning rendered image, the rendering pose information included in the matching pose image data pair is determined as the positioning pose information.

7. The method according to claim 6, wherein: The method further comprises: In response to determining that the three-dimensional entity corresponding to the positioning rendering image has corresponding scene point cloud data, positioning posture information is generated based on the image of the entity to be positioned and the scene point cloud data.

8. The method according to claim 1, wherein: The method of displaying, in the preset terminal device, the positioning entity state information of the three-dimensional entity corresponding to the entity image to be positioned in the neural radiation field scene model based on the positioning posture information and the neural radiation field scene model includes: Determine a pair of posture image data corresponding to the positioning posture information; Determine the three-dimensional entity corresponding to the pose image data pair in the neural radiation field scene model as a positioning three-dimensional entity; Determining the model data of the located three-dimensional entity as the model data to be sent; The model data to be sent, the positioning posture information and the preset posture floating range information are sent to the preset terminal device, so that the preset terminal device can display the positioning entity state information of the three-dimensional entity corresponding to the entity image to be positioned in the neural radiation field scene model.

9. A three-dimensional entity positioning device, comprising: An image rendering unit is configured to perform image rendering processing at various positions on each three-dimensional entity of at least one three-dimensional entity in a pre-created neural radiation field scene model to obtain a position image data pair set; A storage unit, configured to store each obtained set of pose image data pairs into a preset database; A generating unit, configured to generate positioning posture information corresponding to the image of the entity to be located based on the image of the entity to be located and each pose image data pair set stored in the preset database in response to receiving the image of the entity to be located sent by the preset terminal device; The display unit is configured to display, in the preset terminal device, positioning entity state information of the three-dimensional entity corresponding to the entity image to be positioned in the neural radiation field scene model based on the positioning posture information and the neural radiation field scene model.

10. An electronic device comprising: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 8.

11. A computer readable medium having a computer program stored thereon, wherein: When the program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images