Scene restoration method and device, electronic equipment and computer readable medium

Abstract

The embodiment of the invention discloses a scene restoration method and device, electronic equipment and a computer readable medium. A specific embodiment of the method comprises the following steps: storing pre-acquired scene image data; generating pose information of each scene element based on preset point cloud map data and each scene image data; generating each restored picture based on each scene image data and each scene element pose information; for each restored picture in the restored pictures, in response to determining that the restored picture does not meet a preset restoration condition, executing a scene element pose adjustment task to obtain each piece of relocation pose information; and generating a three-dimensional scene space based on the obtained relocation pose information. According to the embodiment, the restoration efficiency of real scene restoration can be improved, and the time cost can be reduced.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technology, and in particular to a scene restoration method, device, electronic device, and computer-readable medium. Background Art

[0002] Real scene restoration is a technology that restores real scenes in the real world to virtual space. At present, when restoring real scenes, the usual method is: first read the real scene data through the camera. Then, the virtual space related to the real scene data is constructed based on the obtained real scene data. By comparing the virtual space with the real scene, the position and posture of each scene element in the virtual space are continuously adjusted, so that the virtual space is completely consistent with the real scene.

[0003] However, when the above method is used to restore the real scene, the following technical problems often occur:

[0004] When comparing the real scene with the virtual space, it is necessary to repeatedly go to the site to optimize and adjust the virtual space, resulting in low efficiency and high time cost when restoring the real scene. When adjusting the virtual space directly by comparing the real scene with the virtual space, some details in the virtual space often deviate from the real scene, resulting in low accuracy in restoring the real scene in the virtual space. Summary of the invention

[0005] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0006] Some embodiments of the present disclosure propose scene restoration methods, devices, electronic devices, and computer-readable media to solve one or more of the technical problems mentioned in the above background technology section.

[0007] In a first aspect, some embodiments of the present disclosure provide a scene restoration method, the method comprising: storing pre-acquired scene image data; generating pose information of scene elements based on preset point cloud map data and the above-mentioned scene image data; generating restoration pictures based on the above-mentioned scene image data and the above-mentioned scene element pose information; for each of the above-mentioned restoration pictures, in response to determining that the restoration picture does not meet the preset restoration conditions, performing a scene element pose adjustment task to obtain repositioning pose information; and generating a three-dimensional scene space based on the obtained repositioning pose information.

[0008] In a second aspect, some embodiments of the present disclosure provide a scene restoration device, comprising: a storage unit configured to store pre-acquired scene image data; a first generation unit configured to generate pose information of each scene element based on preset point cloud map data and the above-mentioned scene image data; a second generation unit configured to generate each restored screen based on the above-mentioned scene image data and the above-mentioned scene element pose information; an execution unit configured to, for each of the above-mentioned restored screens, execute a scene element pose adjustment task in response to determining that the above-mentioned restored screen does not meet a preset restoration condition, and obtain each repositioning pose information; and a third generation unit configured to generate a three-dimensional scene space based on the obtained each repositioning pose information.

[0009] 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 the one or more processors, the one or more processors implement the method described in any implementation manner of the above-mentioned first aspect.

[0010] 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 manner of the above-mentioned first aspect is implemented.

[0011] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the scene restoration method of some embodiments of the present disclosure, the restoration efficiency of the real scene restoration can be improved, the time cost waste can be reduced, and the accuracy of the real scene restoration can be improved. Specifically, the reasons for the low restoration efficiency, high time cost and low accuracy of the real scene restoration are: when comparing the real scene with the virtual space, it is necessary to go to the scene repeatedly to optimize and adjust the virtual space, resulting in low restoration efficiency and high time cost when restoring the real scene. When the virtual space is adjusted directly by comparing the real scene with the virtual space, some details in the virtual space often deviate from the real scene, resulting in low accuracy of restoring the real scene in the virtual space. Based on this, the scene restoration method of some embodiments of the present disclosure, first, stores the pre-acquired image data of each scene. Thus, the image data of the real scene can be obtained so that the real scene can be restored by the image data of the real scene later. Secondly, based on the preset point cloud map data and the above-mentioned image data of each scene, the pose information of each scene element is generated. Thus, the corresponding pose information of the scene elements on the point cloud map in the virtual space can be obtained. Then, based on the above-mentioned scene image data and the pose information of the above-mentioned scene elements, each restoration screen is generated. Thus, the scene elements in the restoration space can be adjusted by the obtained pose information. Then, for each of the restoration screens in the above-mentioned restoration screens, in response to determining that the restoration screen does not meet the preset restoration condition, the scene element pose adjustment task is executed to obtain each repositioning pose information. Thus, when the restoration screen cannot coincide with the corresponding scene image data, the pose of each scene element in the restoration space can be regenerated. Finally, based on the obtained repositioning pose information, a three-dimensional scene space is generated. Thus, the scene elements in the restoration space can be re-adjusted according to the regenerated pose, so that the restoration space is completely consistent with the real scene. Also because when the screen in the restoration space cannot completely coincide with the corresponding scene image data, the pose information of each scene element can be repositioned to re-adjust the pose of each scene element in the restoration space, because the accuracy of restoring the real scene can be improved. Also, the position and posture of each scene element in the restoration space can be adjusted directly by comparing the picture in the restoration space with the corresponding scene image data, without the need for technical personnel to repeatedly go to the site for comparison. This can improve the efficiency of restoring the real scene and reduce time costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying 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.

[0013] Figure 1 is a flow chart of some embodiments of the scene restoration method according to the present disclosure;

[0014] Figure 2 is a flow chart of other embodiments of the scene restoration method according to the present disclosure;

[0015] Figure 3 is a schematic structural diagram of some embodiments of the scene restoration device according to the present disclosure;

[0016] Figure 4 It is the scene graph of point cloud map data;

[0017] Figure 5 It is a page diagram for comparing scene image data and restored images;

[0018] Figure 6 It is the scene graph corresponding to the restored space;

[0019] Figure 7 It is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0020] 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 set forth 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 only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0021] 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 can be combined with each other.

[0022] It should be noted that the concepts such as "first" and "second" mentioned in the present 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.

[0023] 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, it should be understood as "one or more".

[0024] 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.

[0025] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0026] Figure 1 The process 100 of some embodiments of the scene restoration method according to the present disclosure is shown. The scene restoration method comprises the following steps:

[0027] Step 101, storing the pre-acquired image data of each scene.

[0028] In some embodiments, the execution subject (e.g., a computing device) of the scene restoration method may store the pre-acquired scene image data. Among them, the scene image data in the above-mentioned scene image data may be an image corresponding to the real scene to be restored. The above-mentioned scene image data correspond to different angles in the same real scene. In practice, the above-mentioned execution subject may obtain the above-mentioned scene image data from a preset database. The above-mentioned preset database may be a database for storing scene image data. The above-mentioned execution subject may be a server device for constructing a virtual space and restoring the real scene in the virtual space. The above-mentioned server device may be a computing device used by technicians when constructing a virtual space.

[0029] Step 102: Generate position information of each scene element based on the preset point cloud map data and each scene image data.

[0030] In some embodiments, the execution subject may generate pose information of each scene element based on preset point cloud map data and each scene image data. The point cloud map data may be a point cloud map corresponding to a real scene. The point cloud map data may include each scene element and a point cloud map coordinate system. Each of the scene elements may be a virtual object in the point cloud map data. The point cloud map coordinate system may be a three-dimensional coordinate system pre-constructed in the point cloud map data. Each of the scene element pose information may be a matrix for characterizing the pose of the scene element in the point cloud map data in the restored space. The restored space may be a virtual space for restoring the real scene.

[0031] As an example, the scene graph of point cloud map data can be referenced Figure 4 .

[0032] In some optional implementations of some embodiments, the execution subject may generate the pose information of each scene element based on the preset point cloud map data and the above-mentioned each scene image data through the following steps:

[0033] The first step is to generate sensor position information corresponding to each scene image data in the above-mentioned scene image data based on the above-mentioned scene image data. The above-mentioned sensor position information may be the coordinates corresponding to the shooting device in the sensor coordinate system when the scene image data is shot using the shooting device. The above-mentioned sensor coordinate system may be a coordinate system randomly created in the above-mentioned point cloud map data, which does not completely overlap with the above-mentioned point cloud map coordinate system. The above-mentioned shooting device may be a device for shooting scene image data. For example, the above-mentioned shooting device may be a camera.

[0034] The second step is to generate point cloud position information corresponding to each of the above-mentioned scene image data based on the above-mentioned scene image data and the above-mentioned point cloud map data. The above-mentioned point cloud position information may be the three-dimensional coordinates corresponding to the above-mentioned shooting device in the above-mentioned point cloud map coordinate system when the scene image data is shot using the above-mentioned shooting device. In practice, for each of the above-mentioned scene image data, the above-mentioned execution subject may input the above-mentioned scene image data and the above-mentioned point cloud map data into the point cloud registration tool to obtain the point cloud position information corresponding to the above-mentioned scene image data. The above-mentioned point cloud registration tool may be Colmap-PCD.

[0035] The third step is to generate mapping relationship information based on the generated sensor position information and the generated point cloud position information. Among them, the above-mentioned mapping relationship information can be a coordinate transformation matrix used to characterize the change relationship between the sensor coordinate system and the point cloud map coordinate system. In practice, for any one of the above-mentioned scene image data, first, the above-mentioned execution subject can determine the sensor position information and point cloud position information corresponding to the above-mentioned scene image data in the above-mentioned sensor position information and the above-mentioned point cloud position information as the target sensor position information and the target point cloud position information, respectively. Then, the difference between the above-mentioned target sensor position information and the above-mentioned target point cloud position information can be determined as the difference coordinates. Then, the number 1 can be supplemented in the above-mentioned difference coordinates, and the transpose of the supplemented difference coordinates can be determined as the translation vector. For example, when the difference coordinates are (0,0,2), after supplementing 1, it is (0,0,2,1), and the translation vector is the transpose of (0,0,2,1). Then, for any three sensor position information that are not collinear in the above-mentioned sensor position information, first, the above-mentioned three sensor position information can be determined as the first sensor coordinate, the second sensor coordinate and the third sensor coordinate respectively. The point cloud position information corresponding to the above-mentioned first sensor coordinate, the above-mentioned second sensor coordinate and the above-mentioned third sensor coordinate in the above-mentioned point cloud position information can be determined as the first point cloud coordinate, the second point cloud coordinate and the third point cloud coordinate respectively. Then, the vector from the above-mentioned first sensor coordinate to the above-mentioned second sensor coordinate direction can be determined as the first sensor position vector, and the above-mentioned first sensor position vector is normalized to obtain the first sensor vector. Then, the vector from the above-mentioned first sensor coordinate to the above-mentioned third sensor coordinate direction can be determined as the second sensor position vector, and the above-mentioned second sensor position vector is normalized to obtain the second sensor vector. Then, the outer product of the above-mentioned first sensor vector and the above-mentioned second sensor vector can be determined as the third sensor vector. Then, the above-mentioned first sensor vector, the above-mentioned second sensor vector and the above-mentioned third sensor vector can be combined into a three-dimensional matrix as a sensor matrix. By analogy, the point cloud matrix can be determined by the first point cloud coordinates, the second point cloud coordinates and the third point cloud coordinates. Then, the product of the sensor matrix and the transpose of the point cloud matrix can be determined as the coordinate system rotation matrix. Then, a row of 0s can be filled in the coordinate system rotation matrix as the fourth row element of the coordinate system rotation matrix. Finally, the filled coordinate system rotation matrix can be combined with the translation vector into a matrix as the mapping relationship information.

[0036] The fourth step is to generate the pose information of each scene element based on the above point cloud map data and the above mapping relationship information.

[0037] In some optional implementations of some embodiments, the execution subject may generate sensor position information corresponding to each scene image data in the above-mentioned scene image data based on the above-mentioned scene image data according to the following steps:

[0038] The first step is to obtain the sensor coordinate system corresponding to each of the above scene image data. The sensor coordinate system may be a coordinate system constructed in the point cloud map data. In practice, the execution subject may obtain the sensor coordinate system corresponding to each of the above scene image data from a preset coordinate system database. The coordinate system database may be a preset database for storing each sensor coordinate system.

[0039] The second step is to calibrate each of the scene image data and the sensor coordinate system to obtain the sensor position information corresponding to the scene image data. The sensor position information in the above-mentioned sensor position information may be the coordinates corresponding to the shooting device in the above-mentioned sensor coordinate system when the scene image data is shot using the shooting device. In practice, for each of the scene image data, the execution subject may generate the sensor position information of the scene image data through the above-mentioned point cloud registration tool.

[0040] In some optional implementations of some embodiments, the execution subject may generate the pose information of each scene element based on the point cloud map data and the mapping relationship information according to the following steps:

[0041] The first step is to determine the point cloud pose information corresponding to each of the above-mentioned scene elements based on the scene elements and the point cloud map coordinate system included in the above-mentioned point cloud map data. Among them, the above-mentioned point cloud pose information can be a matrix used to characterize the pose of the local coordinate system corresponding to the scene element in the above-mentioned point cloud map coordinate system. In practice, for each of the above-mentioned scene elements, based on the local coordinate system corresponding to the above-mentioned scene element, first, the above-mentioned execution subject can determine the three-dimensional coordinates of the coordinate origin of the above-mentioned local coordinate system in the above-mentioned point cloud map coordinate system. Then, the three-dimensional coordinates can be supplemented by 1 to obtain a coordinate vector. For example, when the three-dimensional coordinates are (0,0,2), (0,0,2,1) after supplementing by 1 is the coordinate vector. Secondly, the unit vectors in the three directions of the horizontal axis, the vertical axis, and the vertical axis in the above-mentioned local coordinate system can be determined. Then, the determined unit vectors can be combined into a third-order matrix as a posture matrix in the order of the horizontal axis, the vertical axis, and the vertical axis. Then, a row of elements 0 can be filled in the above-mentioned posture matrix as the fourth row elements of the above-mentioned posture matrix, and the filled posture matrix and the transpose of the above-mentioned coordinate vector can be combined into a fourth-order matrix as the point cloud pose information corresponding to the above-mentioned scene elements.

[0042] In the second step, for each point cloud pose information in the determined point cloud pose information, based on the mapping relationship information, the scene element pose information corresponding to the point cloud pose information is generated. In practice, for each point cloud pose information in the determined point cloud pose information, first, the execution subject can determine the product of the point cloud pose information and the mapping relationship information as the scene element pose information.

[0043] Step 103: Generate each restored screen based on each scene image data and each scene element position information.

[0044] In some embodiments, the execution subject may generate each restored screen based on each scene image data and each scene element pose information. In practice, for each scene element pose information in the scene element pose information, first, the execution subject may determine the submatrix of the first three rows and first three columns in the scene element pose information as the target submatrix. Secondly, the transposition of the column vector corresponding to the first three rows of the fourth column in the scene element pose information may be determined as the vector coordinate position. Then, the scene element corresponding to the scene element pose information in each scene element of the restored space may be determined as the scene element to be adjusted. An object component may be added to the scene element to be adjusted for referencing the scene element to be adjusted. Among them, the object component may be a component for referencing the scene element to be adjusted. For example, the object component may be a Rigidbody component. Then, the position of the scene element to be adjusted in the restored coordinate system of the restored space may be determined as the initial coordinate position. The difference between the vector coordinate position and the initial coordinate position is determined as the difference coordinate position. Then, the object component may be referenced by the translation function. Then, the above-mentioned difference coordinate position can be input into the above-mentioned translation function to move the above-mentioned scene element to be adjusted to the position corresponding to the above-mentioned vector coordinate position. Among them, the above-mentioned translation function can be a function for moving the above-mentioned scene element to be adjusted. For example, the above-mentioned translation function can be an Addforce function. Then, the two elements of the first row and the third column and the third row and the third column in the above-mentioned target submatrix can be combined into a first matrix coordinate. Then, the above-mentioned first matrix coordinate can be input into an inverse tangent function to obtain first angle data. Then, the negative number of the second row and the third column element in the above-mentioned target submatrix can be input into an inverse sine function to obtain second angle data. Then, the two elements of the first row and the second column and the second row and the first column in the above-mentioned target submatrix can be combined into a second matrix coordinate. Then, the above-mentioned second matrix coordinate can be input into an inverse tangent function to obtain third angle data. Then, the above-mentioned object component can be referenced by a rotation function. Then, the above-mentioned first angle data, the above-mentioned second angle data and the above-mentioned third angle data are input into the above-mentioned rotation function to adjust the posture of the above-mentioned scene element to be adjusted. Among them, the above-mentioned rotation function can be a function for changing the rotation angle of the above-mentioned scene element to be adjusted. For example, the rotation function may be an AddTorque function. This process is repeated until each scene element in the restored space is adjusted. Finally, for each scene image data in the above-mentioned scene image data, the spatial image corresponding to the scene image data in the adjusted restored space may be determined as the restored image.

[0045] In some optional implementations of some embodiments, the execution subject may generate each restored screen based on each scene image data and each scene element posture information according to the following steps:

[0046] In the first step, for each of the above-mentioned scene image data, the following steps are performed:

[0047] The first sub-step is to determine the pose information of each scene element in the pose information of each scene element corresponding to the scene image data as the pose information of each target scene element. In practice, the execution subject can determine the pose information of each scene element corresponding to each scene element contained in the scene image data as the pose information of each target scene element.

[0048] In the second sub-step, for each target scene element position information in the above target scene element position information, the following steps are performed:

[0049] Sub-step one, determining the scene element corresponding to the pose information of the target scene element among the scene elements in the restoration space as the target scene element. The restoration space may be a virtual space for restoring the real scene corresponding to the scene image data. The restoration space may include the scene elements and the restoration coordinate system. The scene elements included in the restoration space are exactly the same as the scene elements included in the point cloud map data. The restoration coordinate system completely corresponds to the sensor coordinate system. The restoration space may be a virtual space built on a development platform. For example, the development platform may be Unity.

[0050] As an example, the scene graph of the restored space can be referenced Figure 6 . Figure 6 Includes technicians and arrows. Figure 6 It is a restoration screen in the restoration space. Figure 6 The arrows in the figure represent the trajectory of the technician's movement. As the technician moves, the restoration screen displayed in the restoration space will change.

[0051] Sub-step two, based on the above-mentioned target scene element pose information, adjust the pose of the above-mentioned target scene element in the restoration space to obtain the restoration space, so as to update the restoration space. In practice, the above-mentioned execution subject can determine the transposition of the column vector corresponding to the first three rows of the fourth column in the above-mentioned target scene element pose information as the translation position. Then, the two elements of the first row and third column and the third row and third column in the above-mentioned target scene element pose information can be combined into the first element coordinates. Then, the first element coordinates can be input into the inverse tangent function to obtain the yaw angle. Then, the negative number of the second row and third column element in the above-mentioned target scene element pose information can be input into the inverse sine function to obtain the pitch angle. Then, the two elements of the first row and second column and the second row and first column in the above-mentioned target scene element pose information can be combined into the second element coordinates. Then, the second element coordinates can be input into the inverse tangent function to obtain the roll angle. Then, the above-mentioned translation position can be input into the position attribute in the adjustment component. Then the yaw angle, the pitch angle and the roll angle are input into the rotation attribute in the adjustment component to adjust the position and posture of the target scene element in the restored coordinate system. The adjustment component may be a component for adjusting the position and posture of each scene element in the virtual space. For example, the adjustment function may be a transformation component (Transform) in Unity. The position attribute may be the position attribute in the Transform component. The rotation attribute may be the rotation attribute in the Transform component.

[0052] The third sub-step is to generate a restored screen corresponding to the scene image data based on the updated restored space and the scene image data. The restored screen may be a spatial screen corresponding to the scene image data in the restored space. In practice, the execution subject may determine the spatial screen corresponding to the scene image data in the restored space as the restored screen.

[0053] Step 104 : for each restored picture in each restored picture, in response to determining that the restored picture does not meet the preset restoration condition, a scene element posture adjustment task is performed to obtain each repositioning posture information.

[0054] In some embodiments, the execution subject may, for each of the restored images, in response to determining that the restored image does not meet the preset restoration condition, execute a scene element posture adjustment task to obtain each repositioning posture information. The preset restoration condition may be that the restored image is completely identical to the corresponding scene image data. Each of the repositioning posture information may be regenerated scene element posture information.

[0055] As an example, the page diagram for comparing scene image data and restored images can be referenced. Figure 5 . Figure 5 It includes scene image data, restored image, and difference image between scene image data and restored image. Figure 5 As shown, "real" can represent a real scene. The scene graph corresponding to "real" can be scene image data. "render" can represent a virtual scene. The image corresponding to "render" in the first row and second column can be a restored screen corresponding to the above scene image data in the adjusted restored space. The image corresponding to "render" in the second row and first column can be a difference map between the above scene image data and the above restored screen. The above difference map can be used to represent the difference between the above scene image data and the above restored screen. "User" can be a control for opening the user center and displaying user information. "Rotate" can be a control for rotating the page. "Upload" can be a control for the above page.

[0056] In the process of adopting technical solutions to solve the above technical problems, the following problems are often accompanied:

[0057] When there is a deviation between the constructed virtual space and the real scene, technicians are still required to go to the real scene for comparison and make corresponding modifications to the virtual space. In the case of large deviations, adjusting the virtual space only through on-site comparison is inefficient and time-consuming.

[0058] Faced with the above technical problems, we decided to adopt the following solutions:

[0059] In some optional implementations of some embodiments, the execution subject may execute the scene element posture adjustment task in response to determining that the restored image does not meet the preset restoration condition based on the following steps to obtain each repositioning posture information:

[0060] In the first step, each scene element corresponding to the restored image among each scene element included in the updated restoration space is determined as each scene element to be processed.

[0061] The second step is to determine the position information of each of the above-mentioned scene elements to be processed in the above-mentioned restored coordinate system as the position information to be processed based on the restored coordinate system included in the above-mentioned restored space. Among them, the above-mentioned position information to be processed can be a matrix used to characterize the position of the scene element to be processed in the restored coordinate system. The method of determining the position information of the scene element to be processed in the restored coordinate system can refer to the specific implementation method of step 102, which will not be repeated here.

[0062] The third step is to obtain each historical mapping relationship information. Among them, the above-mentioned each historical mapping relationship information can be a coordinate transformation matrix generated in the past, which is used to characterize the mapping relationship between the above-mentioned point cloud map coordinate system and the above-mentioned sensor coordinate system. At the same time, since the above-mentioned sensor coordinate system is completely corresponding to the above-mentioned restored coordinate system, the above-mentioned each historical mapping relationship information can also characterize the mapping relationship between the above-mentioned point cloud map coordinate system and the above-mentioned restored coordinate system. In practice, the above-mentioned execution entity can obtain the above-mentioned each historical mapping relationship information from a preset historical mapping relationship information database. Among them, the above-mentioned historical mapping relationship information database can be a database for storing historical mapping relationship information.

[0063] In the fourth step, for each of the determined pieces of to-be-processed pose information, perform the following steps:

[0064] In the first sub-step, the scene element pose information corresponding to the pose information to be processed in the above-mentioned each point cloud pose information is determined as the target pose information.

[0065] The second sub-step is to generate relocation mapping relationship information based on the to-be-processed posture information and the target posture information, wherein the relocation mapping relationship information may be regenerated mapping relationship information.

[0066] The third sub-step is to generate a mapping relationship comparison result based on the above-mentioned relocation mapping relationship information and the above-mentioned historical mapping relationship information. Among them, the above-mentioned mapping relationship comparison result can characterize the difference between the above-mentioned relocation mapping relationship information and the above-mentioned historical mapping relationship information. In practice, first, the above-mentioned execution entity can determine the average matrix corresponding to the above-mentioned historical mapping relationship information as the mapping relationship information to be compared. Then, the modulus length of the difference between the above-mentioned relocation mapping relationship information and the above-mentioned mapping relationship information to be compared can be determined as the difference data. When the above-mentioned difference data is equal to the preset difference threshold, "exactly the same" can be determined as the above-mentioned mapping relationship comparison result. When the above-mentioned difference data is greater than or less than the above-mentioned preset difference threshold, "not the same" can be determined as the above-mentioned mapping relationship comparison result.

[0067] In step 5, in response to determining that each of the obtained mapping relationship comparison results does not satisfy a preset mapping relationship condition, the following steps are performed:

[0068] In the first sub-step, each historical posture information corresponding to each of the above-mentioned posture information to be processed is obtained. Among them, the above-mentioned mapping relationship condition can be that the comparison results of each of the above-mentioned mapping relationships are "completely the same". Each of the above-mentioned historical posture information can be the scene element posture information corresponding to the last storage of each scene element. In practice, the above-mentioned execution entity can obtain the above-mentioned historical posture information from a preset historical posture information database. Among them, the above-mentioned historical posture information database can be a database for storing historical posture information.

[0069] The second sub-step is to determine the above-mentioned historical posture information as each repositioning posture information.

[0070] Step 6: In response to determining that each mapping relationship comparison result obtained satisfies the above mapping relationship condition, the following steps are performed:

[0071] The first sub-step is to send the restored image and the preset relocation information to a target server, wherein the target server may be a server capable of generating position information of each scene element in the restored image in the restored space according to the restored image.

[0072] The second sub-step is, in response to receiving each restored pose information sent by the target server, determining each restored pose information as each repositioned pose information. Wherein, each restored pose information may be a matrix for representing the pose of the scene element in the restored space.

[0073] The above technical solution and its related contents, as an inventive point of an embodiment of the present disclosure, solve the problem of "high time cost". The factors that lead to low efficiency and high time cost of adjusting the virtual space are often as follows: when there is a deviation between the constructed virtual space and the real scene, the technicians are still required to go to the real scene for comparison, so as to make corresponding modifications to the virtual space. In the case of large deviation, the efficiency of adjusting the virtual space only by on-site comparison is low, and the time cost is high. If the above factors are solved, the time cost can be reduced. In order to achieve this effect, the present disclosure first determines the scene elements corresponding to the above-mentioned restored screen in the scene elements included in the updated restored space as the scene elements to be processed. Thus, the scene elements to be adjusted can be determined. Secondly, based on the restored coordinate system included in the restored space, the posture information of each of the scene elements to be processed in the restored coordinate system is determined as the posture information to be processed. Thus, the posture information corresponding to the scene elements to be readjusted can be determined. Then, each historical mapping relationship information is obtained. Thus, the historical mapping relationship information between the restored coordinate system and the point cloud map coordinate system can be obtained. Then, for each of the determined to-be-processed pose information, the following steps are performed: First, the pose information of the scene element corresponding to the to-be-processed pose information in the above-mentioned point cloud pose information is determined as the target pose information. Thus, the mapping relationship between the restored coordinate system and the point cloud map coordinate system can be obtained during this processing. Then, based on the above-mentioned to-be-processed pose information and the above-mentioned target pose information, the repositioning mapping relationship information is generated. Thus, the mapping relationship information between the restored coordinate system and the point cloud map coordinate system can be obtained according to the two pose information of the same scene element in the restored coordinate system and the point cloud map coordinate system. Then, based on the above-mentioned repositioning mapping relationship information and the above-mentioned historical mapping relationship information, a mapping relationship comparison result is generated. Thus, the comparison result between the repositioning mapping relationship information and the above-mentioned historical mapping relationship information can be obtained, and according to the comparison result, the reason for the deviation between the restored space and the real scene is determined. Then, in response to determining that the obtained mapping relationship comparison results do not meet the preset mapping relationship conditions, the following steps are performed: Then, the historical pose information corresponding to the above-mentioned to-be-processed pose information is obtained. Then, the above-mentioned historical posture information is determined as each repositioning posture information. Therefore, when the comparison result indicates that the deviation between the mapping relationship generated this time and the previous mapping relationships is large, the posture of each scene element can be readjusted according to the posture information of each scene element generated previously. Then, in response to determining that the obtained mapping relationship comparison results meet the above-mentioned mapping relationship conditions, the following steps are performed: Then, the above-mentioned restored screen and the preset repositioning information are sent to the target server.Finally, in response to receiving each restored pose information sent by the above-mentioned target server, the above-mentioned each restored pose information is determined as each repositioned pose information. Therefore, when the comparison result indicates that the mapping relationship information generated this time is the same as the previous mapping relationship information, the pose information of each scene element in the restored space can be regenerated by the target server. Also, when there is a deviation between the restored space and the real scene, the cause of the deviation can be determined by comparing the mapping relationship, and then the pose information of each scene element can be regenerated according to different methods according to the cause of the deviation, without the need for technical personnel to repeatedly go to the site, thereby improving the efficiency of adjusting the virtual space and reducing time costs.

[0074] Step 105: Generate a three-dimensional scene space based on the obtained repositioning posture information.

[0075] In some embodiments, the execution subject may generate a three-dimensional scene space based on the obtained repositioning posture information. In practice, the execution subject may input the repositioning posture information and the restoration space into the custom adjustment function to adjust the position and posture of each scene element in the restoration space, and obtain the adjusted restoration space as the three-dimensional scene space.

[0076] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the scene restoration method of some embodiments of the present disclosure, the restoration efficiency of the real scene restoration can be improved, the time cost waste can be reduced, and the accuracy of the real scene restoration can be improved. Specifically, the reasons for the low restoration efficiency, high time cost and low accuracy of the real scene restoration are: when comparing the real scene with the virtual space, it is necessary to go to the scene repeatedly to optimize and adjust the virtual space, resulting in low restoration efficiency and high time cost when restoring the real scene. When the virtual space is adjusted directly by comparing the real scene with the virtual space, some details in the virtual space often deviate from the real scene, resulting in low accuracy of restoring the real scene in the virtual space. Based on this, the scene restoration method of some embodiments of the present disclosure, first, stores the pre-acquired image data of each scene. Thus, the image data of the real scene can be obtained so that the real scene can be restored by the image data of the real scene later. Secondly, based on the preset point cloud map data and the above-mentioned image data of each scene, the pose information of each scene element is generated. Thus, the corresponding pose information of the scene elements on the point cloud map in the virtual space can be obtained. Then, based on the above-mentioned scene image data and the pose information of the above-mentioned scene elements, each restoration screen is generated. Thus, the scene elements in the restoration space can be adjusted by the obtained pose information. Then, for each of the restoration screens in the above-mentioned restoration screens, in response to determining that the restoration screen does not meet the preset restoration condition, the scene element pose adjustment task is executed to obtain each repositioning pose information. Thus, when the restoration screen cannot coincide with the corresponding scene image data, the pose of each scene element in the restoration space can be regenerated. Finally, based on the obtained repositioning pose information, a three-dimensional scene space is generated. Thus, the scene elements in the restoration space can be re-adjusted according to the regenerated pose, so that the restoration space is completely consistent with the real scene. Also because when the screen in the restoration space cannot completely coincide with the corresponding scene image data, the pose information of each scene element can be repositioned to re-adjust the pose of each scene element in the restoration space, because the accuracy of restoring the real scene can be improved. Also, the position and posture of each scene element in the restoration space can be adjusted directly by comparing the picture in the restoration space with the corresponding scene image data, without the need for technical personnel to repeatedly go to the site for comparison. This can improve the efficiency of restoring the real scene and reduce time costs.

[0077] Figure 2 The process 200 of another embodiment of the scene restoration method according to the present disclosure is shown. The scene restoration method comprises the following steps:

[0078] Step 201: storing the pre-acquired image data of each scene.

[0079] In some embodiments, the execution subject (eg, computing device) of the scene restoration method may store the pre-acquired scene image data. The execution subject may be a computing device used to construct a virtual space and restore the real scene in the virtual space.

[0080] Step 202: Generate pose information of each scene element based on the preset point cloud map data and each scene image data.

[0081] In some embodiments, the above-mentioned execution subject can generate each scene element pose information based on the preset point cloud map data and the above-mentioned each scene image data. In practice, first, the above-mentioned execution subject can obtain the sensor coordinate system corresponding to the above-mentioned each scene image data from the above-mentioned coordinate system database. Then, the mapping relationship information between the above-mentioned point cloud map coordinate system and the above-mentioned sensor coordinate system can be determined. The method for determining the mapping relationship information can refer to the specific implementation method of step 102, which will not be repeated here. Then, for each scene image data of the above-mentioned each scene image data, the above-mentioned execution subject can determine the coordinates of each scene element corresponding to the above-mentioned scene image data in the above-mentioned point cloud map data as each point cloud position information. Then, for each point cloud position information in the above-mentioned each point cloud position information, the product of the above-mentioned mapping relationship information and the above-mentioned point cloud position information can be determined as the scene element pose information.

[0082] Step 203: Generate each restored screen based on each scene image data and each scene element position information.

[0083] In some embodiments, the execution subject may generate each restored screen based on each scene image data and each scene element position information. The method of generating each restored screen may refer to the specific implementation of step 103, which will not be described in detail here.

[0084] Step 204 : for each restored picture in each restored picture, in response to determining that the restored picture does not meet the preset restoration condition, a scene element posture adjustment task is performed to obtain each repositioning posture information.

[0085] In some embodiments, the execution subject may, for each of the restored images, perform a scene element posture adjustment task in response to determining that the restored image does not meet the preset restoration condition, and obtain each repositioning posture information. In practice, in response to determining that the restored image does not meet the preset restoration condition, the execution subject may also regenerate each scene element posture information in the manner of step 102. Then, the regenerated scene element posture information may be determined as each repositioning posture information.

[0086] Step 205: determine the updated restoration space as the target restoration space.

[0087] In some embodiments, the execution entity may determine the updated restoration space as the target restoration space.

[0088] Step 206: for each repositioning posture information in each repositioning posture information, perform the following steps:

[0089] Step 2061: Determine the scene element corresponding to the repositioning posture information among the scene elements included in the target restoration space as the scene element to be positioned.

[0090] In some embodiments, the execution entity may determine, among the scene elements included in the target restoration space, the scene elements corresponding to the repositioning posture information as the scene elements to be positioned.

[0091] Step 2062: Based on the repositioning posture information, adjust the posture of the scene element to be positioned in the restoration space to obtain the target restoration space, so as to update the target restoration space.

[0092] In some embodiments, the execution subject may adjust the position and posture of the scene element to be located in the restoration space based on the repositioning posture information to obtain a target restoration space, so as to update the target restoration space. In practice, the execution subject may adjust the position and posture of the scene element to be located by the posture adjustment tool according to the position and posture represented by the repositioning posture information to obtain the target restoration space.

[0093] Step 207: determine the updated target restoration space as the three-dimensional scene space.

[0094] In some embodiments, the execution entity may determine the updated target restoration space as a three-dimensional scene space.

[0095] Further references Figure 3 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a scene restoration device. These device embodiments are similar to Figure 1Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.

[0096] like Figure 3 As shown, the scene restoration device 300 of some embodiments includes: a storage unit 301, a first generation unit 302, a second generation unit 303, an execution unit 304 and a third generation unit 305. The storage unit 301 is configured to store the pre-acquired scene image data; the first generation unit 302 is configured to generate the pose information of each scene element based on the preset point cloud map data and the above scene image data; the second generation unit 303 is configured to generate each restoration screen based on the above scene image data and the above scene element pose information; the execution unit 304 is configured to perform the scene element pose adjustment task for each of the above restoration screens in response to determining that the above restoration screen does not meet the preset restoration condition, and obtain each repositioning pose information; the third generation unit 305 is configured to generate a three-dimensional scene space based on the obtained repositioning pose information.

[0097] It is understood that the units described in the device 300 are similar to those described 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 contained therein, and will not be described in detail here.

[0098] Reference below Figure 7 , which shows a structural schematic diagram of an electronic device (such as a computing device) 700 suitable for implementing some embodiments of the present disclosure. Figure 7 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.

[0099] like Figure 7 As shown, the electronic device 700 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage device 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the electronic device 700 are also stored. The processing device 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0100] Typically, the following devices may be connected to the I / O interface 705: an input device 706 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 707 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 708 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 709. The communication device 709 may allow the electronic device 700 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 7 The electronic device 700 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 7 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0101] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network through the communication device 709, or installed from the storage device 708, or installed from the ROM 702. When the computer program is executed by the processing device 701, the above-mentioned functions defined in the method of some embodiments of the present disclosure are executed.

[0102] It should be noted that the computer-readable medium recorded 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 above 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 of the above. In some embodiments of the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In some embodiments of the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit 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 of the above.

[0103] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may 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.

[0104] The computer-readable medium may be included in the electronic device; or it may exist independently without being installed in the electronic device. The computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device: stores the pre-acquired scene image data; generates the pose information of the scene elements based on the preset point cloud map data and the scene image data; generates the restored images based on the scene image data and the scene element pose information; for each of the restored images, in response to determining that the restored image does not meet the preset restoration condition, performs the scene element pose adjustment task to obtain the repositioning pose information; and generates the three-dimensional scene space based on the repositioning pose information obtained.

[0105] 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 separate 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 via 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., via the Internet using an Internet service provider).

[0106] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square 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 square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0107] The units described in some embodiments of the present disclosure may be implemented by software or by hardware. The described units may also be provided in a processor, for example, may be described as: a processor including a storage unit, a first generation unit, a second generation unit, an execution unit, and a third generation 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 a "unit for storing pre-acquired scene image data".

[0108] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, 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 chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0109] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. 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 the above-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, the above-mentioned features are replaced with the technical features with similar functions disclosed in the embodiments of the present disclosure (but not limited to) and the technical solutions formed.

Claims

1. A scene restoration method, comprising: Storing pre-acquired image data of each scene; Based on the preset point cloud map data and the image data of each scene, generating the pose information of each scene element; Generate each restored screen based on each scene image data and each scene element position information; For each of the restored images, in response to determining that the restored image does not meet a preset restoration condition, a scene element posture adjustment task is performed to obtain each repositioning posture information; Based on the obtained repositioned pose information, a three-dimensional scene space is generated.

2. The method according to claim 1, wherein: The generating of the pose information of each scene element based on the preset point cloud map data and the image data of each scene includes: Based on the respective scene image data, generating sensor position information corresponding to each scene image data in the respective scene image data; Based on the respective scene image data and the point cloud map data, generating point cloud position information corresponding to each scene image data in the respective scene image data; Generate mapping relationship information based on the generated position information of each sensor and the generated position information of each point cloud; Based on the point cloud map data and the mapping relationship information, the pose information of each scene element is generated.

3. The method according to claim 2, wherein: The generating, based on the respective scene image data, sensor position information corresponding to each scene image data in the respective scene image data comprises: Acquire a sensor coordinate system corresponding to each scene image data; For each scene image data in the various scene image data, the scene image data and the sensor coordinate system are calibrated to obtain sensor position information corresponding to the scene image data.

4. The method according to claim 2, wherein: The point cloud map data includes various scene elements and a point cloud map coordinate system; And generating the pose information of each scene element based on the point cloud map data and the mapping relationship information, including: Based on the scene elements and the point cloud map coordinate system included in the point cloud map data, determining the point cloud pose information corresponding to each scene element in the scene elements; For each point cloud pose information in the determined point cloud pose information, scene element pose information corresponding to the point cloud pose information is generated based on the mapping relationship information.

5. The method according to claim 1, wherein: Each scene element pose information in the scene element pose information is the pose information corresponding to the scene element in the preset restoration space; And generating each restored screen based on each scene image data and each scene element posture information includes: For each of the scene image data, the following steps are performed: Determine each scene element pose information corresponding to the scene image data in the each scene element pose information as each target scene element pose information; For each target scene element position information in the target scene element position information, the following steps are performed: Determine the scene element corresponding to the position information of the target scene element among the scene elements in the restoration space as the target scene element, wherein the restoration space includes the scene elements and the restoration coordinate system; Based on the pose information of the target scene element, the pose of the target scene element in the restoration space is adjusted to obtain the restoration space, so as to update the restoration space; Based on the updated restoration space and the scene image data, a restoration screen corresponding to the scene image data is generated.

6. The method according to claim 4 or 5, wherein: In response to determining that the restored image does not meet the preset restoration condition, executing the scene element posture adjustment task to obtain each repositioning posture information includes: Determining each scene element corresponding to the restored picture among each scene element included in the updated restoration space as each scene element to be processed; Based on the restored coordinate system included in the restored space, determining the pose information of each of the scene elements to be processed in the restored coordinate system as the pose information to be processed; Get each historical mapping relationship information; For each of the determined positions and poses to be processed, the following steps are performed: Determine the scene element pose information corresponding to the pose information to be processed in each point cloud pose information as the target pose information; Based on the to-be-processed posture information and the target posture information, generating relocation mapping relationship information; Based on the relocation mapping relationship information and the respective historical mapping relationship information, generating a mapping relationship comparison result; In response to determining that each of the obtained mapping relationship comparison results does not satisfy a preset mapping relationship condition, the following steps are performed: Acquire each historical posture information corresponding to each posture information to be processed; Determine the respective historical pose information as respective repositioning pose information; In response to determining that each obtained mapping relationship comparison result satisfies the mapping relationship condition, the following steps are performed: Sending the restored image and preset relocation information to the target server; In response to receiving the respective pieces of restored posture information sent by the target server, the respective pieces of restored posture information are determined as the respective pieces of repositioned posture information.

7. The method according to claim 5, wherein: The generating of a three-dimensional scene space based on each repositioning posture information obtained includes: Determine the updated restoration space as the target restoration space; For each repositioning pose information in the respective repositioning pose information, the following steps are performed: Determine the scene element corresponding to the repositioning posture information among the scene elements included in the target restoration space as the scene element to be positioned; Based on the repositioning posture information, adjusting the posture of the scene element to be positioned in the restoration space to obtain a target restoration space, so as to update the target restoration space; The updated target restoration space is determined as the three-dimensional scene space.

8. A scene restoration device, comprising: A storage unit, configured to store pre-acquired image data of each scene; A first generating unit is configured to generate position information of each scene element based on preset point cloud map data and each scene image data; A second generating unit is configured to generate each restored screen based on each scene image data and each scene element posture information; an execution unit configured to, for each of the restored images, execute a scene element posture adjustment task in response to determining that the restored image does not meet a preset restoration condition, and obtain each repositioning posture information; The third generating unit is configured to generate a three-dimensional scene space based on the obtained repositioning posture information.

9. 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 7.

10. 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 7 is implemented.

Images