Data processing method and device, electronic equipment and computer readable medium

Abstract

The invention discloses a data processing method and device, electronic equipment and a computer readable medium. The method comprises the steps that a to-be-processed three-dimensional grid and a reference three-dimensional grid are acquired; drawing a first plane representation image of the to-be-processed three-dimensional grid and a second plane representation image of the reference three-dimensional grid in a preset two-dimensional plane space, wherein the preset two-dimensional plane space comprises at least one anchor point set; first position characterization data and second position characterization data of anchor points in each anchor point set are determined, and the first position characterization data are determined according to area description information of vertex surrounding areas corresponding to the anchor points in the first plane characterization image; the second position characterization data is determined according to region description information of a vertex surrounding region corresponding to the anchor point in the second plane characterization image; and determining the grid performance characterization data of the to-be-processed three-dimensional grid according to the difference characterization data between the first position characterization data and the second position characterization data, thereby being beneficial to improving the grid performance evaluation effect.

Description

Technical Field

[0001] The present application relates to the technical field of data processing, and in particular, to a data processing method, apparatus, electronic device, and computer-readable medium. Background Art

[0002] A three-dimensional mesh refers to a three-dimensional solid structure composed of some vertices in three-dimensional space and edges used to connect these vertices, so that the three-dimensional mesh can be used to represent an object in a finer granularity, such as a face, an object, a building, etc.

[0003] In some application scenarios, three-dimensional reconstruction processing can be performed on an image provided by a user to obtain a three-dimensional mesh corresponding to the image, so that the three-dimensional mesh can better represent the object described by the image in three-dimensional space. Summary of the Invention

[0004] The present application provides a data processing method, apparatus, electronic device, and computer-readable medium, which can better determine the mesh performance (such as regularity, etc.) of a three-dimensional mesh.

[0005] To achieve the above object, the technical solutions provided by the present application are as follows:

[0006] The present application provides a data processing method, the method comprising:

[0007] Obtain a three-dimensional mesh to be processed and a reference three-dimensional mesh;

[0008] Draw a first planar representation image of the three-dimensional mesh to be processed and a second planar representation image of the reference three-dimensional mesh in a preset two-dimensional plane space; the first planar representation image is used to represent the state presented by the vertices in the three-dimensional mesh to be processed in the preset two-dimensional plane space; the second planar representation image is used to represent the state presented by the vertices in the reference three-dimensional mesh in the preset two-dimensional plane space; the preset two-dimensional plane space includes at least one set of anchor points;

[0009] Determine first position representation data and second position representation data of the anchor points in each set of anchor points; the first position representation data is determined according to the region description information of the vertex surrounding region corresponding to the anchor point in the first planar representation image; the second position representation data is determined according to the region description information of the vertex surrounding region corresponding to the anchor point in the second planar representation image;

[0010] Determine mesh performance representation data of the three-dimensional mesh to be processed according to the difference representation data between the first position representation data and the second position representation data.

[0011] In a possible implementation manner, the process of determining the grid performance characterization data includes:

[0012] For any anchor point set, a first virtual grid and a second virtual grid are constructed by using the anchor point set, and according to the grid difference characterization data between the first virtual grid and the second virtual grid, the grid performance evaluation result corresponding to the anchor point set is determined; the vertices in the first virtual grid are determined according to the first anchor point in the anchor point set, there is a vertex surrounding area corresponding to the first anchor point in the first plane representation image, and the first description information of the vertices in the first virtual grid is determined according to the first position characterization data of the first anchor point; the vertices in the second virtual grid are determined according to the second anchor point in the anchor point set, there is a vertex surrounding area corresponding to the second anchor point in the second plane representation image, and the second description information of the vertices in the second virtual grid is determined according to the second position characterization data of the second anchor point; the grid difference characterization data is determined according to the difference characterization data between the first description information of the vertices in the first virtual grid and the second description information of the vertices in the second virtual grid;

[0013] According to the grid performance evaluation results corresponding to the at least one anchor point set, the grid performance characterization data of the three-dimensional grid to be processed is determined.

[0014] In a possible implementation manner, the constructing the first virtual grid and the second virtual grid by using the anchor point set includes:

[0015] Determine each anchor point group to be used from the anchor point set; for any anchor point group to be used, the rectangle formed by all the anchor points in the anchor point group to be used meets the preset rectangle condition;

[0016] For any anchor point group to be used, if there is a vertex surrounding area corresponding to each anchor point in the anchor point group to be used in the first plane representation image, then the first virtual grid is constructed according to all the anchor points in the anchor point group to be used and the first position characterization data of all the anchor points; if there is a vertex surrounding area corresponding to some of the anchor points in the anchor point group to be used in the first plane representation image, and the number of the some anchor points is not less than the preset number threshold, then the first virtual grid is constructed according to the some anchor points and the first position characterization data of the some anchor points;

[0017] For any anchor point group to be used, if there are vertex enclosing regions corresponding to each anchor point in the anchor point group to be used in the second plane representation image, the second virtual grid is constructed based on all the anchor points in the anchor point group to be used and the second position representation data of all the anchor points; if there are vertex enclosing regions corresponding to some of the anchor points in the anchor point group to be used in the second plane representation image, and the number of the some anchor points is not less than a preset number threshold, the second virtual grid is constructed based on the some anchor points and the second position representation data of the some anchor points.

[0018] In a possible implementation manner, the anchor point group to be used includes four anchor points;

[0019] The constructing of the first virtual grid based on all the anchor points in the anchor point group to be used and the first position representation data of all the anchor points includes:

[0020] Based on the four anchor points in the anchor point group to be used and the first position representation data of the four anchor points, two triangular faces in the first virtual grid are constructed;

[0021] The constructing of the second virtual grid based on all the anchor points in the anchor point group to be used and the second position representation data of all the anchor points includes:

[0022] Based on the four anchor points in the anchor point group to be used and the second position representation data of the four anchor points, two triangular faces in the second virtual grid are constructed.

[0023] In a possible implementation manner, the number of the some anchor points is three;

[0024] The constructing of the first virtual grid based on the some anchor points and the first position representation data of the some anchor points includes:

[0025] Based on the some anchor points and the first position representation data of the some anchor points, one triangular face in the first virtual grid is constructed;

[0026] The constructing of the second virtual grid based on the some anchor points and the second position representation data of the some anchor points includes:

[0027] Based on the some anchor points and the second position representation data of the some anchor points, one triangular face in the second virtual grid is constructed.

[0028] In a possible implementation manner, the grid difference representation data includes vertex difference representation data of several vertices; for any vertex, the vertex difference representation data of the vertex is determined based on the difference representation data between the first description information and the second description information of the vertex;

[0029] The grid performance evaluation result is determined based on the Laplace losses corresponding to the several vertices. For any vertex, the Laplace loss corresponding to this vertex is determined based on the vertex difference characterization data of this vertex, the vertex difference characterization data of the adjacent vertices of this vertex, and the two diagonals corresponding to the edges formed by this vertex and its adjacent vertices.

[0030] In a possible implementation manner, the at least one anchor point set includes N anchor point sets arranged in sequence, with equal row spacing and equal column spacing, where N is a positive integer;

[0031] The process of obtaining the nth anchor point set includes:

[0032] According to the preset sampling parameters and the arrangement serial number corresponding to the nth anchor point set, determine the starting sampling position corresponding to the nth anchor point set in the preset two-dimensional plane space; the preset sampling parameters include row spacing, column spacing, and the number of anchor point sets; n is a positive integer, and n ≤ N;

[0033] According to the starting sampling position and the preset sampling parameters, determine at least one non-starting sampling position corresponding to the nth anchor point set;

[0034] Collect the anchor points at the starting sampling position and the anchor points at each non-starting sampling position in the preset two-dimensional plane space to obtain the nth anchor point set.

[0035] In a possible implementation manner, the vertex surrounding area is a triangular face;

[0036] The area description information includes at least one of the identifier of the triangular face and the planar positions of each vertex in the triangular face in the preset two-dimensional plane space.

[0037] In a possible implementation manner, the to-be-processed three-dimensional grid is constructed using a three-dimensional reconstruction model;

[0038] After determining the grid performance characterization data of the to-be-processed three-dimensional grid, the method further includes:

[0039] Update the three-dimensional reconstruction model according to the grid performance characterization data.

[0040] This application provides a data processing device, including:

[0041] A grid acquisition unit, configured to acquire a to-be-processed three-dimensional grid and a reference three-dimensional grid;

[0042] An image drawing unit for drawing a first planar representation image of the to-be-processed three-dimensional mesh and a second planar representation image of the reference three-dimensional mesh in a preset two-dimensional plane space; the first planar representation image is used to represent the state presented by the vertices in the to-be-processed three-dimensional mesh in the preset two-dimensional plane space; the second planar representation image is used to represent the state presented by the vertices in the reference three-dimensional mesh in the preset two-dimensional plane space; the preset two-dimensional plane space includes at least one set of anchor points;

[0043] A first determination unit for determining first position representation data and second position representation data of the anchor points in each set of anchor points; the first position representation data is determined based on the region description information of the vertex surrounding region corresponding to the anchor point in the first planar representation image; the second position representation data is determined based on the region description information of the vertex surrounding region corresponding to the anchor point in the second planar representation image;

[0044] A second determination unit for determining the mesh performance representation data of the to-be-processed three-dimensional mesh based on the difference representation data between the first position representation data and the second position representation data.

[0045] This application provides an electronic device, and the device includes: a processor and a memory;

[0046] The memory is used to store instructions or computer programs;

[0047] The processor is used to execute the instructions or computer programs in the memory so that the electronic device executes the data processing method provided by this application.

[0048] This application provides a computer-readable medium, and instructions or computer programs are stored in the computer-readable medium. When the instructions or computer programs run on a device, the device is enabled to execute the data processing method provided by this application.

[0049] This application provides a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes program codes for executing the data processing method provided by this application.

[0050] Compared with the related art, this application has at least the following advantages:

[0051] In the technical solution provided by this application, after obtaining the three-dimensional mesh to be processed (for example, the reconstructed three-dimensional mesh) and the reference three-dimensional mesh (for example, the pre-set standardized three-dimensional mesh template), the first planar representation image of the three-dimensional mesh to be processed and the second planar representation image of the reference three-dimensional mesh are drawn in a pre-set two-dimensional planar space (for example, a blank planar image), so that the first planar representation image is used to represent the state presented by the vertices in the three-dimensional mesh to be processed in the pre-set two-dimensional planar space (for example, the position distribution state of the vertices, and the connection state between different vertices, etc.), and the second planar representation image is used to represent the state presented by the vertices in the reference three-dimensional mesh in the pre-set two-dimensional planar space, so that when the pre-set two-dimensional planar space includes at least one anchor point set, the first position representation data and the second position representation data of the anchor points in each anchor point set are determined, where the first position representation data is determined based on the region description information of the vertex surrounding region corresponding to the anchor point in the first planar representation image, so that the first position representation data can represent to a certain extent the state presented by the three-dimensional mesh to be processed at the anchor point; the second position representation data is determined based on the region description information of the vertex surrounding region corresponding to the anchor point in the second planar representation image, so that the second position representation data can represent to a certain extent the state presented by the reference three-dimensional mesh at the anchor point; then, based on the difference representation data between the first position representation data and the second position representation data, the mesh performance representation data of the three-dimensional mesh to be processed is determined. Among them, since the difference representation data can represent the difference between the three-dimensional mesh to be processed and the reference three-dimensional mesh, so that the mesh performance representation data determined based on the difference representation data can represent the mesh performance presented by the three-dimensional mesh to be processed relative to the reference three-dimensional mesh, so that the mesh performance representation data can represent the quantitative result of the mesh performance presented by the three-dimensional mesh to be processed under one or more mesh performance evaluation dimensions (for example, dimensions such as standardization), so as to achieve the purpose of quantitatively evaluating a three-dimensional mesh under these mesh performance evaluation dimensions, thereby effectively avoiding defects (such as poor mesh performance evaluation effect) caused by the inability to perform quantitative processing for a certain mesh performance evaluation dimension (for example, dimensions such as standardization) or a poor quantitative scheme for a certain mesh performance evaluation dimension (for example, dimensions such as accuracy), and further being beneficial to improving the mesh performance evaluation effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] To more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for the description of the embodiments or related technologies. Obviously, the drawings in the following description are only some embodiments recorded in the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0053] Figure 1 Schematic diagram of a three-dimensional grid provided by an embodiment of the present application;

[0054] Figure 2 Schematic diagram of another three-dimensional grid provided by an embodiment of the present application;

[0055] Figure 3 Flowchart of a data processing method provided by an embodiment of the present application;

[0056] Figure 4 Schematic diagram of a planar characterization image provided by an embodiment of the present application;

[0057] Figure 5 Schematic diagram of another planar characterization image provided by an embodiment of the present application;

[0058] Figure 6 Schematic diagram of the construction of a triangular face provided by an embodiment of the present application;

[0059] Figure 7 Schematic diagram of a virtual grid provided by an embodiment of the present application;

[0060] Figure 8 Schematic diagram of two vertices with a connection relationship provided by an embodiment of the present application;

[0061] Figure 9 Schematic diagram of the structure of a data processing device provided by an embodiment of the present application;

[0062] Figure 10 Schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0063] It has been found through research that in some application scenarios, for the reconstructed three-dimensional grid (for example, Figure 1For a three-dimensional mesh as shown, it may be necessary to evaluate the accuracy and / or normality of the three-dimensional mesh. Among them, the accuracy is used to describe whether the reconstructed three-dimensional mesh can accurately fit the actual object (such as a face, etc.) described by the image data provided by the user. The normality is used to describe whether the reconstructed three-dimensional mesh is normalized; and the present application does not limit the implementation manner of the normalization. For example, in some application scenarios, the normalization can be subjectively judged by means of a checkerboard calibration plate material to determine whether the two-dimensional projections of each black and white grid and its boundary lines are horizontal and vertical after rendering the checkerboard calibration plate material onto the three-dimensional mesh. For example, for Figure 2 the three-dimensional mesh shown, since the two-dimensional projections of each black and white grid and its boundary lines are horizontal and vertical after rendering the checkerboard calibration plate material onto the three-dimensional mesh, the three-dimensional mesh is completely normalized. It can be seen that the normalization evaluation process based on the checkerboard calibration plate material can only represent to a certain extent the result of whether a three-dimensional mesh conforms to the norm, and cannot accurately characterize the degree of normality of a three-dimensional mesh, resulting in poor evaluation effects because this evaluation process cannot perform quantitative processing in terms of normality.

[0064] Based on the above content, to better improve the performance evaluation effect for 3D meshes, this application provides a data processing method, which includes: after obtaining a 3D mesh to be processed (for example, a reconstructed 3D mesh) and a reference 3D mesh (for example, a pre-set standardized 3D mesh template), draw a first planar representation image of the 3D mesh to be processed and a second planar representation image of the reference 3D mesh in a pre-set 2D planar space (for example, a blank planar image), so that the first planar representation image is used to represent the state presented by the vertices in the 3D mesh to be processed in the pre-set 2D planar space (for example, the position distribution state of the vertices, and the connection state between different vertices, etc.), and the second planar representation image is used to represent the state presented by the vertices in the reference 3D mesh in the pre-set 2D planar space, so that when the pre-set 2D planar space includes at least one anchor point set, determine the first position representation data and the second position representation data of the anchor points in each anchor point set, where the first position representation data is determined based on the region description information of the vertex surrounding region corresponding to the anchor point in the first planar representation image, so that the first position representation data can represent to a certain extent the state presented by the 3D mesh to be processed at the anchor point; the second position representation data is determined based on the region description information of the vertex surrounding region corresponding to the anchor point in the second planar representation image, so that the second position representation data can represent to a certain extent the state presented by the reference 3D mesh at the anchor point; then, based on the difference representation data between the first position representation data and the second position representation data, determine the mesh performance representation data of the 3D mesh to be processed. Among them, since the difference representation data can represent the difference between the 3D mesh to be processed and the reference 3D mesh, so that the mesh performance representation data determined based on the difference representation data can represent the mesh performance presented by the 3D mesh to be processed relative to the reference 3D mesh, so that the mesh performance representation data can represent the quantization result of the mesh performance presented by the 3D mesh to be processed under one or more mesh performance evaluation dimensions (for example, dimensions such as normativity), so as to achieve the purpose of quantitatively evaluating a 3D mesh under these mesh performance evaluation dimensions, and thus can effectively avoid defects (such as poor mesh performance evaluation effect) caused by the inability to perform quantitative processing for a certain mesh performance evaluation dimension (for example, dimensions such as normativity) or a poor quantization scheme for a certain mesh performance evaluation dimension (for example, dimensions such as accuracy), which is conducive to improving the mesh performance evaluation effect.

[0065] In addition, this application does not limit the execution subject of the data processing method provided in the embodiments of this application. For example, the data processing method provided in the embodiments of this application can be applied to a terminal device or a server. Another example is that the data processing method provided in the embodiments of this application can also be implemented by means of the data interaction process between the terminal device and the server. Among them, the terminal device can be a smart phone, a computer, a personal digital assistant (PDA), a tablet computer, etc. The server can be an independent server, a cluster server, or a cloud server.

[0066] In order to enable those skilled in the art to better understand the solution of this application, the following will clearly and completely describe the technical solutions in the embodiments of this application with reference to the accompanying drawings in the embodiments of this application. Obviously, the described embodiments are only a part of the embodiments of this application, rather than all the embodiments. Based on the embodiments in this application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of this application.

[0067] To better understand the technical solution provided by this application, the data processing method provided by this application will be described below with reference to some drawings. As Figure 3 shown, the data processing method provided in the embodiments of this application includes S1-S4 below. Among them, the Figure 3 is a flowchart of a data processing method provided in the embodiments of this application.

[0068] S1: Obtain the three-dimensional mesh to be processed and the reference three-dimensional mesh.

[0069] Among them, the three-dimensional mesh to be processed refers to the three-dimensional mesh that needs to be evaluated for mesh performance; and the three-dimensional mesh to be processed is used to describe the state of the object to be processed (for example, face, an object, a creature, etc.) in three-dimensional space. The object to be processed refers to the object described by the three-dimensional mesh to be processed; and this application does not limit the object to be processed. For example, the object to be processed can be a face, an object, a building, or a creature, etc.

[0070] It should be noted that this application does not limit the implementation manner of the three-dimensional mesh. For example, it can be implemented using a mesh grid (for example, Figure 1 the mesh grid shown) so that the three-dimensional mesh includes multiple vertices, the state characterization data of each vertex, and the edges for connecting different vertices. Among them, for any vertex in the three-dimensional mesh, the state characterization data of the vertex can be used to describe the state of the vertex, and this application does not limit the implementation manner of the state characterization data of the vertex. For example, it can at least include two-dimensional plane position description data (such as UV coordinates, etc.) and three-dimensional space position description data (such as XYZ coordinates, etc.).

[0071] In addition, the present application does not limit the implementation manner of the above-mentioned three-dimensional mesh to be processed. For the convenience of understanding, two examples are described below.

[0072] Example 1. In some application scenarios (for example, scenarios such as quantitative processing of the standardization of a reconstructed three-dimensional mesh), the above-mentioned three-dimensional mesh to be processed may refer to a three-dimensional mesh obtained by performing three-dimensional reconstruction processing on a certain image (such as an image input by a user), so that the mesh performance evaluation task for the reconstructed three-dimensional mesh can be completed through the mesh performance evaluation processing of the three-dimensional mesh to be processed.

[0073] It can be seen that in a possible implementation manner, the process of obtaining the above-mentioned three-dimensional mesh to be processed may be as follows: after obtaining an object description image provided by the user (such as a face description image, etc.), the object description image can be subjected to three-dimensional reconstruction processing to obtain the three-dimensional mesh to be processed, so that the three-dimensional mesh to be processed can represent the state of the object described by the object description image (that is, the above-mentioned object to be processed) in three-dimensional space. Among them, the object description image is used to describe the object to be processed; and since the object description image is a two-dimensional image, the object description image can be used to describe the state of the object to be processed in a two-dimensional plane. In addition, the present application does not limit the manner of providing the object description image. For example, the object description image may refer to an image specified by an image selection operation triggered by the user. Another example is that the object description image may refer to an image collected by the user with a certain image acquisition device. Still another example is that the object description image may refer to an image input by the user with a certain input device.

[0074] Example 2. In some application scenarios (such as scenarios for training a three-dimensional reconstruction model), the three-dimensional mesh to be processed may refer to a three-dimensional mesh obtained by performing three-dimensional reconstruction processing on an image using the three-dimensional reconstruction model, so that the model performance of the three-dimensional reconstruction model can be determined through the mesh performance evaluation processing of the three-dimensional mesh to be processed. Among them, the three-dimensional reconstruction model is used to perform three-dimensional reconstruction processing on the input data of the three-dimensional reconstruction model (such as an image); and the embodiments of the present application do not limit the implementation manner of the three-dimensional reconstruction model.

[0075] It can be seen that, in a possible implementation manner, the process of obtaining the above-mentioned three-dimensional mesh to be processed can be as follows: For any round of training process, after obtaining a sample image, the three-dimensional reconstruction model can be used to perform three-dimensional reconstruction processing on the sample image, and the three-dimensional mesh to be processed is obtained and output, so that the three-dimensional mesh to be processed can represent the three-dimensional reconstruction result of the sample image. Among them, the sample image refers to the image required for training the three-dimensional reconstruction model; moreover, the present application does not limit the implementation manner of the sample image. For example, the sample image can be any image in the sample image set required for training the three-dimensional reconstruction model. In addition, the present application also does not limit the process of obtaining the sample image.

[0076] The reference three-dimensional mesh refers to the three-dimensional mesh required for evaluating the mesh performance of the above-mentioned three-dimensional mesh to be processed, so that subsequently, with the reference three-dimensional mesh as the benchmark, the mesh performance of the three-dimensional mesh to be processed can be measured by calculating the relative difference between the three-dimensional mesh to be processed and the reference three-dimensional mesh. It can be seen that the reference three-dimensional mesh can be used to describe the state presented by the above-mentioned object in three-dimensional space when the object to be processed is in a standard state in one or more mesh performance evaluation dimensions.

[0077] In addition, the present application does not limit the implementation manner of the above-mentioned reference three-dimensional mesh. For example, in some application scenarios (such as, the scenario of evaluating the normality of a three-dimensional mesh, etc.), the reference three-dimensional mesh can be a pre-set normalized three-dimensional mesh template (for example, Figure 2 the three-dimensional mesh shown, etc.), so that the reference three-dimensional mesh can represent the state presented by the object in three-dimensional space when the object is represented in a normalized manner. Among them, the normalized three-dimensional mesh template is used to represent the characteristics of the three-dimensional mesh in a normalized state; moreover, the present application does not limit the acquisition method of the normalized three-dimensional mesh template. For example, it can be pre-set by relevant personnel.

[0078] For another example, in some application scenarios (such as, the scenario of evaluating the accuracy of a three-dimensional mesh, etc.), the reference three-dimensional mesh can be a labeled three-dimensional mesh pre-set for the above-mentioned three-dimensional mesh to be processed, so that the labeled three-dimensional mesh can accurately represent the actual state of the above-mentioned object to be processed in three-dimensional space. Among them, the labeled three-dimensional mesh is used to accurately represent the actual state of the above-mentioned object to be processed in three-dimensional space; moreover, the present application does not limit the acquisition method of the labeled three-dimensional mesh. For example, it can be pre-set by relevant personnel.

[0079] In addition, the present application does not limit the acquisition method of the above-mentioned reference three-dimensional mesh. For example, the reference three-dimensional mesh can be pre-set by relevant personnel according to the mesh performance evaluation requirements of the actual application scenario, which is beneficial to improving the mesh performance evaluation effect.

[0080] Based on the relevant content of S1 above, for a to-be-processed three-dimensional mesh, if it is desired to perform mesh performance evaluation on the to-be-processed three-dimensional mesh, it is necessary not only to obtain the to-be-processed three-dimensional mesh, but also to obtain the reference three-dimensional mesh corresponding to the to-be-processed three-dimensional mesh, so that the mesh performance of the to-be-processed three-dimensional mesh can be measured with the reference three-dimensional mesh as a benchmark subsequently.

[0081] S2: Draw a first planar representation image of the to-be-processed three-dimensional mesh and a second planar representation image of the reference three-dimensional mesh in a preset two-dimensional plane space; the first planar representation image is used to represent the state presented by the vertices in the to-be-processed three-dimensional mesh in the preset two-dimensional plane space; the second planar representation image is used to represent the state presented by the vertices in the reference three-dimensional mesh in the preset two-dimensional plane space; the preset two-dimensional plane space includes at least one set of anchor points.

[0082] Among them, the preset two-dimensional plane space refers to the two-dimensional plane space required for mesh performance evaluation processing of a three-dimensional mesh.

[0083] In addition, the present application does not limit the implementation manner of the above-mentioned preset two-dimensional plane space. For example, in some application scenarios, the preset two-dimensional plane space can adopt a preset r h ×r w plane blank image I for implementation. Among them, r h represents the size of the preset two-dimensional plane space in one dimension (for example, the pixel row direction or height); r w represents the size of the preset two-dimensional plane space in another dimension (for example, the pixel column direction or width); and the present application does not limit the implementation manner of the r h and r w For example, in some application scenarios, in order to balance the application scope and the mesh performance evaluation effect, r h = r w = 1280. That is, in a possible implementation manner, the preset two-dimensional plane space can be implemented using a 1280×1280 plane blank image I.

[0084] In addition, for the above-mentioned preset two-dimensional plane space (for example, the r h ×r w plane blank image I, etc.), a large number of anchor points are distributed in the preset two-dimensional plane space so that different anchor points are used to represent different positions in the preset two-dimensional plane space. For example, when the preset two-dimensional plane space adopts r h ×r wWhen implemented on the planar blank image I, the anchor points distributed in the preset two-dimensional planar space can refer to the pixel points that appear in the planar blank image I, so that r anchor points are distributed in the preset two-dimensional planar space. h ×r w anchor points.

[0085] In addition, in order to better improve the grid performance evaluation effect, the anchor points in the above-mentioned preset two-dimensional planar space can be used to construct at least one anchor point set, so that each anchor point set can represent some anchor points in the preset two-dimensional planar space, and there are differences between the anchor points represented by different anchor point sets (for example, there is no intersection between different anchor point sets, etc.), so that different anchor point sets can describe the preset two-dimensional planar space from different perspectives, so that the differences presented by the above-mentioned to-be-processed three-dimensional grid and the reference three-dimensional grid in the preset two-dimensional planar space can be determined more accurately and comprehensively subsequently.

[0086] Furthermore, the present application does not limit the construction method of the above at least one anchor point set. For example, in some application scenarios, the construction process of the at least one anchor point set can specifically be: randomly dividing all the anchor points in the above-mentioned preset two-dimensional planar space to obtain at least one anchor point set, so that the number of anchor points in different anchor point sets is the same, and there is no intersection between different anchor point sets. Another example is that in some application scenarios, the construction process of the at least one anchor point set can specifically be: dividing all the anchor points in the preset two-dimensional planar space row by row and column by column to obtain at least one anchor point set, so that the number of anchor point rows and the number of anchor point columns in different anchor point sets are the same, and there is no intersection between different anchor point sets.

[0087] In fact, in order to better improve the grid performance evaluation effect, at least one anchor point set with equal row spacing and equal column spacing can be constructed, so that each anchor point set can represent the global state of the above-mentioned preset two-dimensional planar space, and different anchor point sets are used for the global states of the preset two-dimensional planar space at different angles. Based on this, it can be known that in a possible implementation manner, when the preset two-dimensional planar space includes at least one anchor point set, the at least one anchor point set can include N anchor point sets arranged in sequence with equal row spacing and equal column spacing, so that the number of anchor points in each anchor point set is equal, so that the number of anchor points in each anchor point set can be determined according to the following formula (1), and N is a positive integer.

[0088]

[0089] In the formula, E number represents the number of anchor points in any one anchor point set; r h represents the size of the above-mentioned preset two-dimensional planar space in one dimension (for example, the pixel row direction or height); r wrepresents the size of the preset two-dimensional plane space in another dimension (for example, the pixel column direction or width); s h represents the row pitch; s w represents the column pitch.

[0090] It should be noted that equal row spacing means that for any set of anchor points, the distances between the pairs of anchor rows with the closest positions in this set of anchor points are equal, and the distance between any pair of anchor rows with the closest positions in this set of anchor points is equal to the distance between any pair of anchor rows with the closest positions in other sets of anchor points. Similarly, equal column spacing means that for any set of anchor points, the distances between the pairs of anchor columns with the closest positions in this set of anchor points are equal, and the distance between any pair of anchor columns with the closest positions in this set of anchor points is equal to the distance between any pair of anchor columns with the closest positions in other sets of anchor points.

[0091] Based on the above formula (1), in a possible implementation, when the preset two-dimensional plane space includes N sets of anchor points arranged in sequence with equal row spacing and equal column spacing, the number of anchor points in the nth set of anchor points is determined according to preset sampling parameters (such as the above s h and the above s w etc.) and the size parameters of the preset two-dimensional plane space (such as r h and r w etc.); n is a positive integer, n ≤ N. Among them, the preset sampling parameter refers to the parameter required for equally spaced sampling processing of the above preset two-dimensional plane space (such as sampling spacing, the number of sets of anchor points, etc.); this application does not limit the preset sampling parameter. For example, when performing equally spaced sampling processing with equal row spacing and equal column spacing for the preset two-dimensional plane space, the preset sampling parameter can include at least one or more of the row pitch, column pitch, and the number of sets of anchor points. The row pitch refers to the parameter required for equally spaced sampling processing in the direction of anchor rows for the preset two-dimensional plane space, so that the row pitch can represent the distance between the two anchor rows with the closest positions in any set of anchor points, so that the row pitch can represent the distance presented by the two anchor rows with the closest positions in any set of anchor points in the row direction. The column pitch refers to the parameter required for equally spaced sampling processing in the direction of anchor columns for the preset two-dimensional plane space, so that the column pitch can represent the distance between the two anchor columns with the closest positions in any set of anchor points, so that the column pitch can represent the distance presented by the two anchor columns with the closest positions in any set of anchor points in the column direction. The number of sets of anchor points refers to the number of sets of anchor points sampled from the preset two-dimensional plane space, that is, N.

[0092] It should be noted that for the number of upper - segment anchor sets, the larger the number of the anchor sets, the more accurate the grid performance metric for the three - dimensional grid, but the larger the computational amount. However, for the upper - segment row spacing and column spacing, the larger these two data are, the larger the distance between the closest anchors at any two positions in an anchor set, making the grid performance metric coarser. It can be seen that in order to better meet the grid performance evaluation requirements in different application scenarios, the above - mentioned preset sampling parameters can be set according to the grid performance evaluation requirements of the actual application scenario.

[0093] It should also be noted that this application does not limit the acquisition method of the above - mentioned preset sampling parameters. For example, it can be preset according to the application scenario. In particular, the preset sampling parameters can be preset according to the actual application scenario so that the preset sampling parameters meet the grid performance metric requirements in this application scenario.

[0094] Based on the above content, it can be known that in some application scenarios, at least one of the above - mentioned anchor sets can be obtained by performing equidistant sampling on all the anchors in the above - mentioned preset two - dimensional plane space (for example, equidistant between rows and equidistant between columns, etc.), so that each anchor set can represent the global state of the preset two - dimensional plane space to a certain extent.

[0095] In addition, this application does not limit the acquisition process of the above - mentioned at least one anchor set. For example, in some application scenarios, when the above - mentioned preset two - dimensional plane space includes at least one anchor set, and the at least one anchor set can include N anchor sets arranged in sequence with equal row spacing and equal column spacing, the acquisition process of the nth anchor set can specifically include the following steps 11 - step 13.

[0096] Step 11: Determine the starting sampling position of the nth anchor set in the preset two - dimensional plane space according to the preset sampling parameters and the arrangement serial number corresponding to the nth anchor set; the preset sampling parameters include row spacing, column spacing, and the number of anchor sets; n is a positive integer, n ≤ N.

[0097] Among them, for the relevant content of the preset sampling parameters, please refer to the above. For the sake of brevity, it will not be elaborated here.

[0098] The nth anchor set refers to the anchor set in the above - mentioned at least one anchor set that is in the nth arrangement position, where n is a positive integer and n ≤ N.

[0099] In addition, for the above - mentioned nth anchor set, the arrangement serial number corresponding to the nth anchor set is used to represent the arrangement position of the nth anchor set in the above - mentioned at least one anchor set; and this application does not limit the implementation method of the arrangement serial number corresponding to the nth anchor set. For example, in some application scenarios, the arrangement serial number corresponding to the nth anchor set can be implemented with the value of n.

[0100] In addition, for the nth anchor set mentioned above, the starting sampling position corresponding to the nth anchor set in the preset two-dimensional plane space refers to the first sampling position required when sampling the nth anchor set from within the preset two-dimensional plane space, so that the starting sampling position can represent the position of the first anchor in the nth anchor set in the preset two-dimensional plane space. Herein, the first anchor refers to the anchor ranked first in the nth anchor set.

[0101] Moreover, this application does not limit the acquisition method of the "starting sampling position corresponding to the nth anchor set in the preset two-dimensional plane space" in the above paragraph. For example, in some application scenarios, the "starting sampling position corresponding to the nth anchor set in the preset two-dimensional plane space" can be determined according to a preset rule.

[0102] For another example, in some application scenarios, the representation effect (such as comprehensiveness, etc.) of at least one of the above anchor sets for the global state of the preset two-dimensional plane space can be improved by ensuring that all anchor sets can cover all the anchors in the above preset two-dimensional plane space as comprehensively as possible. Based on this, it can be known that the "starting sampling position corresponding to the nth anchor set in the preset two-dimensional plane space" above can be determined according to formula (2) below.

[0103]

[0104] In the formula, (δ y , δ x ) represents the "starting sampling position corresponding to the nth anchor set in the preset two-dimensional plane space" above; δ y represents the position coordinate of the "starting sampling position corresponding to the nth anchor set in the preset two-dimensional plane space" in the first dimension (for example, the row direction); δ x represents the position coordinate of the "starting sampling position corresponding to the nth anchor set in the preset two-dimensional plane space" in the second dimension (for example, the column direction); n represents the arrangement serial number corresponding to the nth anchor set; N represents the number of the above anchor sets; s h represents the row pitch; s w represents the column pitch; mod represents the remainder operation.

[0105] Based on the relevant content of step 11 above, it can be known that in some application scenarios, when the above preset two-dimensional plane space is implemented using the plane blank image I of r h ×r w , N anchor sets with equal row spacing and equal column spacing can be determined starting from the pixel position (0, 0) of the plane blank image I, so that the number of anchors in each anchor set is E shown in formula (1) above number, and making the starting sampling position corresponding to the nth anchor set in the preset two-dimensional plane space be (δ y , δ x ) shown in the above formula (2), so that the positions of the other anchors in the nth anchor set except the first anchor can be deduced based on this starting sampling position later. n is a positive integer, n ≤ N, so that the finally obtained N anchor sets can comprehensively cover all the anchors in the preset two-dimensional plane space.

[0106] Step 12: Determine at least one non-starting sampling position corresponding to the nth anchor set according to the starting sampling position corresponding to the nth anchor set in the preset two-dimensional plane space and the above preset sampling parameters; n is a positive integer, n ≤ N.

[0107] Among them, the non-starting sampling position is used to describe the positions of the other anchors in the nth anchor set except the anchor at the above starting sampling position. It can be seen that in a possible implementation manner, the jth non-starting sampling position is used to describe the position of the jth non-first anchor in the nth anchor set (that is, the jth anchor among all the other anchors except the first anchor in the anchor set) in the above preset two-dimensional plane space; j is a positive integer, j ≤ N - 1.

[0108] In addition, the implementation manner of the above Step 12 is not limited in this application. For example, this Step 12 can specifically be: for the jth anchor in the nth anchor set except the anchor at the above starting sampling position, first, according to the size parameters of the above preset two-dimensional plane space (such as the above r h and r w etc.), the above preset sampling parameters (such as the above N, s h , s w etc.), and the serial number of the jth anchor in the nth anchor set corresponding to it (such as the value j), obtain position derivation parameters (such as the j, s h , c h , c w , s w etc. shown in the following formulas (3)-(5)), so that the position derivation parameters can represent the parameters required when deducing the position of the jth anchor based on the above "starting sampling position corresponding to the nth anchor set in the preset two-dimensional plane space"; then, according to this starting sampling position (such as the above (δ y , δ x)) the position derivation parameter, and a preset position derivation formula (for example, formula (3) below, etc.), to determine the j-th non-starting sampling position corresponding to the n-th anchor set, so that the j-th non-starting sampling position can represent the position of the j-th anchor in the preset two-dimensional plane space. j is a positive integer, and j ≤ N - 1.

[0109]

[0110]

[0111]

[0112] In the formula, represents the j-th non-starting sampling position corresponding to the n-th anchor set above, so that the is used to represent the position of the j-th anchor other than the anchor at the starting sampling position above in the n-th anchor set in the preset two-dimensional plane space; represents the position coordinate of the j-th non-starting sampling position corresponding to the n-th anchor set in the first dimension (for example, the row direction); represents the position coordinate of the j-th non-starting sampling position corresponding to the n-th anchor set in the second dimension (for example, the column direction); j is determined according to the arrangement serial number of the j-th anchor in the n-th anchor set, so that j can represent the arrangement position of the j-th anchor among all non-first anchors in the n-th anchor set (that is, all other anchors in the n-th anchor set except the first anchor at the starting sampling position above); c h represents the number of anchor rows in an anchor set; c w represents the number of anchor columns in an anchor set; s h represents the row pitch; s w represents the column pitch; δ y represents the position coordinate of the "starting sampling position corresponding to the n-th anchor set in the preset two-dimensional plane space" in the first dimension (for example, the row direction); δ x represents the position coordinate of the "starting sampling position corresponding to the n-th anchor set in the preset two-dimensional plane space" in the second dimension (for example, the row direction); r h represents the size of the preset two-dimensional plane space in one dimension (for example, the pixel row direction or height); r w represents the size of the preset two-dimensional plane space in the other dimension (for example, the pixel column direction or width).

[0113] It should be noted that the present application does not limit the method for determining j in the above paragraph. For example, in some application scenarios, when the arrangement serial number corresponding to the first anchor point in the nth anchor point set in the above text is 0 in the nth anchor point set, j can be directly implemented by using the arrangement serial number corresponding to the jth non-first anchor point in the nth anchor point set. Another example is that in some application scenarios, when the arrangement serial number corresponding to the first anchor point in the nth anchor point set in the nth anchor point set is 1, j = the arrangement serial number corresponding to the jth anchor point in the nth anchor point set - 1, so that j can represent the arrangement position of the jth non-first anchor point among all non-first anchor points in the nth anchor point set.

[0114] Based on the relevant content of step 12 above, for the nth anchor point set, after obtaining the corresponding starting sampling position of the nth anchor point set in the preset two-dimensional plane space, some non-starting sampling positions corresponding to the nth anchor point set in the preset two-dimensional plane space can be deduced according to the starting sampling position, the size parameters of the preset two-dimensional plane space, and the preset sampling parameters above, so that each non-starting sampling position can represent the position of the corresponding non-first anchor point in the nth anchor point set in the preset two-dimensional plane space.

[0115] Step 13: After obtaining the starting sampling position corresponding to the nth anchor point set in the preset two-dimensional plane space and at least one non-starting sampling position corresponding to the nth anchor point set, the anchor points at the starting sampling position and the anchor points at each non-starting sampling position in the preset two-dimensional plane space are aggregated to obtain the nth anchor point set; n is a positive integer, and n ≤ N.

[0116] In the present application, for the nth anchor point set, after obtaining the starting sampling position corresponding to the nth anchor point set in the preset two-dimensional plane space and at least one non-starting sampling position, the anchor points at the starting sampling position and the anchor points at each non-starting sampling position in the preset two-dimensional plane space can be aggregated to obtain the nth anchor point set, so that the position of the first anchor point in the nth anchor point set is the starting sampling position, and the positions of the other anchor points in the nth anchor point set except the first anchor point are the non-starting sampling positions (for example, the position of the jth non-first anchor point in the nth anchor point set is the jth non-starting sampling position above, j is a positive integer, and j ≤ N - 1).

[0117] Based on the relevant content of the above steps 11 to 13, in some application scenarios, for the above-mentioned preset two-dimensional plane space, the starting sampling positions and some non-starting sampling positions involved in each anchor point set can be determined according to the preset sampling parameters first; then, based on the starting sampling positions and some non-starting sampling positions involved in each anchor point set, all the anchor points in each anchor point set can be determined, so as to achieve the purpose of equidistant sampling in both the row direction and the column direction of the preset two-dimensional plane space to obtain multiple anchor point sets with equal intervals between rows and equal intervals between columns. Among them, since the anchor points in each anchor point set are distributed in the global range of the preset two-dimensional plane space, so that each anchor point set can respectively represent the global sampling result of the preset two-dimensional plane space, thus enabling each anchor point set to represent the global state of the preset two-dimensional plane space to a certain extent; also because different anchor point sets can describe the preset two-dimensional plane space from different angles, so that these anchor point sets can describe the global state of the preset two-dimensional plane space from multiple angles, thus enabling the performance of a certain three-dimensional grid to be analyzed from as many angles as possible when evaluating the grid performance according to these anchor point sets, which is beneficial to improving the grid performance evaluation effect.

[0118] The first plane representation image is used to represent the state of the vertices in the above-mentioned three-dimensional grid to be processed in the preset two-dimensional plane space (for example, the vertex position distribution state, the connection state between different vertices, etc.). For example, the first plane representation image can be implemented using the Figure 4 shown image or Figure 5 the shown image.

[0119] In addition, for the first plane representation image of the above-mentioned three-dimensional grid to be processed, the first plane representation image can be obtained by drawing the two-dimensional plane position description data (such as UV coordinates, etc.) of each vertex in the three-dimensional grid to be processed and all the edges used to connect the vertices into the preset two-dimensional plane space, so that the first plane representation image can represent the position of each vertex in the three-dimensional grid to be processed in the preset two-dimensional plane space and the connection relationship between different vertices, thus enabling the first plane representation image to represent the state (such as position, etc.) of the closed area (such as a triangular face) surrounded by some vertices in the three-dimensional grid to be processed in the preset two-dimensional plane space. It can be seen that for the first plane representation image, the first plane representation image can include multiple vertices (such as Figure 5 the shown vertex 1, etc.), the edges used to connect different vertices (such as Figure 5 the edge used to connect vertex 1 and vertex 2 shown, etc.), and some vertex surrounding areas (such as Figure 5The triangular surface formed by vertex 1, vertex 2, and vertex 3 as shown, etc., so that the first plane representation image can represent the characteristics of the to-be-processed three-dimensional mesh itself.

[0120] It should be noted that the present application does not limit the implementation manner of "drawing" in the above paragraph. For example, it can be implemented by any existing or future method that can draw a three-dimensional mesh onto a certain two-dimensional plane (such as a blank plane image, etc.).

[0121] The second plane representation image is used to represent the state of the vertices in the reference three-dimensional mesh in the preset two-dimensional plane space (such as the vertex position distribution state, the connection state between different vertices, etc.).

[0122] In addition, for the second plane representation image of the above-mentioned reference three-dimensional mesh, the second plane representation image can be obtained by drawing the two-dimensional plane position description data (such as UV coordinates, etc.) of each vertex in the reference three-dimensional mesh and all the edges used to connect the vertices into the preset two-dimensional plane space, so that the second plane representation image can represent the position of each vertex in the reference three-dimensional mesh in the preset two-dimensional plane space and the connection relationship between different vertices, thereby enabling the second plane representation image to represent the state (such as position, etc.) of the closed area (such as a triangular surface) formed by some vertices in the reference three-dimensional mesh in the preset two-dimensional plane space. It can be seen that for the second plane representation image, the second plane representation image can include multiple vertices, the edges used to connect different vertices, and some vertex enclosing areas, so that the second plane representation image can represent the characteristics of the reference three-dimensional mesh itself. It should be noted that the acquisition method of the above-mentioned second plane representation image is similar to the acquisition method of the above-mentioned first plane representation image. For the sake of brevity, it will not be elaborated here.

[0123] Based on the relevant content of S2 above, after obtaining the three-dimensional mesh to be processed and the reference three-dimensional mesh, the first planar representation image of the three-dimensional mesh to be processed and the second planar representation image of the reference three-dimensional mesh can be respectively drawn in a preset two-dimensional plane space (for example, the above-mentioned planar blank image I), so that the first planar representation image can represent the state of the three-dimensional mesh to be processed in the preset two-dimensional plane space, and the second planar representation image can represent the state of the reference three-dimensional mesh in the preset two-dimensional plane space, so that the first planar representation image can represent the characteristics of the three-dimensional mesh to be processed itself, and the second planar representation image can represent the characteristics of the reference three-dimensional mesh itself, so as to be able to complete the determination process of the difference between the three-dimensional mesh to be processed and the reference three-dimensional mesh by means of at least one anchor point set, the first planar representation image and the second planar representation image of the preset two-dimensional plane space in the subsequent process, so as to be able to realize the mesh performance evaluation process for a three-dimensional mesh by using at least one anchor point set of the preset two-dimensional plane space. Among them, because different anchor point sets can describe the preset two-dimensional plane space at different angles, so that when performing mesh performance evaluation processing on a certain three-dimensional mesh according to these anchor point sets, the performance achieved by the three-dimensional mesh can be analyzed from as many angles as possible, which is conducive to improving the mesh performance evaluation effect.

[0124] S3: Determine the first position representation data and the second position representation data of the anchor points in each anchor point set; the first position representation data is determined according to the region description information of the vertex surrounding region corresponding to the anchor point in the first planar representation image; the second position representation data is determined according to the region description information of the vertex surrounding region corresponding to the anchor point in the second planar representation image.

[0125] In this application, for the i-th anchor point in the n-th anchor point set (for example, Figure 5 the shown anchor point 1), if the position of the i-th anchor point in the preset space belongs to a vertex surrounding region in the above-mentioned first planar representation image (for example, Figure 5If the area occupied by the triangular surface (formed by vertex 1, vertex 2, and vertex 3) shown in the preset space, it can be determined that the $i$-th anchor point falls within this vertex enclosing region. Therefore, the corresponding relationship between the $i$-th anchor point and this vertex enclosing region can be constructed, so that this corresponding relationship can represent that this vertex enclosing region is the vertex enclosing region corresponding to the $i$-th anchor point in the first planar representation image, so that subsequently, based on the region description information of the vertex enclosing region corresponding to the $i$-th anchor point in the first planar representation image, the first position representation data of the $i$-th anchor point can be determined, so that the first position representation data can represent the characteristics presented by the above-mentioned three-dimensional mesh to be processed under the $i$-th anchor point. Among them, the region description information is used to describe this vertex enclosing region; moreover, the present application does not limit the region description information. For example, it may include at least one of the region identifier of this vertex enclosing region and the planar positions of each vertex in this vertex enclosing region in the preset two-dimensional planar space. The region identifier is used to uniquely identify this vertex enclosing region; moreover, the present application does not limit the implementation manner of the region identifier. For example, the region identifier may be implemented by referring to the region number corresponding to this vertex enclosing region in the three-dimensional mesh to be processed. Where $i$ is a positive integer, $i\leq I$, $I$ is a positive integer, $I$ represents the number of anchor points in the $n$-th anchor point set, $n$ is a positive integer, $n\leq N$, and $N$ represents the number of anchor point sets.

[0126] It should be noted that the present application does not limit the implementation manner of the above step of "determining the first position representation data of the $i$-th anchor point based on the region description information of the vertex enclosing region corresponding to the $i$-th anchor point in the first planar representation image". For example, when the region description information includes the region identifier of this vertex enclosing region and the planar positions of each vertex in this vertex enclosing region in the preset two-dimensional planar space, the barycentric coordinates of the $i$-th anchor point within this vertex enclosing region (such as the barycentric coordinates shown in the following formulas (6)-(7)) can be calculated first, so that the barycentric coordinates can represent which weight parameters need to be used when linearly representing the position of the $i$-th anchor point using the positions of all vertices in this vertex enclosing region; then, based on the region identifier of this vertex enclosing region and the barycentric coordinates of the $i$-th anchor point within this vertex enclosing region, the first position representation data of the $i$-th anchor point can be determined, so that the first position representation data includes the region identifier and the barycentric coordinates.

[0127]

[0128]

[0129] In the formula, represents the barycentric coordinates of the $i$-th anchor point in the $n$-th anchor point set within its corresponding vertex enclosing region; indicating the position of the $i$-th anchor point in the preset two-dimensional plane space; indicating the position of the $t$-th vertex in the vertex enclosing region in the preset two-dimensional plane space, where $t$ is a positive integer, $t \leq T$, $T$ is a positive integer, and $T$ represents the number of vertices in the vertex enclosing region; indicating the weighted weight (such as a linear weight, etc.) corresponding to the vertex enclosing region.

[0130] Based on the above, in a possible implementation, when each vertex enclosing region in the above first plane representation image is a triangular face, for the $i$-th anchor point in the $n$-th anchor point set (for example, Figure 5 the anchor point 1 shown), if the $i$-th anchor point falls within a triangular face in the first plane representation image (for example, Figure 5 the triangular face formed by vertex 1, vertex 2, and vertex 3 shown), then a correspondence relationship between the anchor point and the triangular face is constructed, so that subsequently, based on the region description information of the triangular face corresponding to the $i$-th anchor point in the first plane representation image (such as at least one of the identifier of the triangular face and the planar positions of the vertices in the triangular face in the preset two-dimensional plane space, etc.), the first position representation data of the $i$-th anchor point (such as the identifier of the triangular face and the centroid coordinates of the $i$-th anchor point within the triangular face, etc.) can be determined, thereby enabling the first position representation data to represent the characteristics presented by the above-mentioned three-dimensional mesh to be processed under the $i$-th anchor point. It should be noted that this application does not limit the implementation manner of the identifier of the triangular face. For example, it can specifically be implemented by the number of the region corresponding to the triangular face in the three-dimensional mesh to be processed. Among them, $i$ is a positive integer, $i \leq I$, $I$ is a positive integer, $I$ represents the number of anchor points in the $n$-th anchor point set, $n$ is a positive integer, $n \leq N$, and $N$ represents the number of anchor point sets.

[0131] Similarly, for the i-th anchor in the n-th anchor set, if the position of the i-th anchor in the preset space falls within the area occupied by the area surrounded by a vertex in the second plane representation image above in the preset space, it can be determined that the i-th anchor falls within this vertex surrounded area. Therefore, the corresponding relationship between the i-th anchor and this vertex surrounded area can be constructed, so that the corresponding relationship can represent that this vertex surrounded area is the vertex surrounded area corresponding to the i-th anchor in the second plane representation image, so that the second position representation data of the i-th anchor can be determined according to the area description information of the vertex surrounded area corresponding to the i-th anchor in the second plane representation image, so that the second position representation data can represent the characteristics presented by the above-mentioned reference three-dimensional grid under the i-th anchor. Among them, the implementation manner of this area description information is similar to the implementation manner of the area description information above. For the sake of brevity, it will not be elaborated here. i is a positive integer, i ≤ I, I is a positive integer, I represents the number of anchors in the n-th anchor set, n is a positive integer, n ≤ N, and N represents the number of anchor sets.

[0132] It can be seen that in a possible implementation manner, when each vertex surrounded area in the above-mentioned second plane representation image is a triangular surface, for the i-th anchor in the n-th anchor set, if the i-th anchor falls within a triangular surface in the second plane representation image, the corresponding relationship between the anchor and the triangular surface is constructed, so that the second position representation data of the i-th anchor (such as the identifier of the triangular surface and the centroid coordinates of the i-th anchor within the triangular surface, etc.) can be determined according to the area description information of the triangular surface corresponding to the i-th anchor in the second plane representation image (such as at least one of the number of the triangular surface and the plane positions of each vertex in the triangular surface in the preset two-dimensional plane space, etc.), so that the second position representation data can represent the characteristics presented by the above-mentioned reference three-dimensional grid under the i-th anchor. Among them, i is a positive integer, i ≤ I, I is a positive integer, I represents the number of anchors in the n-th anchor set, n is a positive integer, n ≤ N, and N represents the number of anchor sets.

[0133] Based on the relevant content of S3 above, for each anchor in each anchor set, after obtaining the first plane representation image of the above-mentioned three-dimensional grid to be processed and the second plane representation image of the above-mentioned reference three-dimensional grid, if it is determined that the anchor (such as, Figure 5If the shown anchor point 1) falls within a vertex bounding region in the first planar representation image, it can be determined that the anchor point belongs to the valid points corresponding to the first planar representation image, and based on the region description information of the vertex bounding region (such as the number of the triangular face and the UV coordinates of each vertex in the triangular face, etc.), the first position representation data of the anchor point can be determined (such as the number of the triangular face and the centroid coordinates of the anchor point within the triangular face, etc.), so that the first position representation data can reflect the characteristics presented by the three-dimensional mesh to be processed under the i-th anchor point; however, if it is determined that the anchor point (such as, Figure 5 the shown anchor point 2) does not fall within any vertex bounding region in the first planar representation image, it can be determined that the anchor point belongs to the invalid points corresponding to the first planar representation image. Similarly, if it is determined that the anchor point falls within a vertex bounding region in the second planar representation image, based on the region description information of the vertex bounding region (such as the number of the triangular face and the UV coordinates of each vertex in the triangular face, etc.), the second position representation data of the anchor point can be determined (such as the number of the triangular face and the centroid coordinates of the anchor point within the triangular face, etc.), so that the second position representation data can reflect the characteristics presented by the reference three-dimensional mesh under the i-th anchor point; however, if it is determined that the anchor point does not fall within any vertex bounding region in the second planar representation image, it can be determined that the anchor point belongs to the invalid points corresponding to the second planar representation image.

[0134] It should be noted that since the three-dimensional meshes near the eye and oral regions are relatively complex, in some application scenarios, the anchor points (such as, Figure 5 the shown anchor point 3) falling within the eye region or the oral internal region can be directly regarded as invalid points.

[0135] S4: Determine the mesh performance representation data of the three-dimensional mesh to be processed according to the difference representation data between the first position representation data and the second position representation data.

[0136] Among them, the mesh performance representation data of the three-dimensional mesh to be processed refers to the quantization result of the mesh performance of the three-dimensional mesh to be processed, so that the mesh performance representation data is used to represent the state (such as the quantization result, etc.) presented by the three-dimensional mesh to be processed under one or more mesh performance evaluation dimensions (such as normality, etc.).

[0137] In addition, the present application does not limit the implementation manner of the mesh performance characterization data of the three-dimensional mesh to be processed above. For example, in some application scenarios (such as, in the scenario of quantifying the standardization of a reconstructed three-dimensional mesh), the mesh performance characterization data can be used to represent the quantification result presented by the three-dimensional mesh to be processed under standardization, so that the mesh performance characterization data can represent the degree of standardization of the three-dimensional mesh to be processed. It should be noted that the present application does not limit the correlation between the mesh performance characterization data and the degree of standardization. For example, in some application scenarios, there is a negative correlation between the mesh performance characterization data and the degree of standardization, that is, if the mesh performance characterization data is smaller, it can indicate that the degree of standardization of the three-dimensional mesh to be processed is higher (that is, more standardized), and vice versa, it indicates that the degree of standardization of the three-dimensional mesh to be processed is lower (that is, more distorted).

[0138] In addition, the present application does not limit the implementation manner of S4 above. For example, in some application scenarios, when the preset two-dimensional plane space above includes N anchor point sets, S4 can specifically be: First, for the i-th anchor point in the n-th anchor point set (such as, Figure 5 the anchor point 1 shown), after obtaining the first position characterization data and the second position characterization data of the i-th anchor point, the difference characterization data between the first position characterization data and the second position characterization data can be calculated, so that the difference characterization data can represent the difference presented by the three-dimensional mesh to be processed relative to the reference three-dimensional mesh at the i-th anchor point. i is a positive integer, i ≤ I, I is a positive integer, I represents the number of anchor points in the n-th anchor point set, n is a positive integer, n ≤ N, and N represents the number of anchor point sets; then, based on the difference characterization data corresponding to all anchor points in all anchor point sets, the mesh performance characterization data of the three-dimensional mesh to be processed is determined, so that the mesh performance characterization data can represent the difference presented by the three-dimensional mesh to be processed relative to the reference three-dimensional mesh, thereby enabling the mesh performance characterization data to represent the state presented by the three-dimensional mesh to be processed in one or more mesh performance evaluation dimensions (such as standardization, etc.).

[0139] It should be noted that the present application does not limit the implementation manner of the step of "determining the mesh performance characterization data of the three-dimensional mesh to be processed based on the difference characterization data corresponding to all anchor points in all anchor point sets" in the above paragraph. For example, it can specifically be: directly adding up the difference characterization data corresponding to all anchor points in all anchor point sets to obtain the mesh performance characterization data of the three-dimensional mesh to be processed.

[0140] In fact, in order to better improve the evaluation effect, the present application also provides a possible implementation manner of the determination process of the grid performance characterization data of the above-mentioned three-dimensional grid to be processed. In this implementation manner, the determination process of the grid performance characterization data of the three-dimensional grid to be processed may include the following steps 21-step 22.

[0141] Step 21: For any set of anchor points, construct a first virtual grid and a second virtual grid by using the set of anchor points, and determine the grid performance evaluation result corresponding to the set of anchor points according to the grid difference characterization data between the first virtual grid and the second virtual grid; the vertices in the first virtual grid are determined according to the first anchor points in the set of anchor points, there is a vertex surrounding area corresponding to the first anchor point in the first plane representation image, and the first description information of the vertices in the first virtual grid is determined according to the first position characterization data of the first anchor point; the vertices in the second virtual grid are determined according to the second anchor points in the set of anchor points, there is a vertex surrounding area corresponding to the second anchor point in the second plane representation image, and the second description information of the vertices in the second virtual grid is determined according to the second position characterization data of the second anchor point; the grid difference characterization data is determined according to the first description information of the vertices in the first virtual grid and the second description information of the vertices in the second virtual grid.

[0142] In this application, for the nth anchor point set, the first virtual grid constructed using the nth anchor point set can be used to characterize the state of the above-mentioned three-dimensional grid to be processed under the nth anchor point set, so that the first virtual grid can represent the characteristics of the three-dimensional grid to be processed under the nth anchor point set. Among them, the vertices in the first virtual grid are determined according to the first anchor point in the nth anchor point set, and the first description information of the vertices in the first virtual grid is determined according to the first position representation data of the first anchor point. Among them, the first anchor point refers to the valid point corresponding to the first plane representation image in the nth anchor point set, so that there is a vertex surrounding area corresponding to the first anchor point in the first plane representation image. That is, for the nth anchor point set, the first anchor point in the nth anchor point set can refer to the anchor point existing in the nth anchor point set and falling within the area included by a certain vertex in the first plane representation image. In addition, for any vertex in the first virtual grid, if the vertex is determined according to a certain first anchor point in the nth anchor point set, the first description information of the vertex is determined according to the first position representation data of this first anchor point (for example, directly determining the first position representation data of this first anchor point as the first description information of the vertex, etc.). Among them, the first description information is used to describe the state of the vertex. In addition, since the first position representation data of this first anchor point can represent the characteristics presented by the three-dimensional grid to be processed under this first anchor point, so that the first description information can also represent the characteristics presented by the three-dimensional grid to be processed under this first anchor point, thus enabling the first virtual grid including the vertex to represent the characteristics presented by the three-dimensional grid to be processed under this first anchor point. n is a positive integer, n ≤ N, and N represents the number of anchor point sets.

[0143] Similarly, for the nth anchor set, the second virtual grid constructed using the nth anchor set can be used to characterize the state of the above-mentioned reference three-dimensional grid under the nth anchor set, so that the second virtual grid can represent the characteristics of the reference three-dimensional grid under the nth anchor set. Among them, the vertices in the second virtual grid are determined according to the second anchors in the nth anchor set, and the second description information of the vertices in the second virtual grid is determined according to the second position representation data of the second anchors. Among them, the second anchor refers to the valid point corresponding to the second plane representation image in the nth anchor set, so that there is a vertex surrounding area corresponding to the second anchor in the second plane representation image. That is, for the nth anchor set, the second anchor in the nth anchor set can refer to the anchor existing in the nth anchor set and falling within a vertex inclusion area in the second plane representation image. In addition, for any vertex in the second virtual grid, if the vertex is determined according to a certain second anchor in the nth anchor set, the second description information of the vertex is determined according to the second position representation data of this second anchor (for example, directly determining the second position representation data of this second anchor as the second description information of the vertex, etc.). Among them, the second description information is used to describe the state of the vertex. In addition, since the second position representation data of this second anchor can represent the characteristics presented by the reference three-dimensional grid under this second anchor, so that the second description information can also represent the characteristics presented by the reference three-dimensional grid under this second anchor, thereby enabling the second virtual grid including the vertex to represent the characteristics presented by the reference three-dimensional grid under this second anchor. n is a positive integer, n ≤ N, and N represents the number of anchor sets.

[0144] Actually, in order to better improve the grid performance evaluation effect, the present application also provides an implementation manner of the above step of "constructing the first virtual grid and the second virtual grid using the anchor set", which may specifically include the following steps 211-step 213.

[0145] Step 211: Determine each anchor group to be used from the nth anchor set; for any anchor group to be used, the rectangle formed by all the anchors in the anchor group to be used satisfies a preset rectangle condition. Among them, n is a positive integer, n ≤ N, and N represents the number of anchor sets.

[0146] Among them, the anchor group to be used includes some anchors in the nth anchor set, and the rectangle formed by these anchors satisfies a preset rectangle condition. The preset rectangle condition refers to the condition required when determining the anchor group to be used from the nth anchor set; and the preset rectangle condition can be set according to the actual application scenario. For example, in some application scenarios, the preset rectangle condition can specifically be: the smallest rectangle.

[0147] It can be seen that in a possible implementation manner, for the nth anchor point set, an anchor point group that can form a minimum rectangle can be searched within the nth anchor point set (for example, the anchor point group including Figure 6 the anchor points a1, a2, a3, and a4 shown), and each anchor point group that can form a minimum rectangle is used as a to-be-used anchor point group, so that the to-be-used anchor point group can represent the anchor point groups that exist in the nth anchor point set and can form a minimum rectangle.

[0148] Based on the relevant content of step 211 above, for the nth anchor point set, some to-be-used anchor point groups can be searched from the nth anchor point set, so that the rectangles formed by all the anchor points in each to-be-used anchor point group meet the preset rectangle conditions, so as to be able to build a virtual three-dimensional grid by means of these to-be-used anchor point groups subsequently. Wherein, n is a positive integer, n ≤ N, and N represents the number of anchor point sets.

[0149] Step 212: For any to-be-used anchor point group determined from the nth anchor point set, if there is a vertex surrounding area corresponding to each anchor point in the to-be-used anchor point group in the first plane representation image, a first virtual grid is constructed according to all the anchor points in the to-be-used anchor point group and the first position representation data of all the anchor points; if there is a vertex surrounding area corresponding to some anchor points in the to-be-used anchor point group in the first plane representation image, and the number of these partial anchor points is not less than a preset number threshold, a first virtual grid is constructed according to these partial anchor points and the first position representation data of these partial anchor points. Wherein, n is a positive integer, n ≤ N, and N represents the number of anchor point sets.

[0150] In this application, for the gth to-be-used anchor point group determined from the nth anchor point set, if there is a vertex surrounding area corresponding to each anchor point in the gth to-be-used anchor point group in the above first plane representation image, it can be determined that all the anchor points in the gth to-be-used anchor point group fall into the corresponding vertex surrounding area in the first plane representation image, so that it can be determined that all the anchor points in the gth to-be-used anchor point group belong to the valid points corresponding to the first plane representation image. Therefore, a first virtual grid can be directly constructed according to all the anchor points in the gth to-be-used anchor point group and the first position representation data of all the anchor points, so that the first virtual grid includes all the anchor points in the gth to-be-used anchor point group, the closed area enclosed by all the anchor points (for example, two triangular faces), and the first position representation data of all the anchor points. Wherein, g is a positive integer, g ≤ G, G is a positive integer, and G represents the number of to-be-used anchor point groups determined from the nth anchor point set.

[0151] It should be noted that the present application does not limit the implementation manner of the step of "constructing the first virtual grid based on all the anchor points in the g-th anchor point group to be used". For example, in some application scenarios, when the g-th anchor point group to be used includes four anchor points, it may specifically be: based on the four anchor points in the g-th anchor point group to be used (for example, Figure 6 the four anchor points a1, a2, a3, and a4 shown in Figure 6 ), and the first position representation data of these four anchor points, construct two triangular faces in the first virtual grid (for example,

[0152] the two triangular faces shown in Figure 6 ), so that these two triangular faces can represent the connection relationship between these four anchor points and the first position representation data of these four anchor points.

[0153] It should also be noted that the present application does not limit the implementation manner of the step of "constructing two triangular faces in the first virtual grid based on the four anchor points in the g-th anchor point group to be used and the first position representation data of these four anchor points". For example, it may specifically be: first connect the four anchor points in the g-th anchor point group to be used to obtain a rectangle (for example, the smallest rectangle surrounded by these four anchor points), so that the four vertices of the rectangle are these four anchor points respectively, and the first description information of the four vertices of the rectangle is that of these four anchor points respectively; then divide the rectangle into two triangular faces by a preset method to obtain two triangular faces in the first virtual grid. Among them, the preset method can be preset. For example, it can adopt any existing or future method that can divide a rectangle into two triangles (for example, Figure 6 the method of adding a diagonal line in the rectangle shown in

[0153] In addition, for the g-th anchor group to be used determined from the n-th anchor set, if there is a vertex bounding region corresponding to some of the anchors (e.g., one anchor, two anchors, or three anchors) in the first planar representation image above, it can be determined that some of the anchors in the g-th anchor group to be used fall into the corresponding vertex bounding region in the first planar representation image. Thus, it can be determined that only some of the anchors in the g-th anchor group to be used belong to the valid points corresponding to the first planar representation image. Therefore, it can be further determined whether the number of these anchors is lower than a preset number threshold (e.g., 3). When it is determined that the number of these anchors is not lower than the preset number threshold (e.g., 3 anchors in the g-th anchor group to be used belong to the valid points corresponding to the first planar representation image, etc.), it can be determined that these anchors can form a closed region in the first virtual grid. Therefore, the first virtual grid can be constructed based on these anchors and the first position representation data of these anchors, so that the first virtual grid includes these anchors, the closed region formed by these anchors, and the first position representation data of these anchors. However, if it is determined that the number of these anchors is lower than the preset number threshold (e.g., 2 or fewer anchors in the g-th anchor group to be used belong to the valid points corresponding to the first planar representation image, etc.), it can be determined that these anchors cannot form a closed region in the first virtual grid. Therefore, the g-th anchor group to be used can be directly discarded. The preset number threshold refers to the minimum number of vertices required to construct a closed region. g is a positive integer, g ≤ G, where G is a positive integer representing the number of anchor groups to be used determined from the n-th anchor set.

[0154] It should be noted that the present application does not limit the implementation manner of the step of "constructing the first virtual grid based on these anchors and the first position representation data of these anchors" in the above paragraph. For example, in some application scenarios, when the g-th anchor group to be used includes four anchors and three of the four anchors belong to the valid points corresponding to the first planar representation image, specifically, it can be: based on these three anchors and the first position representation data of these three anchors, construct a triangular face in the first virtual grid, so that this triangular face can represent the connection relationship between these three anchors and the first position representation data of these three anchors.

[0155] In addition, for the g-th anchor group to be used determined from the n-th anchor set, if there is no vertex surrounding region corresponding to each anchor in the g-th anchor group to be used in the above-mentioned first planar representation image, it can be determined that all the anchors in the g-th anchor group to be used do not fall into the corresponding vertex surrounding region in the first planar representation image. Thus, it can be determined that all the anchors in the g-th anchor group to be used do not belong to the valid points corresponding to the first planar representation image, so the g-th anchor group to be used can be directly discarded. Here, g is a positive integer, g ≤ G, G is a positive integer, and G represents the number of anchor groups to be used determined from the n-th anchor set.

[0156] Based on the relevant content of the above-mentioned step 212, for the n-th anchor set, after finding the g-th anchor group to be used that can form the smallest rectangle from the n-th anchor set, if it is determined that all the anchors in the g-th anchor group to be used belong to the valid points corresponding to the first planar representation image, the smallest rectangle formed by the g-th anchor group to be used can be divided into two triangles, and both of these two triangles can be used as the closed regions in the first virtual grid; if it is determined that 3 anchors in the g-th anchor group to be used belong to the valid points corresponding to the first planar representation image, these 3 anchors can be connected to form a triangle, and this triangle can be used as the closed region in the first virtual grid; if it is determined that 2 anchors in the g-th anchor group to be used belong to the valid points corresponding to the first planar representation image, or it is determined that 1 anchor in the g-th anchor group to be used belongs to the valid points corresponding to the first planar representation image, or it is determined that 0 anchors in the g-th anchor group to be used belong to the valid points corresponding to the first planar representation image, the g-th anchor group to be used can be directly discarded. Here, g is a positive integer, g ≤ G, G is a positive integer, G represents the number of anchor groups to be used determined from the n-th anchor set, n is a positive integer, n ≤ N, and N represents the number of anchor sets.

[0157] Step 213: For any anchor group to be used determined from the n-th anchor set, if there is a vertex surrounding region corresponding to each anchor in the anchor group to be used in the second planar representation image, a second virtual grid is constructed based on all the anchors in the anchor group to be used and the second position representation data of all the anchors; if there is a vertex surrounding region corresponding to some anchors in the anchor group to be used in the second planar representation image, and the number of these some anchors is not less than the preset number threshold, a second virtual grid is constructed based on these some anchors and the second position representation data of these some anchors. Here, n is a positive integer, n ≤ N, and N represents the number of anchor sets.

[0158] It should be noted that the implementation manner of step 213 is similar to that of the above-mentioned step 212. For the sake of brevity, it will not be elaborated here.

[0159] It can be seen that in a possible implementation manner, step 213 above can be specifically as follows: For any anchor point group to be used determined from the nth anchor point set, when the anchor point group to be used includes four anchor points, if there are vertex enclosing regions corresponding to each anchor point in the second plane representation image above, it can be determined that all four anchor points in the anchor point group to be used belong to the valid points corresponding to the second plane representation image. Therefore, two triangular faces in the second virtual grid can be constructed based on the four anchor points in the anchor point group to be used and the second position representation data of these four anchor points, so that these two triangular faces can represent the connection relationship between these four anchor points and the second position representation data of these four anchor points. If there are vertex enclosing regions corresponding to three anchor points in the anchor point group to be used in the second plane representation image, it can be determined that the three anchor points in the anchor point group to be used belong to the valid points corresponding to the second plane representation image. Therefore, one triangular face in the second virtual grid can be constructed based on these three anchor points and the second position representation data of these three anchor points. Wherein, n is a positive integer, n ≤ N, and N represents the number of anchor point sets.

[0160] Based on the relevant content of steps 211 to 213 above, it can be known that in some application scenarios, for the nth anchor point set, the first virtual grid (such as, Figure 7 each virtual grid shown) can be constructed based on the first anchor point (that is, the valid point corresponding to the first plane representation image) in the nth anchor point set, so that the first virtual grid includes some or all of the valid points corresponding to the first plane representation image in the nth anchor point set, the first position representation data of these valid points, and the connection relationship between these valid points, thereby enabling the first virtual grid to represent the state presented by the three-dimensional grid to be processed under the nth anchor point set. Similarly, the second virtual grid can be constructed based on the second anchor point (that is, the valid point corresponding to the second plane representation image) in the nth anchor point set, so that the second virtual grid includes some or all of the valid points corresponding to the second plane representation image in the nth anchor point set, the second position representation data of these valid points, and the connection relationship between these valid points, thereby enabling the second virtual grid to represent the state presented by the reference three-dimensional grid under the nth anchor point set, so as to subsequently evaluate the grid performance of the three-dimensional grid to be processed by means of the difference between the first virtual grid and the second virtual grid. Wherein, n is a positive integer, n ≤ N, and N represents the number of anchor point sets.

[0161] It can be seen that for the nth anchor point set, after constructing the first virtual grid and the second virtual grid using the nth anchor point set, the grid difference characterization data between the first virtual grid and the second virtual grid can be calculated first based on the first description information of the vertices in the first virtual grid and the second description information of the vertices in the second virtual grid, so that the grid difference characterization data can represent the difference between the first virtual grid and the second virtual grid; then, based on the grid difference characterization data, the grid performance evaluation result corresponding to the nth anchor point set is determined, so that the grid performance evaluation result can represent the grid performance presented by the three-dimensional grid to be processed relative to the reference three-dimensional network on the nth anchor point set. Wherein, the grid performance evaluation result corresponding to the nth anchor point set is used to represent the grid performance presented by the three-dimensional grid to be processed on the nth anchor point set. n is a positive integer, n ≤ N, and N represents the number of anchor point sets.

[0162] It should be noted that the present application does not limit the determination method of the "grid difference characterization data between the first virtual grid and the second virtual grid" above. For example, it can be implemented with the help of formula (8) below.

[0163]

[0164] In the formula, ΔX n represents the grid difference characterization data between the first virtual grid and the second virtual grid, and this ΔX n can include the vertex difference characterization data of several vertices (that is, the difference between the first description information of a vertex and the second description information of this vertex); X n represents the first virtual grid, and this X n can include the first description information of these vertices; represents the second virtual grid, and this can include the second description information of these vertices.

[0165] It should also be noted that the present application does not limit the determination process of the grid performance evaluation result corresponding to the nth anchor point set above. For example, it can be implemented with the help of the Laplace loss shown in formulas (9)-(12) below.

[0166] L n = ∑ p δ p (9)

[0167] δ p = ∑ {p,q}∈E w pq (v q - v p ) = [∑ {p,q}∈E w pq vq -v p (10)

[0168]

[0169] ω pq = cotα + cotβ (12)

[0170] In the formula, L n represents the grid performance evaluation result corresponding to the nth anchor point set above; δ p represents the Laplace loss corresponding to the pth vertex in the grid difference characterization data between the first virtual grid and the second virtual grid above; ∑ p δ p represents the sum of the Laplace losses corresponding to all vertices in the grid difference characterization data; v p represents the vertex difference characterization data of the pth vertex; v q represents the vertex difference characterization data of the qth adjacent vertex having a connection relationship with the pth vertex; {p, q} ∈ E indicates that there is an edge between the pth vertex and the qth adjacent vertex, that is, there is a connection relationship; w pq represents the normalized weighted weight corresponding to the edge <v p , v q >, and ∑ {p,q}∈E w pq = 1; α and β are respectively two objects of the triangle where the edge <v p , v q > is located (for example, Figure 8 α and β shown).

[0171] Based on the relevant content of the Laplace loss above, in some application scenarios, for the first virtual grid and the second virtual grid constructed using the nth anchor point set, the grid difference characterization data between the first virtual grid and the second virtual grid may include the vertex difference characterization data of several vertices. Among them, for any vertex (for example, the pth vertex above), the vertex difference characterization data of this vertex (for example, v p above) is determined based on the difference characterization data between the first description information and the second description information of this vertex (for example, determined using formula (8) above); and the grid performance evaluation result corresponding to the nth anchor point set may be determined based on the Laplace losses corresponding to several vertices (for example, δ p above). For any vertex, the Laplace loss corresponding to this vertex is based on the vertex difference characterization data of this vertex (for example, v p above), the vertex difference characterization data of the adjacent vertices of this vertex (for example, v q) determined by the two opposite angles corresponding to the edges formed by the vertex and its adjacent vertices (for example, α and β above).

[0172] It should be noted that for the q-th vertex above, if there is a connection relationship between a certain vertex and the q-th vertex, then this vertex can be regarded as an adjacent vertex of the q-th vertex. q is a positive integer, q ≤ Q, and Q represents the number of vertices involved in the "mesh difference characterization data between the first virtual mesh and the second virtual mesh" above.

[0173] Based on the relevant content of step 21 above, for the n-th anchor set, after obtaining the first position characterization data and the second position characterization data of the anchors in the n-th anchor set, a first virtual mesh can be constructed first according to the first anchor in the n-th anchor set and the first position characterization data of the first anchor, and a second virtual mesh can be constructed according to the second anchor in the n-th anchor set and the second position characterization data of the second anchor; then calculate the mesh difference characterization data between the first virtual mesh and the second virtual mesh; then, determine the mesh performance evaluation result corresponding to the n-th anchor set according to the mesh difference characterization data, so that the mesh performance evaluation result can characterize the mesh performance presented by the three-dimensional mesh to be processed on the n-th anchor set. Wherein, n is a positive integer, n ≤ N, and N represents the number of anchor sets.

[0174] Step 22: Determine the mesh performance characterization data of the three-dimensional mesh to be processed according to the mesh performance evaluation results corresponding to at least one anchor set above.

[0175] It should be noted that the implementation manner of step 22 in this application is not limited. For example, in some possible implementation manners, step 22 may specifically be: taking the average value between the mesh performance evaluation results corresponding to all anchor sets as the mesh performance characterization data of the three-dimensional mesh to be processed. Another example is that in some possible implementation manners, step 22 may specifically be: aggregating the mesh performance evaluation results corresponding to all anchor sets to obtain the mesh performance characterization data of the three-dimensional mesh to be processed.

[0176] Based on the relevant content of steps 21 to 22 above, it can be seen that in some application scenarios, the grid performance characterization data of the above-mentioned three-dimensional grid to be processed can be determined by constructing several groups of virtual three-dimensional grids that cover the entire preset two-dimensional plane space, so that the grid performance characterization data can accurately, comprehensively, and granularly represent the quantization results presented by the three-dimensional grid to be processed under one or more grid performance evaluation dimensions (such as, normativity, etc.). This is beneficial to improving the grid performance evaluation effect. In addition, the present application also uses the Laplace loss to determine the grid performance characterization data of the three-dimensional grid to be processed, so that the grid performance characterization data can more accurately, more comprehensively, and more granularly represent the quantization results presented by the three-dimensional grid to be processed under one or more grid performance evaluation dimensions (such as, normativity, etc.). This is beneficial to better improving the grid performance evaluation effect.

[0177] Based on the relevant content of S1 to S4 above, for the data processing method provided in the embodiments of the present application, after obtaining the to-be-processed three-dimensional mesh (for example, the reconstructed three-dimensional mesh) and the reference three-dimensional mesh (for example, the pre-set standardized three-dimensional mesh template), draw the first planar representation image of the to-be-processed three-dimensional mesh and the second planar representation image of the reference three-dimensional mesh in the pre-set two-dimensional planar space (for example, a planar blank image), so that the first planar representation image is used to represent the state presented by the vertices in the to-be-processed three-dimensional mesh in the pre-set two-dimensional planar space (for example, the position distribution state of the vertices, and the connection state between different vertices, etc.), and the second planar representation image is used to represent the state presented by the vertices in the reference three-dimensional mesh in the pre-set two-dimensional planar space, so that when the pre-set two-dimensional planar space includes at least one anchor point set, determine the first position representation data and the second position representation data of the anchor points in each anchor point set, where the first position representation data is determined according to the region description information of the vertex surrounding region corresponding to the anchor point in the first planar representation image, so that the first position representation data can represent to a certain extent the state presented by the to-be-processed three-dimensional mesh at the anchor point; the second position representation data is determined according to the region description information of the vertex surrounding region corresponding to the anchor point in the second planar representation image, so that the second position representation data can represent to a certain extent the state presented by the reference three-dimensional mesh at the anchor point; then, determine the mesh performance representation data of the to-be-processed three-dimensional mesh according to the difference representation data between the first position representation data and the second position representation data. Among them, because the difference representation data can represent the difference between the to-be-processed three-dimensional mesh and the reference three-dimensional mesh, so that the mesh performance representation data determined based on the difference representation data can represent the mesh performance presented by the to-be-processed three-dimensional mesh relative to the reference three-dimensional mesh, so that the mesh performance representation data can represent the quantization result of the mesh performance presented by the to-be-processed three-dimensional mesh under one or more mesh performance evaluation dimensions (for example, dimensions such as standardization), so as to achieve the purpose of quantitatively evaluating a three-dimensional mesh under these mesh performance evaluation dimensions, and thus can effectively avoid defects (such as poor mesh performance evaluation effect) caused by the inability to perform quantitative processing for a certain mesh performance evaluation dimension (for example, dimensions such as standardization) or a poor quantization scheme for a certain mesh performance evaluation dimension (for example, dimensions such as accuracy), which is conducive to improving the mesh performance evaluation effect.

[0178] In addition, the present application does not limit the application scenarios of the above data processing method. For the convenience of understanding, the following takes two application scenarios as examples for illustration.

[0179] Scenario 1, the data processing method provided by the present application can be used to implement the model training process.

[0180] Based on this, it can be known that in a possible implementation manner, when the above-mentioned three-dimensional mesh to be processed is constructed using a three-dimensional reconstruction model, the data processing method provided by this application not only includes the above-mentioned S1 - S4, but may also include the following step 31. Among them, the execution time of this step 31 is later than the execution time of S4.

[0181] Step 31: Update the three-dimensional reconstruction model according to the mesh performance characterization data of the three-dimensional mesh to be processed.

[0182] Among them, the three-dimensional reconstruction model is used to perform three-dimensional reconstruction processing on the input data (for example, an image) of the three-dimensional reconstruction model.

[0183] Based on the relevant content of the above step 31, for the three-dimensional reconstruction model, after obtaining the three-dimensional mesh to be processed constructed by the three-dimensional reconstruction model, the above-mentioned reference three-dimensional mesh can be used as label information to perform mesh performance evaluation processing on the three-dimensional mesh to be processed, so as to obtain the mesh performance characterization data of the three-dimensional mesh to be processed, so that the mesh performance characterization data can to a certain extent reflect the three-dimensional reconstruction performance of the three-dimensional reconstruction model, so that the three-dimensional reconstruction model can be updated based on the mesh performance characterization data subsequently, so that the updated three-dimensional reconstruction model has better three-dimensional reconstruction performance, so that the new three-dimensional mesh constructed using the updated three-dimensional reconstruction model presents a better performance state under one or more mesh performance evaluation dimensions (such as normality, etc.).

[0184] It can be seen that in a possible implementation manner, the training process of the above-mentioned three-dimensional reconstruction model may include the following steps 32 - step 37.

[0185] Step 32: Determine the image to be processed from the sample image set.

[0186] Among them, the sample image set refers to the training data set required when training the three-dimensional reconstruction model; and this application does not limit the implementation manner of the sample image set.

[0187] The image to be processed refers to the image extracted from the above-mentioned sample image set and needs to be subjected to three-dimensional reconstruction processing during the current round of training; and this image to be processed is used to describe the object to be processed. Among them, the object to be processed refers to the object described by this image to be processed.

[0188] In addition, this application does not limit the acquisition method of the above-mentioned image to be processed. For example, for any round of training process, the acquisition process of the image to be processed can be: randomly select an image from the images in the sample image set that have not been processed yet, and use the selected image as the image to be processed.

[0189] In addition, this application does not limit the number of the above-mentioned images to be processed.

[0190] Based on the relevant content of step 32 above, in some application scenarios, for the current round of training process, a to-be-processed image can be determined from the sample image set, so that subsequent model performance evaluation and model update processing can be carried out based on the to-be-processed image.

[0191] Step 33: Perform three-dimensional reconstruction processing on the to-be-processed image by using a three-dimensional reconstruction model to obtain a to-be-processed three-dimensional grid corresponding to the to-be-processed image, so that the to-be-processed three-dimensional grid is used to describe the state of the to-be-processed object in the three-dimensional space.

[0192] In this application, for the current round of training process, after obtaining the to-be-processed image, the to-be-processed image can be input into the three-dimensional reconstruction model, so that the three-dimensional reconstruction model can perform three-dimensional reconstruction processing on the to-be-processed image, obtain and output a to-be-processed three-dimensional grid corresponding to the to-be-processed image, so that the processed three-dimensional grid is used to describe the state of the to-be-processed object in the three-dimensional space, so that subsequent model performance evaluation processing can be carried out based on the to-be-processed three-dimensional grid and the above-mentioned reference three-dimensional grid.

[0193] It should be noted that the implementation manner of the reference three-dimensional grid in this application is not limited. For example, in some application scenarios (such as scenarios where quantitative processing in terms of standardization needs to be performed on the to-be-processed three-dimensional grid), the reference three-dimensional grid can refer to a pre-set standardized three-dimensional grid template, and the reference three-dimensional grid can remain unchanged during multiple rounds of training processes, so that it is not necessary to obtain the reference three-dimensional grid once in each round of training process, which is beneficial to simplifying the model training process. Another example is that in some application scenarios (such as scenarios where quantitative processing in terms of accuracy needs to be performed on the to-be-processed three-dimensional grid), the reference three-dimensional grid can refer to a labeled three-dimensional grid pre-set for the above-mentioned to-be-processed image, so that the labeled three-dimensional grid can accurately represent the state of the to-be-processed object in the three-dimensional space, so that the reference three-dimensional grid will be updated accordingly as the to-be-processed image is updated, which is beneficial to improving the model training effect.

[0194] Step 34: Draw a first plane representation image of the to-be-processed three-dimensional grid and a second plane representation image of the reference three-dimensional grid in a preset two-dimensional plane space; the first plane representation image is used to represent the state presented by the vertices in the to-be-processed three-dimensional grid in the preset two-dimensional plane space; the second plane representation image is used to represent the state presented by the vertices in the reference three-dimensional grid in the preset two-dimensional plane space; the preset two-dimensional plane space includes at least one anchor point set.

[0195] It should be noted that for the relevant content of step 34, please refer to S2 above. For the sake of brevity, it will not be elaborated here.

[0196] Step 35: Determine the first position representation data and the second position representation data of the anchor points in each anchor point set; the first position representation data is determined based on the region description information of the vertex surrounding region corresponding to the anchor point in the first plane representation image; the second position representation data is determined based on the region description information of the vertex surrounding region corresponding to the anchor point in the second plane representation image.

[0197] It should be noted that for the relevant content of Step 35, please refer to S3 above. For the sake of brevity, it will not be elaborated here.

[0198] Step 36: Determine the mesh performance representation data of the three-dimensional mesh to be processed according to the difference representation data between the first position representation data and the second position representation data.

[0199] It should be noted that for the relevant content of Step 36, please refer to S4 above. For the sake of brevity, it will not be elaborated here.

[0200] Step 37: Update the three-dimensional reconstruction model according to the mesh performance representation data of the three-dimensional mesh to be processed, and return to execute Step 32 and its subsequent steps above until a preset stop condition is reached.

[0201] Among them, the preset stop condition refers to the condition required when ending the model training process; moreover, the present application does not limit this preset stop condition. For example, the preset stop condition may include: the model loss of the three-dimensional reconstruction model above is lower than a preset loss threshold. Another example is that the preset stop condition may include: the change rate of the model loss of the three-dimensional reconstruction model is lower than a preset change rate threshold. Still another example is that the preset stop condition may include: the number of updates of the three-dimensional reconstruction model reaches a preset number threshold.

[0202] In addition, for the model loss of the three-dimensional reconstruction model in the above paragraph, the model loss is used to characterize the three-dimensional reconstruction performance of the three-dimensional reconstruction model; and the model loss is determined based on the mesh performance representation data of the three-dimensional mesh to be processed above. It should be noted that the present application does not limit the acquisition method of this model loss.

[0203] Based on the relevant content of Steps 32 to 37 above, it can be seen that in some application scenarios, for the three-dimensional reconstruction model, the three-dimensional reconstruction model can complete three-dimensional reconstruction learning through multiple rounds of training processes, so that the finally trained three-dimensional reconstruction model can have better three-dimensional reconstruction performance, so as to be able to use the three-dimensional reconstruction model to complete some three-dimensional reconstruction tasks later (for example, the rendering processing task involved in Scenario 2 below).

[0204] Scenario 2, the data processing method provided by the present application can be used to implement a rendering processing scenario.

[0205] Based on this, it can be known that in a possible implementation manner, when the above-mentioned three-dimensional mesh to be processed is obtained by performing three-dimensional reconstruction processing on an image provided by a user, the data processing method provided by this application not only includes the above-mentioned S1 - S4, but may also include the following steps 41 - step 42. Among them, the execution time of step 41 is later than the execution time of S4.

[0206] Step 41: If the mesh performance characterization data of the three-dimensional mesh to be processed reaches a preset performance threshold, then render the target texture map onto the three-dimensional mesh to be processed to obtain a rendering result.

[0207] Among them, the preset performance threshold is used to represent the state that at least needs to be achieved in terms of the mesh performance of a three-dimensional mesh that can perform texture map rendering processing; moreover, the preset performance threshold can be set according to the actual application scenario.

[0208] The target texture map refers to the texture map material specified in advance by the user, so that the target texture map can represent the texture map required when performing texture map rendering processing on the above-mentioned three-dimensional mesh to be processed. It should be noted that this application does not limit the implementation manner of the target texture map. For example, in some application scenarios, the target texture map may refer to the texture map material made by relevant personnel based on a preset three-dimensional mesh template and UV unfolding diagram.

[0209] The rendering result refers to the result obtained by performing texture map rendering processing on the three-dimensional mesh to be processed using the target texture map; moreover, this application does not limit the acquisition method of the rendering result. For example, it can be implemented using any existing or future method that can render a texture map onto a three-dimensional mesh (such as a rendering processing method implemented by means of a pre-constructed three-dimensional rendering engine, etc.).

[0210] Step 42: Display the rendering result.

[0211] Based on the relevant content of steps 41 to 42 above, for some application scenarios, after obtaining the image provided by the user, three-dimensional reconstruction processing can be performed on the image first to obtain a three-dimensional mesh to be processed; then, using the above-mentioned reference three-dimensional mesh as a reference, mesh performance evaluation processing is performed on the three-dimensional mesh to be processed to obtain the mesh performance characterization data of the three-dimensional mesh to be processed, so that the mesh performance characterization data can represent the state presented by the three-dimensional mesh to be processed under one or more mesh performance evaluation dimensions (such as normality, etc.), so that when it is determined that the mesh performance characterization data reaches the preset performance threshold, it can be determined that the three-dimensional mesh to be processed has good mesh performance. Therefore, the target texture specified by the user can be rendered to the three-dimensional mesh to be processed and the rendering result can be displayed, so that the user can see the rendering result. Among them, because the three-dimensional mesh to be processed has good mesh performance, the finally determined rendering result can better meet the image processing requirements, which is conducive to improving the image processing effect.

[0212] Based on the data processing method provided in the embodiments of the present application, the embodiments of the present application also provide a data processing device, which will be described below in combination with Figure 9 for explanation and illustration. Among them, Figure 9 is a schematic structural diagram of a data processing device provided in the embodiments of the present application. It should be noted that for the technical details of the data processing device provided in the embodiments of the present application, please refer to the relevant content of the above data processing method.

[0213] As Figure 9 shown, the data processing device 900 provided in the embodiments of the present application includes:

[0214] A mesh acquisition unit 901, configured to acquire a three-dimensional mesh to be processed and a reference three-dimensional mesh;

[0215] An image drawing unit 902, configured to draw a first plane representation image of the three-dimensional mesh to be processed and a second plane representation image of the reference three-dimensional mesh in a preset two-dimensional plane space; the first plane representation image is used to represent the state presented by the vertices in the three-dimensional mesh to be processed in the preset two-dimensional plane space; the second plane representation image is used to represent the state presented by the vertices in the reference three-dimensional mesh in the preset two-dimensional plane space; the preset two-dimensional plane space includes at least one set of anchor points;

[0216] A first determination unit 903, configured to determine first position characterization data and second position characterization data of the anchor points in each set of anchor points; the first position characterization data is determined according to the region description information of the vertex surrounding region corresponding to the anchor point in the first plane representation image; the second position characterization data is determined according to the region description information of the vertex surrounding region corresponding to the anchor point in the second plane representation image;

[0217] A second determination unit 904, configured to determine the mesh performance characterization data of the to-be-processed three-dimensional mesh according to the difference characterization data between the first position characterization data and the second position characterization data.

[0218] In a possible implementation manner, the second determination unit 904 includes:

[0219] A first determination subunit, configured to, for any anchor point set, construct a first virtual mesh and a second virtual mesh by using the anchor point set, and determine the mesh performance evaluation result corresponding to the anchor point set according to the mesh difference characterization data between the first virtual mesh and the second virtual mesh; the vertices in the first virtual mesh are determined according to the first anchor points in the anchor point set, there is a vertex surrounding region corresponding to the first anchor points in the first plane characterization image, and the first description information of the vertices in the first virtual mesh is determined according to the first position characterization data of the first anchor points; the vertices in the second virtual mesh are determined according to the second anchor points in the anchor point set, there is a vertex surrounding region corresponding to the second anchor points in the second plane characterization image, and the second description information of the vertices in the second virtual mesh is determined according to the second position characterization data of the second anchor points; the mesh difference characterization data is determined according to the difference characterization data between the first description information of the vertices in the first virtual mesh and the second description information of the vertices in the second virtual mesh;

[0220] A second determination subunit, configured to determine the mesh performance characterization data of the to-be-processed three-dimensional mesh according to the mesh performance evaluation results corresponding to the at least one anchor point set.

[0221] In a possible implementation manner, the first determination subunit includes:

[0222] A third determination subunit, configured to determine each to-be-used anchor point group from the anchor point set; for any to-be-used anchor point group, the rectangle formed by all the anchor points in the to-be-used anchor point group satisfies a preset rectangle condition;

[0223] A first construction subunit, configured to, for any to-be-used anchor point group, if there is a vertex surrounding region corresponding to each anchor point in the to-be-used anchor point group in the first plane characterization image, construct the first virtual mesh according to all the anchor points in the to-be-used anchor point group and the first position characterization data of all the anchor points; if there is a vertex surrounding region corresponding to some of the anchor points in the to-be-used anchor point group in the first plane characterization image, and the number of the some anchor points is not less than a preset number threshold, construct the first virtual mesh according to the some anchor points and the first position characterization data of the some anchor points;

[0224] The second construction subunit is used to, for any anchor point group to be used, if there is a vertex enclosing region corresponding to each anchor point in the anchor point group to be used in the second plane representation image, construct the second virtual grid according to all the anchor points in the anchor point group to be used and the second position representation data of all the anchor points; if there is a vertex enclosing region corresponding to some of the anchor points in the anchor point group to be used in the second plane representation image, and the number of the some anchor points is not less than a preset number threshold, construct the second virtual grid according to the some anchor points and the second position representation data of the some anchor points.

[0225] In a possible implementation manner, the anchor point group to be used includes four anchor points;

[0226] The first construction subunit is specifically used to: construct two triangular faces in the first virtual grid according to the four anchor points in the anchor point group to be used and the first position representation data of the four anchor points;

[0227] The second construction subunit is specifically used to: construct two triangular faces in the second virtual grid according to the four anchor points in the anchor point group to be used and the second position representation data of the four anchor points.

[0228] In a possible implementation manner, the number of the some anchor points is three;

[0229] The first construction subunit is specifically used to: construct one triangular face in the first virtual grid according to the some anchor points and the first position representation data of the some anchor points;

[0230] The second construction subunit is specifically used to: construct one triangular face in the second virtual grid according to the some anchor points and the second position representation data of the some anchor points.

[0231] In a possible implementation manner, the grid difference representation data includes vertex difference representation data of several vertices; for any vertex, the vertex difference representation data of the vertex is determined according to the difference representation data between the first description information of the vertex and the second description information of the vertex;

[0232] The grid performance evaluation result is determined according to the Laplace losses corresponding to the several vertices. For any vertex, the Laplace loss corresponding to the vertex is determined according to the vertex difference representation data of the vertex, the vertex difference representation data of the adjacent vertices of the vertex, and the two diagonals corresponding to the edge formed by the vertex and the adjacent vertices of the vertex.

[0233] In a possible implementation manner, the at least one anchor point set includes N anchor point sets arranged in sequence, equidistant between rows and equidistant between columns, and N is a positive integer;

[0234] The data processing device 900 further includes:

[0235] An anchor set acquisition unit, configured to determine a starting sampling position corresponding to the nth anchor set in the preset two-dimensional plane space according to a preset sampling parameter and an arrangement serial number corresponding to the nth anchor set; the preset sampling parameter includes a row pitch, a column pitch, and the number of anchor sets; determine at least one non-starting sampling position corresponding to the nth anchor set according to the starting sampling position and the preset sampling parameter; and set the anchors at the starting sampling position and the anchors at each non-starting sampling position in the preset two-dimensional plane space to obtain the nth anchor set; n is a positive integer, and n ≤ N.

[0236] In a possible implementation manner, the vertex surrounding region is a triangular face; the region description information includes at least one of an identifier of the triangular face and planar positions of each vertex in the triangular face in the preset two-dimensional plane space.

[0237] In a possible implementation manner, the three-dimensional mesh to be processed is constructed by using a three-dimensional reconstruction model;

[0238] The data processing device 900 further includes:

[0239] A model update unit, configured to update the three-dimensional reconstruction model according to the mesh performance characterization data.

[0240] Based on the relevant content of the above data processing device 900, for the data processing device 900 provided in the embodiments of the present application, after obtaining the to-be-processed three-dimensional mesh (for example, the reconstructed three-dimensional mesh) and the reference three-dimensional mesh (for example, the pre-set normalized three-dimensional mesh template), draw the first planar representation image of the to-be-processed three-dimensional mesh and the second planar representation image of the reference three-dimensional mesh in a pre-set two-dimensional planar space (for example, a planar blank image), so that the first planar representation image is used to represent the state presented by the vertices in the to-be-processed three-dimensional mesh in the pre-set two-dimensional planar space (for example, the position distribution state of the vertices, and the connection state between different vertices, etc.), and the second planar representation image is used to represent the state presented by the vertices in the reference three-dimensional mesh in the pre-set two-dimensional planar space, so that when the pre-set two-dimensional planar space includes at least one anchor point set, determine the first position representation data and the second position representation data of the anchor points in each anchor point set, where the first position representation data is determined according to the region description information of the vertex surrounding region corresponding to the anchor point in the first planar representation image, so that the first position representation data can represent to a certain extent the state presented by the to-be-processed three-dimensional mesh at the anchor point; the second position representation data is determined according to the region description information of the vertex surrounding region corresponding to the anchor point in the second planar representation image, so that the second position representation data can represent to a certain extent the state presented by the reference three-dimensional mesh at the anchor point; then, determine the mesh performance representation data of the to-be-processed three-dimensional mesh according to the difference representation data between the first position representation data and the second position representation data. Among them, since the difference representation data can represent the difference between the to-be-processed three-dimensional mesh and the reference three-dimensional mesh, so that the mesh performance representation data determined based on the difference representation data can represent the mesh performance presented by the to-be-processed three-dimensional mesh relative to the reference three-dimensional mesh, so that the mesh performance representation data can represent the quantization result of the mesh performance presented by the to-be-processed three-dimensional mesh under one or more mesh performance evaluation dimensions (for example, dimensions such as normality), so as to achieve the purpose of quantitatively evaluating a three-dimensional mesh under these mesh performance evaluation dimensions, thus effectively avoiding defects (such as poor mesh performance evaluation effect) caused by the inability to perform quantitative processing for a certain mesh performance evaluation dimension (for example, dimensions such as normality) or the poor quantization scheme for a certain mesh performance evaluation dimension (for example, dimensions such as accuracy), and further being beneficial to improving the mesh performance evaluation effect.

[0241] In addition, an embodiment of the present application further provides an electronic device, which includes a processor and a memory: the memory is used to store instructions or computer programs; the processor is used to execute the instructions or computer programs in the memory, so that the electronic device executes any implementation manner of the data processing method provided by the embodiment of the present application.

[0242] See Figure 10 , which shows a schematic structural diagram of an electronic device 1000 suitable for implementing the embodiments of the present disclosure. The terminal devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet Computers), PMPs (Portable Multimedia Players), in-vehicle terminals (such as in-vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 10 The electronic device shown is only an example and should not impose any limitations on the functions and usage scope of the embodiments of the present disclosure.

[0243] As Figure 10 shown, the electronic device 1000 may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 1001, which may perform various appropriate actions and processes according to the programs stored in the read-only memory (ROM) 1002 or the programs loaded from the storage device 1008 into the random access memory (RAM) 1003. In the RAM 1003, various programs and data required for the operation of the electronic device 1000 are also stored. The processing device 1001, the ROM 1002, and the RAM 1003 are connected to each other through a bus 1004. The input / output (I / O) interface 1005 is also connected to the bus 1004.

[0244] Generally, the following devices may be connected to the I / O interface 1005: an input device 1006 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 1007 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 1008 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 may allow the electronic device 1000 to communicate with other devices wirelessly or wiredly to exchange data. Although Figure 10 shows the electronic device 1000 having various devices, it should be understood that it is not required to implement or have all the shown devices. Instead, more or fewer devices may be implemented or had.

[0245] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program includes program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 1009, or installed from the storage device 1008, or installed from the ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment of the present disclosure are executed.

[0246] The electronic device provided by the embodiment of the present disclosure and the method provided by the above embodiment belong to the same inventive concept. The technical details not described in detail in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0247] An embodiment of the present application also provides a computer-readable medium, in which instructions or a computer program are stored. When the instructions or the computer program run on a device, the device is enabled to execute any implementation manner of the data processing method provided by the embodiment of the present application.

[0248] It should be noted that the above-mentioned computer-readable medium in the present disclosure may be a computer-readable signal medium, 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, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium 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 the present disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, apparatus, or device. In the present disclosure, the computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take various 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 the computer-readable storage medium, and the computer-readable signal medium can send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted by any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0249] In some embodiments, the client and the server can communicate using any currently known or future-developed network protocol such as HTTP (Hyper Text Transfer Protocol), and can be interconnected with digital data communication in any form or medium (for example, a communication network). Examples of the communication network include a local area network ("LAN"), a wide area network ("WAN"), the Internet (for example, the Internet), and a peer-to-peer network (for example, an ad hoc peer-to-peer network), as well as any currently known or future-developed network.

[0250] The above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist separately and not be assembled into the electronic device.

[0251] The above-mentioned computer-readable medium carries one or more programs, and when the one or more programs are executed by the electronic device, the electronic device can execute the above-mentioned method.

[0252] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages or combinations thereof. The programming languages include, but are not limited to, object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may execute entirely on the user's computer, partially on the user's computer, execute as a stand-alone software package, execute partially on the user's computer and partially on a remote computer, or execute entirely on the remote computer or server. In the case of 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).

[0253] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions noted in the blocks may occur in a different order than noted in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system for performing the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0254] The units involved in the embodiments described in the present disclosure may be implemented in software or in hardware. Among them, the name of the unit / module does not constitute a limitation to the unit itself in some cases.

[0255] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, by way of non-limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGA), application specific integrated circuits (ASIC), application specific standard products (ASSP), system on a chip (SOC), complex programmable logic devices (CPLD), and so on.

[0256] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0257] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. For the same or similar parts among the various embodiments, reference can be made to each other. For the systems or devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and reference can be made to the description in the method part for the relevant parts.

[0258] It should be understood that in this application, "at least one (item)" means one or more, and "a plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships can exist. For example, "A and / or B" can mean: only A exists, only B exists, and both A and B exist simultaneously. Here, A and B can be singular or plural. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. "At least one (one) of the following" or its similar expressions refer to any combination of these items, including any combination of single items (ones) or plural items (ones). For example, at least one (one) of a, b, or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0259] It should also be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising said element.

[0260] The steps of the methods or algorithms described in connection with the embodiments disclosed herein can be implemented directly in hardware, in software modules executed by a processor, or in a combination thereof. The software modules can be placed in a random access memory (RAM), memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium well known in the art.

[0261] The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A data processing method, characterized in that: The method comprises: Obtaining a three-dimensional mesh to be processed and a reference three-dimensional mesh; Draw a first plane representation image of the three-dimensional mesh to be processed and a second plane representation image of the reference three-dimensional mesh in a preset two-dimensional plane space; the first plane representation image is used to represent the state of the vertices in the three-dimensional mesh to be processed in the preset two-dimensional plane space; the second plane representation image is used to represent the state of the vertices in the reference three-dimensional mesh in the preset two-dimensional plane space; the preset two-dimensional plane space includes at least one anchor point set; Determine first position representation data and second position representation data of an anchor point in each of the anchor point sets; the first position representation data is determined based on region description information of a vertex enclosed region corresponding to the anchor point in the first plane representation image; the second position representation data is determined based on region description information of a vertex enclosed region corresponding to the anchor point in the second plane representation image; The grid performance characterization data of the three-dimensional grid to be processed is determined according to the difference characterization data between the first position characterization data and the second position characterization data.

2. The method according to claim 1, characterized in that The process of determining the grid performance characterization data includes: For any anchor point set, a first virtual grid and a second virtual grid are constructed using the anchor point set, and a grid performance evaluation result corresponding to the anchor point set is determined based on the grid difference representation data between the first virtual grid and the second virtual grid; the vertices in the first virtual grid are determined based on the first anchor point in the anchor point set, a vertex enclosing area corresponding to the first anchor point exists in the first plane representation image, and the first description information of the vertices in the first virtual grid is determined based on the first position representation data of the first anchor point; the vertices in the second virtual grid are determined based on the second anchor point in the anchor point set, a vertex enclosing area corresponding to the second anchor point exists in the second plane representation image, and the second description information of the vertices in the second virtual grid is determined based on the second position representation data of the second anchor point; the grid difference representation data is determined based on the difference representation data between the first description information of the vertices in the first virtual grid and the second description information of the vertices in the second virtual grid; Determine mesh performance characterization data of the three-dimensional mesh to be processed according to the mesh performance evaluation result corresponding to the at least one anchor point set.

3. The method according to claim 2, characterized in that The method of constructing the first virtual grid and the second virtual grid by using the anchor point set includes: Determine each anchor point group to be used from the anchor point set; for any anchor point group to be used, a rectangle formed by all anchor points in the anchor point group to be used satisfies a preset rectangle condition; For any anchor point group to be used, if there are vertex enclosing areas corresponding to the anchor points in the anchor point group to be used in the first plane representation image, the first virtual grid is constructed according to all the anchor points in the anchor point group to be used and the first position representation data of all the anchor points; if there are vertex enclosing areas corresponding to some of the anchor points in the anchor point group to be used in the first plane representation image, and the number of the some anchor points is not less than a preset number threshold, the first virtual grid is constructed according to the some anchor points and the first position representation data of the some anchor points; For any anchor point group to be used, if there exists in the second plane representation image a vertex enclosing area corresponding to each anchor point in the anchor point group to be used, the second virtual grid is constructed based on all the anchor points in the anchor point group to be used and the second position representation data of all the anchor points; if there exists in the second plane representation image a vertex enclosing area corresponding to some of the anchor points in the anchor point group to be used, and the number of the some anchor points is not less than a preset number threshold, the second virtual grid is constructed based on the some anchor points and the second position representation data of the some anchor points.

4. The method according to claim 3, characterized in that: The anchor point group to be used includes four anchor points; The step of constructing the first virtual grid according to all anchor points in the anchor point group to be used and the first position representation data of all anchor points includes: Constructing two triangular faces in the first virtual grid according to four anchor points in the anchor point group to be used and first position representation data of the four anchor points; The step of constructing the second virtual grid according to all anchor points in the anchor point group to be used and the second position representation data of all anchor points includes: Two triangular faces in the second virtual mesh are constructed according to the four anchor points in the anchor point group to be used and the second position representation data of the four anchor points.

5. The method according to claim 3, characterized in that: The number of the partial anchor points is three; The constructing the first virtual grid according to the part of anchor points and the first position representation data of the part of anchor points includes: Constructing a triangular face in the first virtual grid according to the partial anchor points and the first position representation data of the partial anchor points; The constructing the second virtual grid according to the part of the anchor points and the second position representation data of the part of the anchor points includes: A triangular face in the second virtual mesh is constructed according to the partial anchor points and the second position representation data of the partial anchor points.

6. The method according to claim 2, characterized in that The mesh difference representation data includes vertex difference representation data of a plurality of vertices; for any vertex, the vertex difference representation data of the vertex is determined based on the difference representation data between the first description information of the vertex and the second description information of the vertex; The mesh performance evaluation result is determined based on the Laplace losses corresponding to the several vertices. For any vertex, the Laplace loss corresponding to the vertex is determined based on the vertex difference characterization data of the vertex, the vertex difference characterization data of the adjacent vertices of the vertex, and the two diagonals corresponding to the edges formed by the vertex and the adjacent vertices of the vertex.

7. The method according to claim 1, characterized in that The at least one anchor point set comprises N anchor point sets arranged in sequence with equal distances between rows and columns, where N is a positive integer; The process of obtaining the nth anchor point set includes: According to preset sampling parameters and the arrangement sequence number corresponding to the nth anchor point set, determine the starting sampling position corresponding to the nth anchor point set in the preset two-dimensional plane space; the preset sampling parameters include row spacing, column spacing and the number of anchor point sets; n is a positive integer, n≤N; Determining at least one non-starting sampling position corresponding to the nth anchor point set according to the starting sampling position and the preset sampling parameters; The anchor points at the starting sampling position and the anchor points at each of the non-starting sampling positions in the preset two-dimensional plane space are grouped together to obtain the nth anchor point set.

8. The method according to claim 1, characterized in that: The vertex enclosed area is a triangular surface; The region description information includes at least one of an identifier of the triangular face and a plane position of each vertex in the triangular face in the preset two-dimensional plane space.

9. The method according to claim 1, characterized in that: The three-dimensional mesh to be processed is constructed using a three-dimensional reconstruction model; After determining the mesh performance characterization data of the three-dimensional mesh to be processed, the method further includes: The three-dimensional reconstruction model is updated according to the grid performance characterization data.

10. A data processing device, characterized in that: include: A grid acquisition unit, used for acquiring a three-dimensional grid to be processed and a reference three-dimensional grid; An image drawing unit, used for drawing a first plane representation image of the three-dimensional grid to be processed and a second plane representation image of the reference three-dimensional grid in a preset two-dimensional plane space; The first plane representation image is used to represent the state of the vertices in the three-dimensional mesh to be processed in the preset two-dimensional plane space; The second plane representation image is used to represent the state of the vertices in the reference three-dimensional mesh in the preset two-dimensional plane space; the preset two-dimensional plane space includes at least one anchor point set; A first determination unit is used to determine first position representation data and second position representation data of an anchor point in each anchor point set; the first position representation data is determined based on region description information of a vertex enclosed region corresponding to the anchor point in the first plane representation image; the second position representation data is determined based on region description information of a vertex enclosed region corresponding to the anchor point in the second plane representation image; The second determining unit is used to determine the grid performance characterization data of the to-be-processed three-dimensional grid according to the difference characterization data between the first position characterization data and the second position characterization data.

11. An electronic device, characterized in that: The device comprises: a processor and a memory; The memory is used to store instructions or computer programs; The processor is used to execute the instructions or computer programs in the memory so that the electronic device executes the method according to any one of claims 1 to 9.

12. A computer-readable medium, characterized in that The computer-readable medium stores instructions or computer programs, and when the instructions or computer programs are executed on a device, the device executes the method according to any one of claims 1 to 9.

Images