Three-dimensional model reconstruction method and device

Abstract

The present invention provides a method and device for reconstructing a three-dimensional model, which belongs to the technical field of three-dimensional model construction, and can solve the problems of complex structure and low modeling efficiency of existing three-dimensional models. The method for reconstructing a three-dimensional model disclosed in the present invention includes: obtaining point cloud data of each initial model according to the data features of a group of initial three-dimensional models; selecting one of the group of initial three-dimensional models as a standard three-dimensional model, and using the difference between the points in the standard three-dimensional model and the points in other initial three-dimensional models to obtain multiple discrete deformation fields; using a multi-dimensional Gaussian process to convert multiple discrete deformation fields into a statistical morphological model; resampling the statistical morphological model to obtain a target three-dimensional model.

Description

Technical Field

[0001] The present invention belongs to the technical field of three-dimensional model construction, and in particular relates to a three-dimensional model reconstruction method and device. Background Art

[0002] With the continuous development of 3D model construction technology, 3D models have been widely used in more and more fields. Among them, polygon optimization and smoothing of 3D models are a very important part of the 3D development process. Most 3D models need to increase or decrease the number of polygons of the model according to the application scenario and usage to achieve the purpose of optimization and smoothing, so that the model can adapt to more scenarios.

[0003] However, currently, the model is mainly edited manually, and the workload required is similar to rebuilding the 3D model, which is a huge workload. At the same time, as a model animation solution that is widely used in the 3D field and has good effects, the deformer lacks relevant automated operations for the deformer in the process of model smoothing and optimization, resulting in a doubling of workload when processing deformer-related model optimization. Therefore, how to use automated processes to process the deformer to reconstruct the 3D model is a problem that the industry urgently needs to solve. Summary of the invention

[0004] The present disclosure aims to solve at least one of the technical problems existing in the prior art, and provides a method and device for reconstructing a three-dimensional model.

[0005] In a first aspect, an embodiment of the present disclosure provides a method for reconstructing a three-dimensional model, wherein the method for reconstructing a three-dimensional model includes:

[0006] According to data features of a group of initial three-dimensional models, obtaining point cloud data of each of the initial models;

[0007] Selecting one of the initial three-dimensional models as a standard three-dimensional model, and obtaining a plurality of discrete deformation fields by using the difference between points in the standard three-dimensional model and points in other initial three-dimensional models;

[0008] Using a multidimensional Gaussian process, a plurality of discrete deformation fields are converted into a statistical morphological model;

[0009] The statistical morphological model is resampled to obtain a target three-dimensional model.

[0010] Optionally, acquiring point cloud data of each of the initial models according to data features of a group of initial three-dimensional models includes:

[0011] placing the deformer of the initial three-dimensional model in an average state and obtaining an average state model;

[0012] According to the average state model, obtaining the limit state model of multiple deformation components of the deformer;

[0013] storing the average state model and the limit state model as readable data;

[0014] The readable data are sorted to obtain point cloud data of the initial model.

[0015] Optionally, the limit state model includes: a positive limit model and a negative limit model.

[0016] Optionally, the readable data includes: polygonal file format data.

[0017] Optionally, selecting one of the initial three-dimensional models as a standard three-dimensional model and obtaining a plurality of discrete deformation fields by using differences between points in the standard three-dimensional model and points in other initial three-dimensional models includes:

[0018] According to the point cloud data, obtaining a grid corresponding to the point cloud data;

[0019] Calculating the difference between the point corresponding to the point cloud data and the reference point according to the grid;

[0020] A plurality of discrete deformation fields are obtained according to the difference between the point corresponding to the point cloud data and the reference point.

[0021] Optionally, the method of converting the plurality of discrete deformation fields into a statistical morphological model by using a multidimensional Gaussian process comprises:

[0022] According to the points corresponding to the point cloud data, obtain the mean of each point and the covariance of each point;

[0023] Obtain a multidimensional Gaussian process according to the mean and the covariance;

[0024] According to the multidimensional Gaussian process, the statistical morphology model is obtained.

[0025] Optionally, resampling the statistical morphological model to obtain a target three-dimensional model includes:

[0026] According to the points in the statistical morphological model, select some of the points;

[0027] The points of the parts are integrated to obtain the target three-dimensional model.

[0028] In a second aspect, an embodiment of the present disclosure provides a three-dimensional model reconstruction device, wherein the three-dimensional model reconstruction device includes:

[0029] A point cloud data acquisition module is configured to acquire point cloud data of each of the initial models according to data features of a group of initial three-dimensional models;

[0030] A deformation field conversion module is configured to select one of the initial three-dimensional models as a standard three-dimensional model, and obtain a plurality of discrete deformation fields by using the difference between points in the standard three-dimensional model and points in other initial three-dimensional models;

[0031] A statistical morphological model conversion module is configured to convert a plurality of discrete deformation fields into a statistical morphological model using a multi-dimensional Gaussian process;

[0032] The target three-dimensional model acquisition module is configured to resample the statistical morphological model to acquire the target three-dimensional model.

[0033] Optionally, the point cloud data acquisition module includes:

[0034] an average state model acquisition submodule, configured to place the deformer of the initial three-dimensional model in an average state and acquire an average state model;

[0035] A limit state model acquisition submodule is configured to acquire a limit state model of a plurality of deformation components of the deformer according to the average state model;

[0036] A readable data storage submodule is configured to store the average state model and the limit state model as readable data;

[0037] The sorting submodule is configured to sort the readable data to obtain the point cloud data of the initial model.

[0038] Optionally, the deformation field conversion module includes:

[0039] A grid acquisition submodule is configured to acquire a grid corresponding to the point cloud data according to the point cloud data;

[0040] a difference calculation submodule, configured to calculate the difference between the point corresponding to the point cloud data and the reference point according to the grid;

[0041] The interpolation submodule is configured to obtain a plurality of discrete deformation fields according to the difference between the point corresponding to the point cloud data and the reference point.

[0042] Optionally, the statistical morphology model conversion module includes:

[0043] The mean and covariance acquisition submodule is configured to acquire the mean of each point and the covariance of each point according to the point corresponding to the point cloud data;

[0044] A multidimensional Gaussian process acquisition module is configured to acquire a multidimensional Gaussian process according to the mean and the covariance;

[0045] The statistical morphological model acquisition submodule is configured to acquire the statistical morphological model according to the multidimensional Gaussian process.

[0046] Optionally, the target three-dimensional model acquisition module includes:

[0047] A selection submodule is configured to select some of the points in the statistical morphological model according to the points in the statistical morphological model;

[0048] The integration submodule is configured to integrate the points of the portion to obtain the target three-dimensional model.

[0049] In a third aspect, an embodiment of the present disclosure provides an electronic device, including:

[0050] at least one processor; and

[0051] a memory communicatively connected to the at least one processor; wherein,

[0052] The memory stores one or more computer programs that can be executed by the at least one processor, and the one or more computer programs are executed by the at least one processor so that the at least one processor can perform the three-dimensional model reconstruction method provided above.

[0053] In a fourth aspect, an embodiment of the present disclosure provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the three-dimensional model reconstruction method provided above. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 A schematic diagram of a process for constructing a three-dimensional model provided in an embodiment of the present disclosure.

[0055] Figure 2 The figure is a flowchart of a method for obtaining point cloud data of an initial model.

[0056] Figure 3 A flowchart of a deformation field conversion method is shown in FIG.

[0057] Figure 4 A schematic diagram of the structure of an exemplary three-dimensional model.

[0058] Figure 5 A flowchart of a transformation method for a statistical morphological model is shown.

[0059] Figure 6 A schematic diagram of the structure of another exemplary three-dimensional model.

[0060] Figure 7 The present invention is a flowchart of a method for acquiring a target three-dimensional model.

[0061] Figure 8 A schematic diagram of the structure of a three-dimensional model reconstruction device provided in an embodiment of the present disclosure.

[0062] Fig. 9 It is a schematic diagram of the structure of an electronic device provided in some embodiments of the present disclosure. DETAILED DESCRIPTION

[0063] In order to enable those skilled in the art to better understand the technical solution of the present disclosure, the present disclosure is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0064] Unless otherwise defined, the technical terms or scientific terms used in the present disclosure should be understood by people with ordinary skills in the field to which the present disclosure belongs. The "first", "second" and similar words used in the present disclosure do not indicate any order, quantity or importance, but are only used to distinguish different components. Similarly, similar words such as "one", "one" or "the" do not indicate quantity restrictions, but indicate that there is at least one. Similar words such as "include" or "comprise" mean that the elements or objects appearing before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Similar words such as "connect" or "connected" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0065] In 3D model building technology, the number of polygons of the model needs to be increased or decreased according to the application scenario and usage to achieve the purpose of optimization and smoothing, so that the model can adapt to more scenarios. However, the model is currently mainly edited manually, and the workload required is similar to rebuilding the 3D model, which is a huge workload. At the same time, as a model animation solution that is widely used in the 3D field and has good effects, the deformer lacks relevant automated operations for the deformer in the process of model smoothing and optimization, resulting in a doubling of the workload when processing deformer-related model optimization.

[0066] In order to solve at least one of the above-mentioned technical problems, the embodiment of the present disclosure provides a method and device for reconstructing a three-dimensional model. The method and device for reconstructing the three-dimensional model provided by the embodiment of the present disclosure will be further described in detail below in combination with the accompanying drawings and specific implementation methods.

[0067] It should be noted that in order to better describe the method and device for constructing a three-dimensional model provided in the embodiment of the present disclosure, the terms involved therein are explained here.

[0068] Statistical Shape Models (SSM) are geometric models that describe a set of semantically similar objects in a very compact way. SSM represents the average shape of a family of three-dimensional objects and their variations in shape. The creation of SSM requires a correspondence mapping, which can be achieved by using the respective sampling parameterization. If the corresponding parameterization of all shapes can be established, the variations between individual shape features can be studied mathematically.

[0069] Deformer (Blend shape) is a technology that deforms a single mesh to achieve a combination of many predefined shapes and any number of them. In Maya / 3ds Max, we call it a deformation target. For example, a single mesh is the basic shape of the default shape (such as an expressionless face), and other shapes of the basic shape are used for blending / deformation, which are different expressions (smile, frown, closed eyelids). These are collectively called blend shapes or deformation targets. In actual performance, it is manifested by transforming a group of models with different shapes but the same topological information such as model points and wiring, and using a series of parameters to manipulate the model to actually deform into a certain shape of this group of models.

[0070] Polygon smoothing optimization is to optimize the number of faces and face structure of the model by reorganizing the polygons of the model. If the faces of the model need to be changed by increasing the number of model faces, it is polygon smoothing of the model. If the faces of the model need to be changed by reducing the number of model faces, it is polygon optimization of the model.

[0071] In a first aspect, the present disclosure provides a method for constructing a three-dimensional model. Figure 1 A schematic diagram of a process for constructing a three-dimensional model provided in an embodiment of the present disclosure is shown in FIG. Figure 1 As shown, the method for constructing the three-dimensional model includes the following steps S101 to S104.

[0072] S101, acquiring point cloud data of each initial model according to data features of a group of initial three-dimensional models.

[0073] In the above step S101, the initial three-dimensional model is specifically a three-dimensional model of the human body, such as the whole human body or a certain part of the human body, which can be a hand, foot, head or internal organs. Taking the initial three-dimensional model as a three-dimensional model of the hand as an example, its data features may include: the length and width of each finger, the range of movement of each finger in the three-dimensional space, etc. The initial three-dimensional model can be stored in RVT, 3DS, DWG, FBX, IFC, OSGB, OBJ and other formats, which can be read and processed by 3DMAX, SoftImage, Maya, UG and AutoCAD and other software. Multiple point cloud data can form a grid, which is often composed of triangles, quadrilaterals or other simple convex polygons, and the final grid can form a three-dimensional model. Power supply data can be stored in binary file formats such as las, laz, pcd, pcap, ply, pts, etc.

[0074] S102, selecting one of a group of initial three-dimensional models as a standard three-dimensional model, and obtaining a plurality of discrete deformation fields by using the difference between points in the standard three-dimensional model and points in other initial three-dimensional models.

[0075] In the above step S102, the converted point cloud data has the feature that the grids are one-to-one corresponding. For example, the tenth point cloud data in each initial three-dimensional model represents the middle finger of the finger. One of the initial three-dimensional models is selected as the standard three-dimensional model. The standard three-dimensional model has a moderate shape, for example, a three-dimensional model of a finger in a normal stretched state. Each point cloud data can only represent a certain point in the hand, and each point is discontinuous. The difference between the point in the standard three-dimensional model and the point in other initial three-dimensional models can be calculated to form multiple discontinuous deformation fields, that is, discrete deformation fields.

[0076] S103, using a multi-dimensional Gaussian process, converting multiple discrete deformation fields into a statistical morphological model.

[0077] In the above step S103, the data of multiple discrete deformation fields are introduced into the Gaussian process formula, and the multiple discrete deformation fields can be interpolated to form a deformation field of a continuous domain, and the deformation fields of multiple continuous domains can constitute a statistical morphological model.

[0078] S104, resampling the statistical morphological model to obtain a target three-dimensional model.

[0079] In the above step S104, for the statistical morphological model with a continuous domain, the nearest neighbor interpolation method, bilinear interpolation method, cubic convolution interpolation method, etc. can be used to select some points therein to form a new three-dimensional model, namely, the target three-dimensional model.

[0080] In the reconstruction method of the three-dimensional model provided by the embodiment of the present disclosure, the point cloud data of the initial three-dimensional model can be firstly obtained, wherein each point cloud data corresponds to a point in the grid, the point cloud data can be converted into a deformation field in the grid, and the space between the grid points can be processed by interpolation calculation to form a plurality of discrete deformation fields, and then the plurality of discrete deformation fields can be converted into a statistical morphological model of a deformation field with a continuous domain by using a multidimensional Gaussian process, and the statistical morphological model is resampled according to the application scenario to obtain a deformer with a specific number of grid points to achieve smooth optimization of the deformer model and form a target three-dimensional model. In this way, the non-functional characteristics of a certain aspect of the three-dimensional model can be improved without changing the functional characteristics of the original model, such as improving the readability of the three-dimensional model, reducing the complexity of the original model, etc. The three-dimensional model can be reconstructed by automated means, so that the workload can be greatly reduced, thereby effectively improving the efficiency of the reconstruction of the three-dimensional model.

[0081] In some embodiments, Figure 2 A flowchart of a method for obtaining point cloud data of an initial model is shown in FIG. Figure 2 As shown, the above step S101, based on the data features of a group of initial three-dimensional models, obtains the point cloud data of each initial model, including the following steps S1011 to S1014.

[0082] S1011, placing the deformer of the initial three-dimensional model in an average state, and obtaining an average state model.

[0083] S1012: Obtain limit state models of multiple deformation components of the deformer according to the average state model.

[0084] S1013, storing the average state model and the limit state model as readable data.

[0085] S1014, sorting the readable data to obtain point cloud data of the initial model.

[0086] Specifically, in this step, it is mainly necessary to convert a three-dimensional model containing a deformer into separate models for the next software processing. The deformer can be placed in an average state first, and then the maximum value of each deformation component of the deformer can be selected to export this model. In a specific example, the deformer has 5 deformation components, and 10 separate models need to be exported, that is, the limit state model of the positive and negative parts of each deformation classification in the average state. At the same time, the initial average state model needs to be exported as a reference. It should be noted here that, taking the horizontal direction as a deformation component, the limit position to which the grid point in the three-dimensional model moves to the left in the horizontal direction can be defined as its negative limit state, and the limit position to which it moves to the right in the horizontal direction can be defined as its positive polarity state. The deformation components in other directions can also refer to the above description, and will not be listed one by one here.

[0087] In order to facilitate the reading of the 3D model, the model in polygonal file format (ply) will be used to mainly export the mesh information of the 3D model. After exporting the model, the model data needs to be processed. The main purpose is to convert the complete model information into a point cloud state, that is, only save the point coordinate data in the model file in sequence to obtain the point cloud data of the initial model.

[0088] In some embodiments, Figure 3 is a flow chart of a method for transforming a deformation field, such as Figure 3 As shown, the above step S102 selects one of a group of initial three-dimensional models as a standard three-dimensional model, and uses the difference between the points in the standard three-dimensional model and the points in other initial three-dimensional models to obtain multiple discrete deformation fields, including the following steps S1021 to S1023.

[0089] S1021, based on the point cloud data, obtaining a grid corresponding to the point cloud data.

[0090] S1022, calculating the difference between the point corresponding to the point cloud data and the reference point according to the grid.

[0091] S1023, obtaining a plurality of discrete deformation fields according to the difference between the point corresponding to the point cloud data and the reference point.

[0092] Specifically, the point cloud data converted in the previous stage has a feature that the grids are all corresponding. That is, they all have the same number of points, and points with the same address in the grid represent the same point / area in the grid.

[0093] Any mesh corresponding to this reference can be represented as a deformation field, which is defined on this reference mesh; that is, the points of the reference mesh are the domain that defines the deformation field. The deformation can be calculated by taking the difference between the corresponding points of the mesh and the reference points.

[0094] The deformation field obtained in the above steps is discrete because it is only defined on the grid points. This is not ideal because the real-world objects being modeled are continuous and the discretization of the grid is quite arbitrary. In the scheme of the disclosed embodiment, it is necessary to obtain a continuous representation of the deformation field by interpolation. The interpolation can be found by finding the nearest point on the surface for each point in the three-dimensional space, and using the corresponding deformation as the deformation of the given point. The points on the surface are then obtained by interpolating the centroids of the corresponding vertices. As a result of the interpolation, the deformation field of the entire real space is obtained, that is, the deformation field corresponding to any point can be obtained.

[0095] Figure 4 is a schematic diagram of an exemplary three-dimensional model structure, such as Figure 4 As shown in , a figure is transformed into an interpolation of the corresponding point position of a reference model to the figure, that is, the deformation field. Figure 4 The shape of the hand model is composed of contour points. The black dots are in an averaged state. The black dot contour can be used as a basis. The other hand contour is the contour pointed by the arrow in the figure. The direction indicated by the arrow is expressed as a vector from the black dot, which is the reference point of the point, to this point to the actual position of the other hand contour point. This operation can be used for every point of each model. This is a deformation field.

[0096] Continue to see above Figure 4 In this hand shape 3D model, the existing contour is composed of a set of points. So the model actually expressed is a discrete contour. When we connect these points into a line, we form a continuous contour instead of a series of points with distances. In this way, the contour continuity process is realized, that is, it can be represented by a set of y(x) functions. Similarly, the two continuous hand contours are subjected to the above deformation field extraction operation. Figure 4 The subtraction of the corresponding coordinates of the two hand contours in can generate the deformation field of the continuous domain.

[0097] In some embodiments, Figure 5 A schematic diagram of a transformation method of a statistical morphological model is shown in FIG. Figure 5 As shown, the above step S103, using a multi-dimensional Gaussian process, converts multiple discrete deformation fields into a statistical morphological model, including the following steps S1031 to S1033.

[0098] S1031, according to the points corresponding to the point cloud data, obtain the mean of each point and the covariance of each point.

[0099] S1032, obtaining a multidimensional Gaussian process according to the mean and covariance.

[0100] S1033, obtaining a statistical morphological model according to a multidimensional Gaussian process.

[0101] Specifically, taking the deformer with 5 deformation components as an example, a total of 11 models were obtained. The positive maximum model and the negative maximum model corresponding to each deformation component were taken as a group to calculate the statistical morphological model of the continuous domain. In this step, the following logic will be used. First, the mean μ of each point in the model is calculated for each group (Formula 1), and then the covariance of any corresponding point is calculated (Formula 2).

[0102]

[0103]

[0104] Finally, μ and ∑ in the above are brought into a multi-dimensional Gaussian process (Formula 3).

[0105]

[0106] In this way, a multi-dimensional Gaussian process is obtained. This process has a lot of information and properties that can be extracted. However, in the embodiment of the present disclosure, this Gaussian process is mainly used as a sum of the above-mentioned model deformation field. In summary, in the above-mentioned mathematical calculation, multiple models are serialized and then reintegrated together. For example, the hand shape model is used as an example. Figure 6 As shown in the figure, the black outline is the hand shape that we set as the average model, and the black shadows around the hand shape are the possible positions of the hand outline in different models under different circumstances. It can be understood as a series of shadows superimposed by overlapping hands in different shapes. In this process, the Gaussian process learns a kind of information, that is, when some points of the hand outline appear at a certain position in the shadow, the position of each point of the entire outline can be obtained.

[0107] After the above explanation, by inputting the positions of a finite number of points in the positive maximum value model corresponding to a certain deformation component in the above Gaussian process, the expression of the entire contour is obtained, and the continuous expression of the entire contour is obtained.

[0108] In some embodiments, Figure 7 A flowchart of a method for obtaining a target three-dimensional model is shown in FIG. Figure 7 As shown, the above step S104, resampling the statistical morphological model to obtain the target three-dimensional model, includes the following steps S1041 to S1042.

[0109] S1041, selecting some of the points in the statistical morphological model.

[0110] S1042, integrating some points to obtain a target three-dimensional model.

[0111] Specifically, after completing the above steps, we can get the expression of the positive maximum value model corresponding to a certain deformation component in the continuous space. After implementing this step, we only need to resample the model according to actual needs to obtain the new point position of the model. Taking the hand shape model as an example, after obtaining the contour line of a certain shape of the hand, when we need a hand contour point map composed of 100 points, we only need to select the required 100 points in the entire contour line as needed to realize the smoothing or optimization process of the entire three-dimensional model.

[0112] The operation for the new deformer generated at the end, that is, the combination of a group of models with different shapes, is the same as the above operation. It only needs to be resampled in the standard model of the entire Gaussian process. According to the characteristics that the positions of each point in the entire model are corresponding, a new model with different shapes of the points in the same selected area can be obtained to form a new deformer. The original deformer has dense points and many model points. After the corresponding operation, the resampling smoothing optimization is performed to generate a deformer model with fewer points.

[0113] In a second aspect, the embodiments of the present disclosure provide a three-dimensional model reconstruction device. Figure 8 A schematic diagram of a structure of a three-dimensional model reconstruction device provided by an embodiment of the present disclosure, such as Figure 8 As shown, the three-dimensional model reconstruction device includes: a point cloud data acquisition module 801, a deformation field conversion module 802, a statistical morphological model conversion module 803 and a target three-dimensional model acquisition module 804.

[0114] The point cloud data acquisition module 801 is configured to acquire point cloud data of each initial model according to data features of a group of initial three-dimensional models; the deformation field conversion module 802 is configured to select one of a group of initial three-dimensional models as a standard three-dimensional model, and use the difference between the points in the standard three-dimensional model and the points in other initial three-dimensional models to acquire multiple discrete deformation fields; the statistical morphological model conversion module 803 is configured to use a multi-dimensional Gaussian process to convert multiple discrete deformation fields into a statistical morphological model; the target three-dimensional model acquisition module 804 is configured to resample the statistical morphological model to acquire the target three-dimensional model.

[0115] The three-dimensional model reconstruction device provided in the embodiments of the present disclosure is used to implement the three-dimensional model reconstruction method provided in any of the above embodiments. For specific related descriptions, please refer to the description of the three-dimensional model reconstruction method in any of the above embodiments, which will not be repeated here.

[0116] Specifically, the point cloud data acquisition module 801 includes: an average state model acquisition submodule 8011, which is configured to place the deformer of the initial three-dimensional model in an average state and obtain the average state model; a limit state model acquisition submodule 8012, which is configured to obtain the limit state model of multiple deformation components of the deformer based on the average state model; a readable data storage submodule 8013, which is configured to store the average state model and the limit state model as readable data; and a sorting submodule 8014, which is configured to sort the readable data to obtain the point cloud data of the initial model.

[0117] The deformation field conversion module 802 includes: a grid acquisition submodule 8021, which is configured to acquire a grid corresponding to the point cloud data based on the point cloud data; a difference calculation submodule 8022, which is configured to calculate the difference between the point corresponding to the point cloud data and the reference point based on the grid; and an interpolation submodule 8023, which is configured to acquire the deformation field of the continuous domain based on the difference between the point corresponding to the point cloud data and the reference point.

[0118] The statistical morphological model conversion module 803 includes: a mean and covariance acquisition submodule 8031, which is configured to acquire the mean of each point and the covariance of each point according to the points corresponding to the point cloud data; a multidimensional Gaussian process acquisition module 8032, which is configured to acquire a multidimensional Gaussian process according to the mean and covariance; and a statistical morphological model acquisition submodule 8033, which is configured to acquire a statistical morphological model according to the multidimensional Gaussian process.

[0119] The target three-dimensional model acquisition module 804 includes: a selection submodule 8041, which is configured to select some points in the statistical morphological model according to the points; and an integration submodule 8042, which is configured to integrate some points to obtain the target three-dimensional model.

[0120] In a third aspect, an embodiment of the present disclosure provides an electronic device, Fig. 9 It is a schematic diagram of the structure of an electronic device provided in some embodiments of the present disclosure, such as Fig. 9 As shown, the electronic device includes: one or more processors 901; a memory 902, on which one or more programs are stored, and when the one or more programs are executed by one or more processors, the one or more processors implement the three-dimensional model reconstruction method provided in any of the above embodiments; one or more I / O interfaces 903, connected between the processor and the memory, and configured to implement information interaction between the processor and the memory.

[0121] Among them, the processor 901 is a device with data processing capabilities, including but not limited to a central processing unit (CPU); the memory 902 is a device with data storage capabilities, including but not limited to random access memory (RAM, more specifically SDRAM, DDR, etc.), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory (FLASH); the I / O interface (read-write interface) 903 is connected between the processor 901 and the memory 902, and can realize information interaction between the processor 901 and the memory 902, including but not limited to a data bus (Bus), etc.

[0122] In some embodiments, the processor 901 , the memory 902 , and the I / O interface 903 are connected to each other through a bus, and further connected to other components of the computing device.

[0123] In a fourth aspect, this embodiment provides a computer-readable medium having a computer program stored thereon, and when the program is executed by a processor, the method for reconstructing a three-dimensional model provided in any of the above embodiments is implemented.

[0124] It will be appreciated by those skilled in the art that all or some of the steps, systems, and functional modules / units in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In hardware implementations, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or temporary medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, it is well known to those skilled in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0125] It is to be understood that the above embodiments are merely exemplary embodiments used to illustrate the principles of the present disclosure, but the present disclosure is not limited thereto. For those of ordinary skill in the art, various modifications and improvements can be made without departing from the spirit and substance of the present disclosure, and these modifications and improvements are also considered to be within the scope of protection of the present disclosure.

Claims

1. A method for reconstructing a three-dimensional model, wherein: The three-dimensional model reconstruction method comprises: According to data features of a group of initial three-dimensional models, obtaining point cloud data of each of the initial models; Selecting one of the initial three-dimensional models as a standard three-dimensional model, and obtaining a plurality of discrete deformation fields by using the difference between points in the standard three-dimensional model and points in other initial three-dimensional models; Using a multidimensional Gaussian process, a plurality of discrete deformation fields are converted into a statistical morphological model; Resampling the statistical morphological model to obtain a target three-dimensional model; The step of obtaining point cloud data of each of the initial three-dimensional models according to data features of the initial three-dimensional models includes: placing the deformer of the initial three-dimensional model in an average state and obtaining an average state model; According to the average state model, obtaining the limit state model of multiple deformation components of the deformer; storing the average state model and the limit state model as readable data; sorting the readable data to obtain point cloud data of the initial model; The step of selecting one of the initial three-dimensional models as a standard three-dimensional model and obtaining a plurality of discrete deformation fields by using the difference between points in the standard three-dimensional model and points in other initial three-dimensional models includes: According to the point cloud data, obtaining a grid corresponding to the point cloud data; Calculating the difference between the point corresponding to the point cloud data and the reference point according to the grid; A plurality of discrete deformation fields are obtained according to the difference between the point corresponding to the point cloud data and the reference point.

2. The three-dimensional model reconstruction method according to claim 1, wherein: The limit state model includes: a positive limit model and a negative limit model.

3. The three-dimensional model reconstruction method according to claim 1, wherein: The readable data includes: polygon file format data.

4. The method for reconstructing a three-dimensional model according to claim 1, wherein: The method of converting the plurality of discrete deformation fields into a statistical morphological model by using a multidimensional Gaussian process includes: According to the points corresponding to the point cloud data, obtain the mean of each point and the covariance of each point; Obtain a multidimensional Gaussian process according to the mean and the covariance; According to the multidimensional Gaussian process, the statistical morphology model is obtained.

5. The method for reconstructing a three-dimensional model according to claim 4, wherein: Resampling the statistical morphological model to obtain a target three-dimensional model includes: According to the points in the statistical morphological model, select some of the points; The points of the parts are integrated to obtain the target three-dimensional model.

6. A three-dimensional model reconstruction device, wherein: The three-dimensional model reconstruction device comprises: A point cloud data acquisition module is configured to acquire point cloud data of each of the initial models according to data features of a group of initial three-dimensional models; A deformation field conversion module is configured to select one of the initial three-dimensional models as a standard three-dimensional model, and obtain a plurality of discrete deformation fields by using the difference between points in the standard three-dimensional model and points in other initial three-dimensional models; A statistical morphological model conversion module is configured to convert a plurality of discrete deformation fields into a statistical morphological model using a multi-dimensional Gaussian process; a target three-dimensional model acquisition module, configured to resample the statistical morphological model to acquire a target three-dimensional model; The point cloud data acquisition module includes: an average state model acquisition submodule, configured to place the deformer of the initial three-dimensional model in an average state and acquire an average state model; A limit state model acquisition submodule is configured to acquire a limit state model of a plurality of deformation components of the deformer according to the average state model; A readable data storage submodule is configured to store the average state model and the limit state model as readable data; A sorting submodule, configured to sort the readable data to obtain point cloud data of the initial model; The deformation field conversion module comprises: A grid acquisition submodule is configured to acquire a grid corresponding to the point cloud data according to the point cloud data; a difference calculation submodule, configured to calculate the difference between the point corresponding to the point cloud data and the reference point according to the grid; The interpolation submodule is configured to obtain a plurality of discrete deformation fields according to the difference between the point corresponding to the point cloud data and the reference point.

7. The three-dimensional model reconstruction device according to claim 6, wherein: The statistical morphology model conversion module comprises: The mean and covariance acquisition submodule is configured to acquire the mean of each point and the covariance of each point according to the point corresponding to the point cloud data; A multidimensional Gaussian process acquisition module is configured to acquire a multidimensional Gaussian process according to the mean and the covariance; The statistical morphological model acquisition submodule is configured to acquire the statistical morphological model according to the multidimensional Gaussian process.

8. The three-dimensional model reconstruction device according to claim 7, wherein: The target three-dimensional model acquisition module includes: A selection submodule is configured to select some of the points in the statistical morphological model according to the points in the statistical morphological model; The integration submodule is configured to integrate the points of the portion to obtain the target three-dimensional model.

9. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores one or more computer programs that can be executed by the at least one processor, and the one or more computer programs are executed by the at least one processor to enable the at least one processor to perform the three-dimensional model reconstruction method according to any one of claims 1 to 5.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the computer program implements the three-dimensional model reconstruction method according to any one of claims 1 to 5.

Images