CN112700533A - Three-dimensional reconstruction method and device, electronic equipment and storage medium - Google Patents
Three-dimensional reconstruction method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN112700533A CN112700533A CN202011609669.2A CN202011609669A CN112700533A CN 112700533 A CN112700533 A CN 112700533A CN 202011609669 A CN202011609669 A CN 202011609669A CN 112700533 A CN112700533 A CN 112700533A
- Authority
- CN
- China
- Prior art keywords
- model
- vertex
- preset
- target
- converted
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Abstract
The present disclosure relates to a three-dimensional reconstruction method, an apparatus, an electronic device, and a storage medium, the method including: the method comprises the following steps of obtaining a target face model, a preset head skeleton model and a preset dental gum model matched with the preset head skeleton model, wherein the preset head skeleton model at least comprises: presetting a jaw bone model and a skull bone model; fitting the preset head skeleton model based on the target face model to obtain a fitting position of the preset head skeleton model; determining the fitting position of the preset dental gum model according to the fitting position of the preset head skeleton model and the position corresponding relation between the preset head skeleton model and the preset dental gum model; and performing position conversion on the vertex of the preset tooth gum model based on the fitting position of the preset tooth gum model to obtain the target tooth gum model. The present disclosure at least solves the problem of difficulty in accurately constructing the oral cavity structure of a three-dimensional model of a human face in the related art.
Description
Technical Field
The present disclosure relates to the field of skeleton model construction technologies, and in particular, to a three-dimensional reconstruction method and apparatus, an electronic device, and a storage medium.
Background
With the wide application of virtual reality technology in various industries, the technology for reconstructing three-dimensional human body models is developed rapidly, and the reconstruction of three-dimensional human face models as important components of three-dimensional human body models also becomes a mature technology.
However, due to the limitations of the three-dimensional reconstruction algorithms, the reconstructed face model usually has no corresponding internal structure of the mouth. Therefore, when the three-dimensional face model corresponding to the virtual character is driven to perform actions such as opening the mouth, laughing and the like, if the internal structures of the oral cavity such as the teeth, the gum and the like of the virtual character are not rendered, the performance quality of the virtual character is greatly influenced.
In order to solve the problem, in the related art, a pixel corresponding relation between pictures is obtained according to a multi-view visual picture, and a relative pose of a camera and a sparse three-dimensional point cloud are calculated, so that an internal structure of an oral cavity is reconstructed in a mode of obtaining a three-dimensional model of an object in a mode of converting the point cloud into a triangular mesh.
Aiming at the problem that the oral cavity structure of a human face three-dimensional model is difficult to accurately construct in the related technology, an effective solution is not provided at present.
Disclosure of Invention
The present disclosure provides a three-dimensional reconstruction method, apparatus, electronic device, and storage medium, to at least solve the problem in the related art that it is difficult to accurately construct an oral cavity structure of a three-dimensional model of a human face. The technical scheme of the disclosure is as follows:
according to a first aspect of the embodiments of the present disclosure, there is provided a three-dimensional reconstruction method, including: the method comprises the following steps of obtaining a target face model, a preset head skeleton model and a preset dental gum model matched with the preset head skeleton model, wherein the preset head skeleton model at least comprises: presetting a jaw bone model and a skull bone model; fitting the preset head skeleton model based on the target face model to obtain a fitting position of the preset head skeleton model; determining the fitting position of the preset dental gum model according to the fitting position of the preset head skeleton model and the position corresponding relation between the preset head skeleton model and the preset dental gum model; and performing position conversion on the vertex of the preset tooth gum model based on the fitting position of the preset tooth gum model to obtain the target tooth gum model.
Optionally, fitting the preset head skeleton model based on the target face model, and obtaining a fitting position of the preset head skeleton model includes: converting the position of each vertex of the preset head skeleton model through a target conversion relation to obtain each converted vertex of the preset head skeleton model and the position of each converted vertex, wherein the target conversion relation is used for representing the position conversion relation between the preset head skeleton model and a target head skeleton model corresponding to the target face model; carrying out iterative deformation on each converted vertex of the preset head skeleton model to obtain deformation displacement of each converted vertex; and moving the position of the converted vertex by a distance corresponding to the deformation displacement in the normal direction that each converted vertex corresponds to the surface of the preset head skeleton model to obtain the target position of the converted vertex, and forming the fitting position of the preset head skeleton model by the target position of each converted vertex.
Optionally, iteratively deforming each converted vertex of the preset head bone model, and obtaining a deformation displacement of each converted vertex includes: and performing iterative deformation on each converted vertex by taking the minimum shell deformation energy of each converted vertex and the minimum sum of the difference values of the deformation displacement of each converted vertex and the skin thickness adjustment value corresponding to the vertex as a target to obtain the deformation displacement of each converted vertex, wherein the skin thickness adjustment value corresponding to each converted vertex is determined by the distance from the converted vertex to the skin surface layer vertex of the target face model and the skin thickness range interval corresponding to the target face model.
Optionally, under the condition that the distance from the converted vertex to the vertex of the skin surface layer is smaller than the minimum value of the skin thickness range interval, calculating a difference value between the distance and the minimum value, and determining a calculation result as a skin thickness adjustment value corresponding to the converted vertex; under the condition that the distance from the converted vertex to the skin surface layer vertex is larger than the maximum value of the skin thickness range interval, calculating the difference value between the distance and the maximum value, and determining the calculation result as a skin thickness adjustment value corresponding to the converted vertex; and under the condition that the distance from the converted vertex to the skin surface layer vertex is larger than or equal to the minimum value of the skin thickness range, and the distance from the converted vertex to the surface of the target face model is smaller than or equal to the maximum value of the skin thickness range, determining that the skin thickness adjustment value corresponding to the converted vertex is zero.
Optionally, in the process of iteratively deforming each transformed vertex of the preset head bone model, the deformation displacement of the target vertex satisfies the following constraint condition: and the deformation displacement of the target vertex is equal to the distance between the target vertex and the preset skin surface layer vertex corresponding to the target vertex, wherein the target vertex is a vertex with determined skin thickness corresponding to each converted vertex, and the distance between the target vertex and the preset skin surface layer vertex corresponding to the target vertex is the skin thickness corresponding to the target vertex.
Optionally, converting the position of each vertex of the preset head bone model through the target conversion relationship, and obtaining each converted vertex of the preset head bone model and the position of each converted vertex include: acquiring the vertex of a convex region of a preset head skeleton model; converting the position of the vertex of the protruding region of the preset head skeleton model through a first conversion relation to obtain the converted vertex of the protruding region and the converted position of the vertex of the protruding region, wherein the first conversion relation represents the conversion relation between a plurality of first mark points of the preset head skeleton model and a plurality of preset head skeleton points corresponding to the target face model; combining the vertexes of the converted convex regions with vertexes of the preset head skeleton model except the convex regions to obtain each converted vertex of the preset head skeleton model; and combining the positions of the vertexes of the converted protruding regions and the positions of the vertexes outside the protruding regions of the preset head bone model to obtain the positions of the converted vertexes of the preset head bone model.
Optionally, before transforming the positions of the vertices of the preset head bone model through the first transformation relationship to obtain the preliminary fitting positions of the vertices of the preset head bone model, the method further includes: determining a plurality of second mark vertexes of the target face model, and respectively determining skin thicknesses corresponding to the second mark vertexes; moving the position of the second mark vertex by a distance corresponding to the skin thickness of the second mark vertex in the normal direction of the second mark vertex corresponding to the surface of the target face model to obtain the position of a preset head skeleton point corresponding to the second mark vertex; determining the positions of a plurality of first mark vertexes of a preset head model, wherein the position corresponding relation exists between the first mark vertexes and the second mark vertexes; and acquiring a conversion relation between the position of the preset head skeleton point and the positions of the multiple first mark vertexes to obtain a first conversion relation.
Optionally, the preset dental gum model includes a preset upper dental gum model and a preset lower dental gum model, and determining the fitting position of the preset dental gum model according to the fitting position of the preset head skeleton model and the position corresponding relationship between the preset head skeleton model and the preset dental gum model includes: determining a plurality of first mark positions in fitting positions of vertexes of a preset skull model, and determining a plurality of second mark positions on a preset upper dental gum model, wherein the plurality of first mark positions and the plurality of second mark positions have corresponding relations; converting the position of the vertex of the preset upper dental gum model based on the corresponding relation between the plurality of first mark positions and the plurality of second mark positions to obtain the fitting position of the vertex of the preset upper dental gum model; determining a plurality of third mark positions in fitting positions of vertexes of a preset jaw bone model, and determining a plurality of fourth mark positions on a preset lower dental gum model, wherein the plurality of third mark positions and the plurality of fourth mark positions have corresponding relations; and converting the position of the vertex of the preset lower dental gum model based on the corresponding relation between the plurality of third mark positions and the plurality of fourth mark positions to obtain the fitting position of the vertex of the preset lower dental gum model.
According to a second aspect of the embodiments of the present disclosure, there is provided a three-dimensional reconstruction apparatus, including an obtaining unit configured to obtain a target face model, a preset head skeleton model, and a preset dental gum model matching with the preset head skeleton model, where the preset head skeleton model at least includes: presetting a jaw bone model and a skull bone model; the fitting unit is configured to fit the preset head skeleton model based on the target face model to obtain a fitting position of the preset head skeleton model; the determining unit is configured to determine the fitting position of the preset dental gum model according to the fitting position of the preset head skeleton model and the position corresponding relation between the preset head skeleton model and the preset dental gum model; and the conversion unit is configured to perform position conversion on the vertex of the preset dental gum model based on the fitting position of the preset dental gum model to obtain the target dental gum model.
According to a third aspect of the embodiments of the present disclosure, there is provided an electronic apparatus including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement the three-dimensional reconstruction method of any one of the above.
According to a fourth aspect of embodiments of the present disclosure, there is provided a computer-readable storage medium, wherein instructions, when executed by a processor of an electronic device, enable the electronic device to perform the three-dimensional reconstruction method of any one of the above.
According to a fifth aspect of embodiments of the present disclosure, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the three-dimensional reconstruction method of any one of the above.
The technical scheme provided by the embodiment of the disclosure at least brings the following beneficial effects:
this is disclosed through obtaining target face model, predetermine head skeleton model and with predetermine the predetermined tooth gum model that head skeleton model matches, wherein, includes at least in the predetermined head skeleton model: presetting a jaw bone model and a skull bone model; fitting the preset head skeleton model based on the target face model to obtain a fitting position of the preset head skeleton model; determining the fitting position of the preset dental gum model according to the fitting position of the preset head skeleton model and the position corresponding relation between the preset head skeleton model and the preset dental gum model; based on the fitting position of the preset dental gum model, the vertex of the preset dental gum model is subjected to position conversion to obtain the target dental gum model, the purpose of determining the fitting position of the preset dental gum model by taking the fitting position of the preset head skeleton model as a reference can be achieved, the technical effect of accurately constructing the dental gum model on the human face model is achieved, and the problem that the oral cavity structure of the human face three-dimensional model is difficult to accurately construct in the related technology is solved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure and are not to be construed as limiting the disclosure.
Fig. 1 is a schematic view of an application scenario of a three-dimensional reconstruction method according to an exemplary embodiment.
Fig. 2 is a flow chart illustrating a method of three-dimensional reconstruction in accordance with an exemplary embodiment.
FIG. 3 is a diagram illustrating a model of a target face in a three-dimensional reconstruction method according to an exemplary embodiment.
Fig. 4 is a schematic diagram illustrating a predetermined skull model in a three-dimensional reconstruction method according to an exemplary embodiment.
Fig. 5 is a schematic diagram illustrating a preset jaw bone model in a three-dimensional reconstruction method according to an exemplary embodiment.
FIG. 6 is a schematic diagram illustrating a model of a predetermined dental gums in a three-dimensional reconstruction method according to an exemplary embodiment.
Fig. 7 is a schematic diagram illustrating a method for three-dimensional reconstruction according to an exemplary embodiment, in which a second marker point is marked on the surface of the target face model.
Fig. 8 is a schematic diagram illustrating a method for three-dimensional reconstruction according to an exemplary embodiment, in which a first marker point is marked on a surface of a predetermined skull model.
Fig. 9 is a block diagram illustrating a three-dimensional reconstruction apparatus according to an exemplary embodiment.
Fig. 10 is a block diagram illustrating a terminal according to an example embodiment.
Detailed Description
In order to make the technical solutions of the present disclosure better understood by those of ordinary skill in the art, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.
It should be noted that the terms "first," "second," and the like in the description and claims of the present disclosure and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the disclosure described herein are capable of operation in sequences other than those illustrated or otherwise described herein. The implementations described in the exemplary embodiments below are not intended to represent all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure, as detailed in the appended claims.
The three-dimensional reconstruction method according to the first embodiment provided by the present application may be applied to an application scenario as shown in fig. 1, where fig. 1 is an application scenario diagram of information processing in an embodiment, and the application scenario may include a first client 110 and a server 120, where the server 120 may be in communication connection with the first client 110 through a network, respectively. The first client 110 displays the target face model, the preset head skeleton model and the preset dental gum model matched with the preset head skeleton model, which are obtained from the server 120, and triggers a first target request to the server 120, and the server 120 responds to the first target request to fit the preset head skeleton model based on the target face model and returns the obtained fitting position data of the preset head skeleton model. The method comprises the steps that a first client 110 displays a fitting position of a preset head skeleton model, a second target request is triggered to a server 120, the server 120 responds to the second target request, determines the fitting position of a preset tooth gum model according to the fitting position of the preset head skeleton model and the position corresponding relation between the preset head skeleton model and the preset tooth gum model, carries out position conversion on the top point of the preset tooth gum model based on the fitting position of the preset tooth gum model to obtain a target tooth gum model, and returns the target tooth gum model, so that the target tooth gum model is displayed in a face model of the first client 110, the technical effect of accurately constructing the tooth gum model on a face model is achieved, and the problem that the oral cavity structure of the three-dimensional face model is difficult to accurately construct in the related technology is solved.
Fig. 2 is a flowchart illustrating a three-dimensional reconstruction method according to an exemplary embodiment, where the three-dimensional reconstruction method is used in a server, as shown in fig. 2, and includes the following steps.
In step 8201, a target face model, a preset head skeleton model and a preset dental gum model matching the preset head skeleton model are obtained, wherein the preset head skeleton model at least comprises: a preset jaw bone model and a preset skull bone model.
Specifically, the target face model obtained in the embodiment of the present disclosure is a three-dimensional model, and the target face model may be obtained by scanning a target face and using a three-dimensional reconstruction algorithm, or may be obtained by other methods.
Alternatively, as shown in fig. 3, the target face model may be characterized by neutral-expression three-dimensional face data in the form of a triangular mesh, and may be further characterized by other-expression three-dimensional face data in the form of a triangular mesh.
It should be noted that there is a corresponding relationship between the facial surface of the same organism and the jaw bone and the skull bone, meanwhile, since the upper dental bed is attached to the skull bone to drive the teeth to make rigid motion therewith, and the lower dental bed is attached to the jaw bone to drive the teeth to make rigid motion therewith, a head bone model (a jaw bone model and a skull bone model) can be obtained, and then a target dental bed model corresponding to the target facial model is constructed based on the dental bed model matched with the jaw bone model and the skull bone model, thereby obtaining the oral cavity structure of the target facial model.
It should be further noted that, while the target face model is constructed, a head skeleton model corresponding to the target face model is not generally constructed, and the preset head skeleton model obtained in the embodiment of the present disclosure is a set of head skeleton models of the same organism to which the target face model belongs. Specifically, the preset head skeleton model is a three-dimensional model, and in the case that the target face model is a human face model, as shown in fig. 4 and 5, the preset head skeleton model may include a set of universal human head bone template model and jaw bone template model, the head bone template model may be represented by three-dimensional head bone data in a triangular mesh form, and the jaw bone template model may also be represented by three-dimensional jaw bone data in a triangular mesh form.
The embodiment of the disclosure obtains the preset head skeleton model and also obtains the preset dental gum model matched with the preset head skeleton model, and correspondingly, the preset dental gum model is also a three-dimensional model, as shown in fig. 6, the preset dental gum model includes a preset upper dental gum and a preset lower dental gum, and the preset dental gum model can be represented by three-dimensional dental gum data in a triangular mesh form.
In step S202, a preset head skeleton model is fitted based on the target face model, and a fitting position of the preset head skeleton model is obtained.
Specifically, the preset skull model can be subjected to deformation processing according to the position of the target face model, so that the fitting position of the preset skull model is obtained by fitting to the position aligned with the target face model, and meanwhile, the preset jaw bone model is subjected to deformation processing, so that the fitting position of the preset jaw bone model is obtained by fitting to the position aligned with the target face model.
In step S203, the fitting position of the preset dental gum model is determined according to the fitting position of the preset head skeleton model and the position corresponding relationship between the preset head skeleton model and the preset dental gum model.
Specifically, after the fitting position of the preset skull model and the fitting position of the preset jaw model are obtained, the fitting position of the preset upper dental gum model is determined according to the corresponding relation between the preset upper dental gum model and the preset skull model, and the fitting position of the preset lower dental gum model is determined according to the corresponding relation between the preset lower dental gum model and the preset skull model, namely, the position of the oral cavity structure of the target face model is obtained.
In step S204, based on the fitting position of the preset dental gum model, position conversion is performed on the vertex of the preset dental gum model to obtain a target dental gum model.
Specifically, the position of the vertex of the preset dental gum model is converted to the fitting position, so that the target dental gum model fitted with the target face model is obtained.
Through the embodiment of the disclosure, a set of preset head skeleton models associated with the target face model is obtained, the preset head skeleton models are fitted to the positions attached to the target face model, the fitting positions of the preset tooth gum models matched with the preset head skeleton models are further determined, the internal structure of the oral cavity is reconstructed in a mode that the pixel corresponding relation between pictures is obtained through obtaining multi-view visual pictures, and the accurate internal structure of the oral cavity of the target face model can be obtained.
Optionally, in the three-dimensional reconstruction method shown in the embodiment of the present disclosure, fitting the preset head skeleton model based on the target face model to obtain a fitting position of the preset head skeleton model includes: converting the position of each vertex of the preset head skeleton model through a target conversion relation to obtain each converted vertex of the preset head skeleton model and the position of each converted vertex, wherein the target conversion relation is used for representing the position conversion relation between the preset head skeleton model and a target head skeleton model corresponding to the target face model; carrying out iterative deformation on each converted vertex of the preset head skeleton model to obtain deformation displacement of each converted vertex; and moving the position of the converted vertex by a distance corresponding to the deformation displacement in the normal direction that each converted vertex corresponds to the surface of the preset head skeleton model to obtain the target position of the converted vertex, and forming the fitting position of the preset head skeleton model by the target position of each converted vertex.
Specifically, the target head skeleton model corresponding to the target face model may be a theoretical head skeleton model corresponding to the target face model, for example, a theoretical position of the head skeleton model corresponding to the target face model may be determined according to a skin thickness of each vertex corresponding to the target face model, so as to determine the theoretical head skeleton model, and meanwhile, a target conversion relationship between the preset head skeleton model and the theoretical head skeleton model is determined, and a position of each vertex of the preset head skeleton model is converted through the target conversion relationship.
It should be noted that, the positions of the vertexes of the preset head skeleton model are converted through the target conversion relationship, the preset head skeleton model can be roughly fitted to the position aligned with the target face model, in order to obtain a more accurate fitting position of the preset head skeleton model, further iterative optimization needs to be performed on the vertexes of the converted preset head skeleton model to obtain deformation displacements of the vertexes after conversion, and then the positions of the vertexes after conversion are updated through the deformation displacements to obtain the fitting position of the preset head skeleton model.
Optionally, in the three-dimensional reconstruction method illustrated in the embodiment of the present disclosure, the vertex of the preset head bone model includes a vertex of a convex region and a vertex of a concave region of the model surface, and converting the position of each vertex of the preset head bone model through a target conversion relationship to obtain each converted vertex of the preset head bone model and the position of each converted vertex include: acquiring the vertex of a convex region of a preset head skeleton model; converting the position of the vertex of the protruding region of the preset head skeleton model through a first conversion relation to obtain the converted vertex of the protruding region and the converted position of the vertex of the protruding region, wherein the first conversion relation represents the conversion relation between a plurality of first mark points of the preset head skeleton model and a plurality of preset head skeleton points corresponding to the target face model; combining the vertexes of the converted convex regions with vertexes of the preset head skeleton model except the convex regions to obtain each converted vertex of the preset head skeleton model; and combining the positions of the vertexes of the converted protruding regions and the positions of the vertexes outside the protruding regions of the preset head bone model to obtain the positions of the converted vertexes of the preset head bone model.
Specifically, since the position relationship between the protruding region on the surface of the preset head skeleton model and the protruding region of the target head skeleton model corresponding to the target face model is easier to be determined more accurately, for example, a first conversion relationship between a plurality of first mark points of the preset head skeleton model and a plurality of preset head skeleton points corresponding to the target face model can be obtained to represent the relationship between the two, and the influence of the position of the vertex of the protruding region on the surface of the preset head skeleton model on the fit degree between the preset head skeleton model and the target face model is large in the process of roughly fitting the preset head skeleton model to the position aligned with the target face model, in order to reduce the amount of calculation, the position conversion can be performed on the vertex of the protruding region on the surface of the preset head skeleton model through the first conversion relationship to obtain the vertex of the converted protruding region and the position thereof, and combining the vertexes and positions of the converted convex regions and the vertexes and positions of the original concave regions to obtain the vertexes and positions of the preset head skeleton model after the target conversion relation is converted.
Optionally, in the three-dimensional reconstruction method shown in the embodiment of the present disclosure, before transforming the position of the vertex of the preset head bone model through the first transformation relationship to obtain a preliminary fitting position of the vertex of the preset head bone model, the method further includes: determining a plurality of second mark vertexes of the target face model, and respectively determining skin thicknesses corresponding to the second mark vertexes; moving the position of the second mark vertex by a distance corresponding to the skin thickness of the second mark vertex in the normal direction of the second mark vertex corresponding to the surface of the target face model to obtain the position of a preset head skeleton point corresponding to the second mark vertex; determining the positions of a plurality of first mark vertexes of a preset head model, wherein the position corresponding relation exists between the first mark vertexes and the second mark vertexes; and acquiring a conversion relation between the position of the preset head skeleton point and the positions of the multiple first mark vertexes to obtain a first conversion relation.
Specifically, the plurality of second marker points on the surface of the target face model may be points with known skin thickness, the skin thickness corresponding to the second marker points may be theoretical skin thickness, and the theoretical skin thickness may be determined by anatomical characteristics.
The preset bone point corresponding to the second mark point can be a theoretical bone point, and the position of the second mark point is converted according to the theoretical skin thickness to obtain the theoretical bone point, for example, vfaceRepresenting a second marked point, nfaceThe normal vector corresponding to the second marking point is represented, delta represents the theoretical skin thickness corresponding to the second marking point, and the theoretical bone point v corresponding to the second marking point can be determined through the following formulaskull_targ etThe position of (2): v. ofskull_targ et＝vface-δnface。
The multiple first mark points on the preset head skeleton model surface are mark points corresponding to the multiple second mark points on the target face model surface, for example, as shown in fig. 7, a second mark point 0 is marked at the brow bone position of the target face model, a second mark point 1 is marked at the nose bridge position, a second mark point 2 is marked at the forehead position, and second mark points 3 and 4 are respectively marked at the upper ear positions. As shown in fig. 8, according to the relative relationship between the structure of the face model and the structure of the skull model, the first mark point 0, the first mark point 1, the first mark point 2, the first mark point 3, and the first mark point 4 corresponding to the second mark point 0, the second mark point 1, the second mark point 2, the second mark point 3, and the second mark point 4 are marked at the corresponding positions on the preset skull model.
Further, after the positions of the plurality of first mark points and the positions of the second mark points are obtained, a first conversion relation is determined according to the relationship between the positions of the theoretical skeleton points corresponding to the plurality of first mark points and the positions of the plurality of first mark points, specifically, the first conversion relation can be represented by a rigid transformation matrix, a target rigid transformation matrix can be determined through at least 3 pairs of mark points, and the target rigid transformation matrix is used for transforming the vertex of the convex area on the surface of the head skeleton model to the position close to the vertex of the convex area of the theoretical head skeleton model corresponding to the human face model.
It should be noted that, whether the target transformation relationship is accurate or not depends on the accuracy of the theoretical head skeleton, and because it is difficult to accurately determine the theoretical head skeleton, the obtained target transformation relationship is difficult to accurately transform the position of the preset head skeleton model into the position attached to the target face model, and it is necessary to further perform deformation optimization on each vertex of the preset head skeleton model to obtain a more accurate fitting position.
Specifically, when further performing deformation optimization on each converted vertex of the preset head skeleton model, the distance from the converted vertex to the skin surface vertex of the target face model can be obtained, and multiple iteration changes are performed on each converted vertex according to the deformation constraint of the vertex, which is the relationship between the distance and the skin thickness range, so that the position of the converted vertex is more attached to the target face model.
Optionally, in the three-dimensional reconstruction method shown in the embodiment of the present disclosure, iteratively deforming each converted vertex of the preset head bone model, and obtaining a deformation displacement of each converted vertex includes: and performing iterative deformation on each converted vertex by taking the minimum shell deformation energy of each converted vertex and the minimum sum of the difference values of the deformation displacement of each converted vertex and the skin thickness adjustment value corresponding to the vertex as a target to obtain the deformation displacement of each converted vertex, wherein the skin thickness adjustment value corresponding to each converted vertex is determined by the distance from the converted vertex to the skin surface layer vertex of the target face model and the skin thickness range interval corresponding to the target face model.
It should be noted that, in the process of performing iterative deformation on each vertex, on one hand, in order to ensure smooth deformation of each vertex after transformation of the preset head bone model, the minimum thin-shell deformation energy term corresponding to each vertex is taken as a first optimization target.
On the other hand, the deformation displacement of the vertex is constrained by the skin thickness range, specifically, the position of the transformed vertex after iteration needs to fall within the skin thickness range interval, in the case that the distance from the transformed vertex to the skin surface layer vertex of the target face model is greater than the maximum value of the skin thickness range interval, the vertex needs to be deformed to a position close to the skin surface layer vertex so as to fall within the skin thickness range interval, and in the case that the distance from the transformed vertex to the skin surface layer vertex of the target face model is less than the minimum value of the skin thickness range interval, the vertex needs to be deformed to a position far away from the skin surface layer vertex so as to fall within the skin thickness range interval.
In order to represent that the deformation displacement of the vertex is constrained by the skin thickness range, a skin thickness adjustment value is determined according to the distance from the converted vertex to the skin surface vertex of the target face model and the skin thickness range interval corresponding to the target face model, and the closer the deformation displacement corresponding to the converted vertex is to the skin thickness adjustment value, the closer the converted vertex is to the skin thickness adjustment value, the more the converted vertex is attached to the target face model after deformation is carried out.
Optionally, under the condition that the distance from the converted vertex to the vertex of the skin surface layer is smaller than the minimum value of the skin thickness range interval, calculating a difference value between the distance and the minimum value, and determining a calculation result as a skin thickness adjustment value corresponding to the converted vertex; under the condition that the distance from the converted vertex to the skin surface layer vertex is larger than the maximum value of the skin thickness range interval, calculating the difference value between the distance and the maximum value, and determining the calculation result as a skin thickness adjustment value corresponding to the converted vertex; and under the condition that the distance from the converted vertex to the skin surface layer vertex is larger than or equal to the minimum value of the skin thickness range, and the distance from the converted vertex to the surface of the target face model is smaller than or equal to the maximum value of the skin thickness range, determining that the skin thickness adjustment value corresponding to the converted vertex is zero.
Further, the minimum sum of the difference values of the deformation displacement of each converted vertex and the skin thickness adjustment value corresponding to the vertex is taken as a second optimization target, so that the first optimization target and the second optimization target are integrated to obtain an optimization target of iterative deformation, the optimization target is solved, and the deformation displacement of each vertex of the preset head skeleton model is obtained.
In an alternative embodiment, the vertex of the convex region may be selected from the preset head bone model, and the vertex position obtained after the target transformation relation is transformed is xiI is an element of S and the normal direction is niWhere S is the set of all vertices of the convex region of the first head bone model.
The following optimization objectives are determined:
wherein E isshell(d) Is the energy term of deformation of the thin shell, d is the deformation displacement of each transformed vertex of the preset head skeleton modeliDeformable displacement of vertex i, n, for a transformation of a preset head skeleton modeliIs the normal vector to i, wiIs the weight corresponding to i, δiFor the skin thickness adjustment value corresponding to i, according to the distance from the vertex i to the surface of the target face model
Set up wiAnd deltai：
Otherwise, δi＝0，wi＝1。
Wherein [ delta ]min，δmax]Is a personThe skin thickness range region between the face skin and the skull, which is an empirical value range region, may be set to [2mm, 7mm, in particular]。
Because the skin thickness corresponding to the protruding region of the preset head skeleton model is relatively thin, a target vertex capable of accurately determining the theoretical skin thickness according to anatomy exists, the deformation displacement of the target vertex is strongly restricted by the theoretical skin thickness, and optionally, in the process of carrying out iterative deformation on each converted vertex of the preset head skeleton model, the deformation displacement of the target vertex meets the following restriction conditions: and the deformation displacement of the target vertex is equal to the distance between the target vertex and the preset skin surface layer vertex corresponding to the target vertex, wherein the target vertex is a vertex with determined skin thickness corresponding to each converted vertex, and the distance between the target vertex and the preset skin surface layer vertex corresponding to the target vertex is the skin thickness corresponding to the target vertex.
Specifically, a plurality of points with known theoretical skin thickness of the convex region can be selected from a preset head skeleton model, and a plurality of target vertexes j are obtained through target conversion relation conversion, wherein the positions of the target vertexes j are xjJ is belonged to C, and the corresponding vertex of the skin surface layer is
In the normal direction of
Wherein, C is the set of all target points, and the constraint conditions are determined as follows:
wherein, deltajIs j corresponding to the skin thickness.
Under the constraint condition, the optimization target is iteratively solved to obtain the deformation displacement d of each converted head bone vertex, and after each iteration, the converted head bone vertex position is updated according to the following formula: x is the number ofi＝xi+djBy a predetermined number of timesFor example, the first iteration may be performed through 3 to 5 iterations to obtain the target position of the vertex of the transformed head skeleton, and the target positions of the vertex of the transformed head skeleton are combined to obtain the fitting position of the preset head skeleton.
According to the embodiment of the disclosure, a universal preset head skeleton model can be fitted to a target face model through deformation, then the thickness between a key point on the surface of the target face model and a key point of the preset head skeleton model is used as a constraint, and the deformation amount of a converted vertex of the preset head skeleton is solved frame by frame, so that a target position of the converted vertex of the preset head skeleton is obtained, a fitting position of the preset head skeleton model is obtained, and finally the fitting position of the preset head skeleton model is used as a reference to generate the fitting position of a target tooth bed in the oral cavity corresponding to the target face model. The three-dimensional position of the internal structure of the oral cavity is directly fitted through the reconstruction data of the target face model and the anatomical characteristics of the face, and compared with the method of directly reconstructing the oral cavity through vision, the accuracy of oral cavity structure reconstruction is improved, and the difficulty of oral cavity structure reconstruction is reduced.
Optionally, in the three-dimensional reconstruction method illustrated in the embodiment of the present disclosure, the preset dental gum model includes a preset upper dental gum model and a preset lower dental gum model, and determining the fitting position of the preset dental gum model according to the fitting position of the preset head bone model and the position corresponding relationship between the preset head bone model and the preset dental gum model includes: determining a plurality of first mark positions in fitting positions of vertexes of a preset skull model, and determining a plurality of second mark positions on a preset upper dental gum model, wherein the plurality of first mark positions and the plurality of second mark positions have corresponding relations; converting the position of the vertex of the preset upper dental gum model based on the corresponding relation between the plurality of first mark positions and the plurality of second mark positions to obtain the fitting position of the vertex of the preset upper dental gum model; determining a plurality of third mark positions in fitting positions of vertexes of a preset jaw bone model, and determining a plurality of fourth mark positions on a preset lower dental gum model, wherein the plurality of third mark positions and the plurality of fourth mark positions have corresponding relations; and converting the position of the vertex of the preset lower dental gum model based on the corresponding relation between the plurality of third mark positions and the plurality of fourth mark positions to obtain the fitting position of the vertex of the preset lower dental gum model.
It should be noted that since the upper gums are attached to the skull and follow it for rigid movement, the lower gums are attached to the jaw and follow it for rigid movement. The corresponding point pairs between the preset upper dental articulator model and the preset skull model can be determined, and the fitting positions of all vertexes of the preset upper dental articulator model can be obtained by deforming all vertexes of the preset upper dental articulator model in a thin shell deformation mode by taking the fitting positions of the preset skull model as a reference.
Correspondingly, the corresponding point pair between the preset lower dental articulator model and the preset jaw model can be determined, the fitting position of the preset jaw model is used as a reference, and each vertex of the preset lower dental articulator model is deformed in a shell deformation mode, so that the fitting position of each vertex of the preset lower dental articulator model can be obtained.
Through the embodiment of the disclosure, the preset head skeleton model is fitted according to the target head skeleton model, after the fitting position of the preset head skeleton model is obtained, the deformation of each vertex of the preset tooth gum model by the thin shell deformation mode is further determined, the target tooth gum model is obtained, namely, the tooth gum model attached to the target head skeleton model is obtained, the effect that the inner structure of the oral cavity is not required to be reconstructed in a mode of acquiring multi-view visual pictures, and the inner structure of the oral cavity of the target face model can be accurately constructed is achieved.
Fig. 9 is a block diagram illustrating a three-dimensional reconstruction apparatus according to an exemplary embodiment. Referring to fig. 9, the apparatus includes an acquisition unit 91, a fitting unit 92, a determination unit 93, and a conversion unit 94.
Specifically, the obtaining unit 91 is configured to obtain a target face model, a preset head skeleton model and a preset dental gum model matching with the preset head skeleton model, where the preset head skeleton model at least includes: a preset jaw bone model and a preset skull bone model.
A fitting unit 92 configured to fit the preset head skeleton model based on the target face model, resulting in a fitting position of the preset head skeleton model.
A determining unit 93 configured to determine a fitting position of the preset dental gum model according to the fitting position of the preset head bone model and a position correspondence between the preset head bone model and the preset dental gum model.
And a conversion unit 94 configured to perform position conversion on the vertex of the preset dental gum model based on the fitting position of the preset dental gum model to obtain the target dental gum model.
Alternatively, in the three-dimensional reconstruction apparatus shown in the embodiment of the present disclosure, the fitting unit 92 includes: the first conversion module is configured to convert the positions of all vertexes of the preset head skeleton model through a target conversion relation to obtain all converted vertexes of the preset head skeleton model and the positions of all converted vertexes, wherein the target conversion relation is used for representing the position conversion relation between the preset head skeleton model and a target head skeleton model corresponding to the target face model; the deformation module is configured to carry out iterative deformation on each converted vertex of the preset head skeleton model to obtain deformation displacement of each converted vertex; and the second conversion module is configured to move the positions of the converted vertexes by a distance corresponding to the deformation displacement in the normal direction in which each converted vertex corresponds to the surface of the preset head skeleton model to obtain target positions of the converted vertexes, and the target positions of the converted vertexes form the fitting positions of the preset head skeleton model.
Optionally, in the three-dimensional reconstruction apparatus shown in the embodiment of the present disclosure, the apparatus further includes: the deformation module includes: and the deformation submodule is configured to perform iterative deformation on each converted vertex to obtain the deformation displacement of each converted vertex by taking the minimum shell deformation energy of each converted vertex and the minimum sum of the difference values of the deformation displacement of each converted vertex and the skin thickness adjustment value corresponding to the vertex as targets, wherein the skin thickness adjustment value corresponding to each converted vertex is determined by the distance from the converted vertex to the skin surface layer vertex of the target face model and the skin thickness range interval corresponding to the target face model.
Optionally, in the three-dimensional reconstruction apparatus shown in the embodiment of the present disclosure, the apparatus further includes: the first calculation submodule is configured to calculate a difference value between the distance and the minimum value under the condition that the distance from the converted vertex to the vertex of the skin surface layer is smaller than the minimum value of the skin thickness range interval, and determine a calculation result as a skin thickness adjustment value corresponding to the converted vertex; the second calculation submodule is configured to calculate a difference value between the distance and the maximum value under the condition that the distance from the converted vertex to the vertex of the skin surface layer is larger than the maximum value of the skin thickness range interval, and determine a calculation result as a skin thickness adjustment value corresponding to the converted vertex; and the third calculation sub-module is configured to determine that the skin thickness adjustment value corresponding to the converted vertex is zero when the distance from the converted vertex to the skin surface layer vertex is greater than or equal to the minimum value of the skin thickness range and the distance from the converted vertex to the target face model surface is less than or equal to the maximum value of the skin thickness range.
Optionally, in the three-dimensional reconstruction apparatus shown in the embodiment of the present disclosure, in the process of iteratively deforming each transformed vertex of the preset head bone model, the deformation displacement of the target vertex satisfies the following constraint condition: and the deformation displacement of the target vertex is equal to the distance between the target vertex and the preset skin surface layer vertex corresponding to the target vertex, wherein the target vertex is a vertex with determined skin thickness corresponding to each converted vertex, and the distance between the target vertex and the preset skin surface layer vertex corresponding to the target vertex is the skin thickness corresponding to the target vertex.
Optionally, in the three-dimensional reconstruction apparatus shown in the embodiment of the present disclosure, the first conversion module includes: an acquisition submodule configured to acquire a vertex of a convex region of a preset head bone model; the conversion submodule is configured to convert the position of the vertex of the protruding region of the preset head skeleton model through a first conversion relation to obtain the converted vertex of the protruding region and the converted position of the vertex of the protruding region, wherein the first conversion relation represents the conversion relation between a plurality of first mark points of the preset head skeleton model and a plurality of preset head skeleton points corresponding to the target face model; a first combining submodule configured to combine the vertexes of the converted protruding regions and vertexes other than the protruding regions of the preset head bone model to obtain each converted vertex of the preset head bone model; and the second combination submodule is configured to combine the positions of the vertexes of the converted protruding regions and the positions of the vertexes outside the protruding regions of the preset head bone model to obtain the positions of the converted vertexes of the preset head bone model.
Optionally, in the three-dimensional reconstruction apparatus shown in the embodiment of the present disclosure, the apparatus further includes: the first determining module is configured to determine a plurality of second mark vertexes of the target face model before converting the positions of the vertexes of the preset head skeleton model through a first conversion relation to obtain a primary fitting position of the vertexes of the preset head skeleton model, and determine skin thicknesses corresponding to the second mark vertexes respectively; the third conversion module is configured to move the position of the second mark vertex by a distance corresponding to the skin thickness of the second mark vertex in the normal direction of the target face model surface corresponding to the second mark vertex to obtain the position of a preset head skeleton point corresponding to the second mark vertex; a second determining module configured to determine positions of a plurality of first marked vertexes of the preset head model, wherein the plurality of first marked vertexes and the plurality of second marked vertexes have position correspondence; an obtaining module configured to obtain a conversion relation between a position of a preset head bone point and positions of a plurality of first marker vertexes, resulting in a first conversion relation.
Optionally, in the three-dimensional reconstruction apparatus illustrated in the embodiment of the present disclosure, the preset dental gum model includes a preset upper dental gum model and a preset lower dental gum model, and the determining unit 93 includes: a third determination module configured to determine a plurality of first mark positions in fitting positions of vertices of the preset skull model and a plurality of second mark positions on the preset upper dental gum model, wherein the plurality of first mark positions and the plurality of second mark positions have corresponding relations; the fourth conversion module is configured to convert the position of the vertex of the preset upper dental articulator model based on the corresponding relation between the plurality of first mark positions and the plurality of second mark positions to obtain a fitting position of the vertex of the preset upper dental articulator model; a fourth determination module configured to determine a plurality of third mark positions in fitting positions of vertices of the preset jaw bone model and a plurality of fourth mark positions on the preset lower dental gum model, wherein the plurality of third mark positions and the plurality of fourth mark positions have a corresponding relationship therebetween; a fifth conversion module configured to convert the position of the vertex of the preset lower dental articulator model based on the correspondence between the plurality of third mark positions and the plurality of fourth mark positions to obtain a fitting position of the vertex of the preset lower dental articulator model
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
With regard to the apparatus in the above-described embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment related to the method, and will not be elaborated here.
In an exemplary embodiment, there is also provided an electronic device including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement the three-dimensional reconstruction method of any one of the above.
In an exemplary embodiment, there is also provided a computer-readable storage medium having instructions that, when executed by a processor of an electronic device of an information processing method, enable the electronic device of the information processing method to perform any one of the three-dimensional reconstruction methods described above. Alternatively, the computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
In an exemplary embodiment, a computer program product is also provided, which, when being executed on a data processing device, is adapted to carry out a program for initializing a three-dimensional reconstruction method as defined in any of the above. The computer product may be a terminal, which may be any one of a group of computer terminals. Optionally, in this embodiment of the present disclosure, the terminal may also be a terminal device such as a mobile terminal.
Optionally, in this embodiment of the present disclosure, the terminal may be located in at least one network device of a plurality of network devices of a computer network.
Alternatively, fig. 10 is a block diagram illustrating a structure of a terminal according to an exemplary embodiment. As shown in fig. 10, the terminal may include: one or more (only one shown) processors 101, a memory 103 for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement any of the above page processing methods.
The memory may be configured to store software programs and modules, such as program instructions/modules corresponding to the page processing method and apparatus in the embodiments of the disclosure, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, implementing the page processing method. The memory may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory may further include memory located remotely from the processor, and these remote memories may be connected to the computer terminal through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
It can be understood by those skilled in the art that the structure shown in fig. 10 is only an illustration, and the computer terminal may also be a terminal device such as a smart phone (e.g., an Android phone, an iOS phone, etc.), a tablet computer, a palmtop computer, a Mobile Internet Device (MID), a PAD, and the like. Fig. 10 is a diagram illustrating a structure of the electronic device. For example, the terminal 10 may also include more or fewer components (e.g., network interfaces, display devices, etc.) than shown in FIG. 10, or have a different configuration than shown in FIG. 10.
Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the disclosure disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of the disclosure following, in general, the principles of the disclosure and including such departures from the present disclosure as come within known or customary practice within the art to which the disclosure pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.
It will be understood that the present disclosure is not limited to the precise arrangements described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims (10)
1. A method of three-dimensional reconstruction, comprising:
obtaining a target face model, a preset head skeleton model and a preset dental gum model matched with the preset head skeleton model, wherein the preset head skeleton model at least comprises: presetting a jaw bone model and a skull bone model;
fitting the preset head skeleton model based on the target face model to obtain a fitting position of the preset head skeleton model;
determining the fitting position of the preset dental gum model according to the fitting position of the preset head skeleton model and the position corresponding relation between the preset head skeleton model and the preset dental gum model;
and performing position conversion on the vertex of the preset dental gum model based on the fitting position of the preset dental gum model to obtain the target dental gum model.
2. The three-dimensional reconstruction method according to claim 1, wherein the fitting the preset head skeleton model based on the target face model to obtain a fitting position of the preset head skeleton model comprises:
converting the position of each vertex of the preset head skeleton model through a target conversion relation to obtain each converted vertex of the preset head skeleton model and the position of each converted vertex, wherein the target conversion relation is used for representing the position conversion relation between the preset head skeleton model and a target head skeleton model corresponding to the target face model;
performing iterative deformation on each converted vertex of the preset head skeleton model to obtain deformation displacement of each converted vertex;
and moving the position of each converted vertex by a distance corresponding to the deformation displacement in the normal direction of the surface of the preset head bone model corresponding to each converted vertex to obtain the target position of each converted vertex, and forming the fitting position of the preset head bone model by the target position of each converted vertex.
3. The three-dimensional reconstruction method of claim 2, wherein said iteratively deforming each of said transformed vertices of said predetermined head bone model to obtain a deformed displacement of each of said transformed vertices comprises:
and performing iterative deformation on each converted vertex by taking the minimum shell deformation energy of each converted vertex and the minimum sum of the difference values of the deformation displacement of each converted vertex and the skin thickness adjustment value corresponding to the vertex as targets to obtain the deformation displacement of each converted vertex, wherein the skin thickness adjustment value corresponding to each converted vertex is determined by the distance from the converted vertex to the skin surface layer vertex of the target face model and the skin thickness range interval corresponding to the target face model.
4. The three-dimensional reconstruction method according to claim 3,
under the condition that the distance from the converted vertex to the skin surface layer vertex is smaller than the minimum value of the skin thickness range interval, calculating the difference value between the distance and the minimum value, and determining the calculation result as the skin thickness adjustment value corresponding to the converted vertex;
under the condition that the distance from the converted vertex to the vertex of the skin surface layer is larger than the maximum value of the skin thickness range interval, calculating the difference value between the distance and the maximum value, and determining the calculation result as the skin thickness adjustment value corresponding to the converted vertex;
and under the condition that the distance from the converted vertex to the skin surface layer vertex is larger than or equal to the minimum value of the skin thickness range, and the distance from the converted vertex to the surface of the target face model is smaller than or equal to the maximum value of the skin thickness range, determining that the skin thickness adjustment value corresponding to the converted vertex is zero.
5. The three-dimensional reconstruction method according to claim 3, wherein during the iterative deformation of each transformed vertex of the preset head bone model, the deformation displacement of the target vertex satisfies the following constraint conditions: and the deformation displacement of the target vertex is equal to the distance between the target vertex and a preset skin surface layer vertex corresponding to the target vertex, wherein the target vertex is a vertex with determined skin thickness corresponding to each converted vertex, and the distance between the target vertex and the preset skin surface layer vertex corresponding to the target vertex is the skin thickness corresponding to the target vertex.
6. The three-dimensional reconstruction method according to claim 2, wherein the transforming the positions of the vertices of the preset head bone model through the target transformation relationship to obtain the transformed vertices of the preset head bone model and the positions of the transformed vertices comprises:
acquiring the vertex of the convex area of the preset head skeleton model;
converting the position of the vertex of the protruding region of the preset head skeleton model through a first conversion relation to obtain the converted vertex of the protruding region and the converted position of the vertex of the protruding region, wherein the first conversion relation represents the conversion relation between a plurality of first mark points of the preset head skeleton model and a plurality of preset head skeleton points corresponding to the target face model;
combining the converted vertexes of the convex region and vertexes of the preset head skeleton model except for the convex region to obtain each converted vertex of the preset head skeleton model;
combining the positions of the vertexes of the converted protruding regions and the positions of the vertexes of the preset head bone model except the protruding regions to obtain the positions of the converted vertexes of the preset head bone model.
7. A three-dimensional reconstruction apparatus, comprising:
an obtaining unit configured to obtain a target face model, a preset head skeleton model and a preset dental gum model matching with the preset head skeleton model, wherein the preset head skeleton model at least comprises: presetting a jaw bone model and a skull bone model;
a fitting unit configured to fit the preset head skeleton model based on the target face model to obtain a fitting position of the preset head skeleton model;
a determining unit configured to determine a fitting position of the preset dental gum model according to the fitting position of the preset head skeleton model and a position correspondence between the preset head skeleton model and the preset dental gum model;
and the conversion unit is configured to perform position conversion on the vertex of the preset dental gum model based on the fitting position of the preset dental gum model to obtain a target dental gum model.
8. An electronic device, comprising:
a processor;
a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the instructions to implement the three-dimensional reconstruction method of any one of claims 1 to 6.
9. A computer-readable storage medium in which instructions, when executed by a processor of an electronic device, enable the electronic device to perform the three-dimensional reconstruction method of any one of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program, when being executed by a processor, implements the three-dimensional reconstruction method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011609669.2A CN112700533B (en) | 2020-12-28 | 2020-12-28 | Three-dimensional reconstruction method, three-dimensional reconstruction device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011609669.2A CN112700533B (en) | 2020-12-28 | 2020-12-28 | Three-dimensional reconstruction method, three-dimensional reconstruction device, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112700533A true CN112700533A (en) | 2021-04-23 |
| CN112700533B CN112700533B (en) | 2023-10-03 |
Family
ID=75512497
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011609669.2A Active CN112700533B (en) | 2020-12-28 | 2020-12-28 | Three-dimensional reconstruction method, three-dimensional reconstruction device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112700533B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090311647A1 (en) * | 2008-06-11 | 2009-12-17 | Jing-Jing Fang | 3d planning and prediction method for optimizing facial skeleton symmetry in orthognathic surgery |
| CN107205794A (en) * | 2013-10-09 | 2017-09-26 | 北京大学口腔医学院 | Digital control laser automates tooth preparation method and equipment and tooth positioner |
| CN108961369A (en) * | 2018-07-11 | 2018-12-07 | 厦门幻世网络科技有限公司 | The method and apparatus for generating 3D animation |
| CN111612897A (en) * | 2020-06-05 | 2020-09-01 | 腾讯科技（深圳）有限公司 | Three-dimensional model fusion method, device and equipment and readable storage medium |
-
2020
- 2020-12-28 CN CN202011609669.2A patent/CN112700533B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090311647A1 (en) * | 2008-06-11 | 2009-12-17 | Jing-Jing Fang | 3d planning and prediction method for optimizing facial skeleton symmetry in orthognathic surgery |
| CN107205794A (en) * | 2013-10-09 | 2017-09-26 | 北京大学口腔医学院 | Digital control laser automates tooth preparation method and equipment and tooth positioner |
| CN108961369A (en) * | 2018-07-11 | 2018-12-07 | 厦门幻世网络科技有限公司 | The method and apparatus for generating 3D animation |
| CN111612897A (en) * | 2020-06-05 | 2020-09-01 | 腾讯科技（深圳）有限公司 | Three-dimensional model fusion method, device and equipment and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112700533B (en) | 2023-10-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11302064B2 (en) | Method and apparatus for reconstructing three-dimensional model of human body, and storage medium | |
| WO2019219012A1 (en) | Three-dimensional reconstruction method and device uniting rigid motion and non-rigid deformation | |
| CN110599540B (en) | Real-time three-dimensional human body shape and posture reconstruction method and device under multi-viewpoint camera | |
| WO2019219013A1 (en) | Three-dimensional reconstruction method and system for joint optimization of human body posture model and appearance model | |
| WO2019219014A1 (en) | Three-dimensional geometry and eigencomponent reconstruction method and device based on light and shadow optimization | |
| CN108053437B (en) | Three-dimensional model obtaining method and device based on posture | |
| CN111428579A (en) | Face image acquisition method and system | |
| CN111784754B (en) | Tooth orthodontic method, device, equipment and storage medium based on computer vision | |
| CN111932678B (en) | Multi-view real-time human motion, gesture, expression and texture reconstruction system | |
| CN111862299A (en) | Human body three-dimensional model construction method and device, robot and storage medium | |
| CN109961496B (en) | Expression driving method and expression driving device | |
| TW202109359A (en) | Face image processing method, image equipment and storage medium | |
| WO2020207177A1 (en) | Image augmentation and neural network training method and apparatus, device and storage medium | |
| CN108053373A (en) | One kind is based on deep learning model fisheye image correcting method | |
| CN109785322B (en) | Monocular human body posture estimation network training method, image processing method and device | |
| CN110796719A (en) | Real-time facial expression reconstruction method | |
| US11928778B2 (en) | Method for human body model reconstruction and reconstruction system | |
| CN112734890A (en) | Human face replacement method and device based on three-dimensional reconstruction | |
| CN113902851A (en) | Face three-dimensional reconstruction method and device, electronic equipment and storage medium | |
| CN112700533B (en) | Three-dimensional reconstruction method, three-dimensional reconstruction device, electronic equipment and storage medium | |
| CN112507766B (en) | Face image extraction method, storage medium and terminal equipment | |
| CN116797733A (en) | Real-time three-dimensional object dynamic reconstruction method | |
| CN116051737A (en) | Image generation method, device, equipment and storage medium | |
| Zhang et al. | Constructing a realistic face model of an individual for expression animation | |
| JP2021026265A (en) | Image processing device, image processing program, and image processing method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |