Expression model generation method and device, storage medium, and computer equipment

Abstract

The present application discloses a method and device for generating an expression model, a storage medium, and a computer device. The method includes: adding a first deformation target corresponding to an expression model to be transferred to an initial character model to obtain a first expression model, wherein the initial character model is an expressionless model including an expression display part and a non-expression display part; obtaining first boundary data corresponding to a first connection area of ​​the first expression model, wherein the first connection area corresponds to the connection between the expression display part and the non-expression display part of the first expression model; if the first boundary data indicates that the first connection area includes at least two boundaries, then after setting the first connection area to a non-deformed state, the first expression model is reversed to obtain an intermediate expression model; and adding a second deformation target corresponding to the intermediate expression model to the initial character model to obtain a second expression model. The present application can remove redundant movements at the connection between the expression part and the non-expression part, which helps to improve the authenticity of the character when making expressions.

Description

[0001] This application is a divisional application of the Chinese patent application filed with the China Patent Office on June 30, 2021, with application number 202110743217.1 and titled “Method and device for generating expression model, storage medium, and computer device”. Technical Field

[0002] The present application relates to the field of animation production technology, and in particular to a method and device for generating an expression model, a storage medium, and a computer device. Background Art

[0003] In the prior art, when the deformation target of the template expression is transmitted to the new character model, the character's expression part is transmitted as a separate deformation target to the new character model, and the non-expression part is not transmitted, so as to simplify the expression binding and save resources. However, the expression part and the non-expression part are connected. If only the expression part is transmitted, for example, the template expression corresponding to the head and neck is transmitted as the deformation target to the new character model, the movement of the neck of the template expression will be substituted into the new character model, which may cause a seam to appear at the connection between the neck and the body when the new character makes an expression, reducing the authenticity of the expression of the new character. Summary of the invention

[0004] In view of this, the present application provides a method and apparatus for generating an expression model, a storage medium, and a computer device, which can remove redundant movements at the connection between expression parts and non-expression parts, thereby helping to improve the authenticity of the character's expressions.

[0005] According to one aspect of the present application, a method for generating an expression model is provided, comprising: adding a first deformation target corresponding to an expression model to be transferred to an initial character model to obtain a first expression model, wherein the initial character model is an expressionless model including an expression display part and a non-expression display part; obtaining first boundary data corresponding to a first connection area of ​​the first expression model, wherein the first connection area corresponds to a connection between an expression display part and a non-expression display part of the first expression model; if the first boundary data indicates that the first connection area includes at least two boundaries, then after setting the first connection area to a non-deformed state, the first expression model is reversed to obtain an intermediate expression model; and adding a second deformation target corresponding to the intermediate expression model to the initial character model to obtain a second expression model.

[0006] According to another aspect of the present application, there is provided a device for generating an expression model, including: a first model generation module, configured to add a first deformation target corresponding to the expression model to be transmitted to an initial character model to obtain a first expression model, where the initial character model is a non-expression model including an expression display part and a non-expression display part; a boundary data acquisition module, configured to acquire first boundary data corresponding to a first connection area of the first expression model, where the first connection area corresponds to a connection between the expression display part and the non-expression display part of the first expression model; a first animation export module, configured to, if the first boundary data indicates that the first connection area includes at least two boundaries, set the first connection area to a non-deformable state and then reverse the first expression model to obtain an intermediate expression model; and a second model generation module, configured to add a second deformation target corresponding to the intermediate expression model to the initial character model to obtain a second expression model.

[0007] According to yet another aspect of the present application, there is provided a storage medium having a computer program stored thereon, and when the program is executed by a processor, the above-mentioned method for generating an expression model is implemented.

[0008] According to still another aspect of the present application, there is provided a computer device, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, and when the processor executes the program, the above-mentioned method for generating an expression model is implemented.

[0009] By means of the above technical solution, for a method, a device, a storage medium, and a computer device for generating an expression model provided by the present application, when transmitting an expression to an initial character model, first add a first deformation target corresponding to the expression model to be transmitted to the initial character model to obtain a first expression model. If the first connection area corresponding to the expression display part and the non-expression display part of the first expression model has multiple boundaries, set the first connection area to a non-deformable state and then reverse the first expression model to obtain an intermediate expression model with a second deformation target, so as to remove the vertex displacement of the first connection area in the deformation target of the original first expression model. Finally, add the intermediate expression model as a deformation target to the non-expression initial character model to obtain a second expression model, so that there will be no seam at the connection area when the second expression model makes an expression. When the present application performs expression transmission to a new character model, it can verify the connection area between the expression display part and the non-expression display part, and in the case where there are multiple boundaries in the connection area, set this area to a non-deformable state and perform model reverse operation, so as to add the reverse result to the non-expression new character model, so that the finally obtained model has a real expression effect and no seam generation, and at the same time, only the deformation target of the expression display part needs to be transmitted, ensuring the expression transmission efficiency.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0012] Figure 1 A schematic diagram of a flow chart of a method for generating an expression model provided in an embodiment of the present application is shown;

[0013] Figure 2 A schematic diagram of a model connection area provided in an embodiment of the present application is shown;

[0014] Figure 3 A schematic diagram of boundary lines of a model connection area provided in an embodiment of the present application is shown;

[0015] Figure 4 A schematic diagram of the structure of an expression model generation device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0016] The present application will be described in detail below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.

[0017] In this embodiment, a method for generating an expression model is provided. Figure 1 As shown, the method includes:

[0018] Step 101, adding a first deformation target corresponding to the expression model to be transferred to the initial character model to obtain a first expression model, wherein the initial character model is an expressionless model;

[0019] In the embodiment of the present application, the initial character model is an expressionless model that needs to transmit expression. The expressionless initial character model may include an expression display part and a non-expression display part, or may only include an expression display part, wherein the expression display part may be the head of the model, or may be the head and neck of the model, and the non-expression display part is other parts of the initial character model except the expression display part, and the first deformation target is specifically the deformation target corresponding to the expression display part, that is, the deformation target of the expression model to be transmitted. In a specific application scenario, the deformation target may be a Blendshape in the Maya software (MAYA software is a famous 3D modeling and animation software under Autodesk), or may be a Morph in 3dsmax (3D Studio Max, often referred to as 3d Max or 3ds MAX, is a 3D animation rendering and production software based on PC system developed by Discreet (later merged by Autodesk)), and the deformation target can make the character model vertices displace according to the specified deformation target without binding bones.

[0020] In the above embodiment, taking the example that the initial character model includes an expression display part and a non-expression display part, in order to realize expression transmission, the first deformation target of the expression model to be transmitted is first added to the expression display part of the expressionless initial character model to obtain a first expression model. The first expression model is the initial character model carrying the expression corresponding to the first deformation target. At this time, the expression display part of the first expression model is accompanied by expression features, while the non-expression display part is still consistent with the expressionless initial character model.

[0021] Step 102, obtaining first boundary data corresponding to a first connection area of ​​the first expression model;

[0022] Next, since the expression display part in the first expression model is accompanied by the expression corresponding to the first deformation target, and the non-expression display part is still consistent with the expressionless initial character model, in some cases, such as when the expression display part is the head and neck, and the expression corresponding to the first deformation target includes neck deformation, if the model directly displays the expression, the neck may have a seam where it is connected to the body due to deformation. In order to determine whether there is a gap at the connection between the expression display part and the non-expression display part, resulting in an unrealistic effect when the character model displays the expression. Or in the case where the initial character model is a model of the expression display part, avoid the appearance of a gap at the connection between the initial character model and other models of the non-expression display part when the initial character model is combined with other models of the non-expression display part. In an embodiment of the present application, the first boundary data corresponding to the vicinity of the connection between the expression display part and the non-expression display part in the first expression model, that is, the first boundary data corresponding to the first connection area, is obtained. In the case where the expression display part is the head and neck, such as Figure 2As shown, the first connection area can be a circle connected to the body and close to the lower part of the neck, that is, the dark area in the figure. The first boundary data is specifically the boundary line generated by the character model under the deformation when making an expression. If there are multiple boundary lines at the same position corresponding to the first connection area, it means that the deformation target of the deformation target has moved at the connection.

[0023] Optionally, step 102 may specifically include: reversing the expression display part of the first expression model to obtain the first boundary data, and displaying the first boundary data in the form of a wireframe view, so that the model boundary corresponding to the expression display part of the first expression model is displayed in the form of lines.

[0024] In the above embodiment, the first boundary data can be obtained by performing a reverse operation on the first expression model, wherein the reverse operation specifically refers to copying each deformation target of the model as a separate model. After the boundary data is obtained by the reverse operation, the boundary lines of the first connection area can be displayed in the form of a wireframe view, such as Figure 3 As shown, it can be displayed in the form of a side view for easy observation. The reverse operation can be performed through the Maya Python script. First select the model to be reversed, and then run the script. The script function can be integrated into the expression workflow auxiliary toolkit. The script code can be as follows:

[0025]

[0026] Step 103, if the first boundary data indicates that the first connection area includes at least two boundaries, after setting the first connection area to a non-deformed state, the first expression model is reversed to obtain an intermediate expression model;

[0027] In the embodiment of the present application, if the same position corresponding to the first connection area contains two or more boundary lines, it means that some facial expressions drive the model boundary of the facial expression display part to move, which will produce an unrealistic seam with the non-expression display part. The same position can specifically refer to a model edge or a model face corresponding to the facial expression display part in the model. In actual application scenarios, after the first boundary data is displayed in a wireframe view, the tester can zoom in and observe to determine whether the human eye can see the seam when the character model generates facial expressions. The model boundary line can also be identified by intelligent recognition, for example, identifying whether the number of deformation target boundary lines (deformation target boundary lines refer to boundary lines corresponding to the first deformation target) at the same position whose distance from the boundary line of the character model itself is greater than a preset value is two or more. If it contains at least two boundaries, the first connection area is set to a non-deformed state, that is, the area is set to a vertex that is not affected by the change of the deformation target, and then the first expression model is reversed to obtain an intermediate expression model with a second deformation target, that is, the deformation target displacement of the first connection area in the first deformation target is erased to generate the second deformation target, and the deformation target that causes the expression display part and the non-expression display part to produce an unrealistic seam is removed.

[0028] Optionally, step 103 may specifically include: if the first boundary data indicates that the first connection area contains at least two boundaries, setting the deformation weight corresponding to the first connection area to 0, so that the first connection area is not affected by the deformation of the first deformation target; reversing the first expression model to obtain the intermediate expression model, wherein the second deformation target corresponding to the intermediate expression model does not include the deformation target corresponding to the first connection area.

[0029] In the above embodiment, taking Maya as an example, specifically, the blend deformation weight drawing tool can be opened, and the drawing operation of the drawing tool can be set to replace, and the value can be changed to 0, and then the reverse operation can be performed on the first expression model. After the reverse operation, all deformation targets of the model can be obtained, that is, the intermediate expression model with the second deformation target can be obtained.

[0030] Step 104, adding a second deformation target corresponding to the intermediate expression model to the initial character model without expression to obtain a second expression model.

[0031] Finally, the second deformation target of the intermediate expression model is reassigned to the expressionless initial character model to obtain the second expression model, so that when the final second expression model generates expression deformation based on the second deformation target, no seams will be generated between the expression display part and the non-expression display part, and the second expression model can display expressions more realistically. When the template expression is assigned to the new character model, not only can the template expression be basically retained, but also the expression display effect of the new character model can be guaranteed.

[0032] Optionally, step 104 may specifically include: adding a second deformation target corresponding to the intermediate expression model to the expressionless initial character model copy to obtain the intermediate expression model; or, after deleting the first deformation target of the first expression model, adding a second deformation target corresponding to the intermediate expression model to the expressionless initial character model to obtain the second expression model.

[0033] In the above embodiment, the expressionless initial character model can be copied to obtain the initial character model copy, and the second deformation target can be added to the initial character model copy to obtain the second expression model. Alternatively, the historical operation records in the first expression model can be deleted and restored to the expressionless character model, and then the second deformation target can be added to obtain the second expression model.

[0034] By applying the technical solution of this embodiment, when transferring expressions to the initial character model, the first deformation target corresponding to the expression model to be transferred is first added to the initial character model to obtain the first expression model. If the expression display part of the first expression model has multiple boundaries with the first connection area corresponding to the non-expression display part, the first connection area is set to a non-deformed state, and the first expression model is reversely operated to obtain an intermediate expression model with a second deformation target, so as to remove the vertex displacement of the first connection area in the deformation target of the original first expression model. Finally, the intermediate expression model is added as a deformation target to the expressionless initial character model to obtain the second expression model, so that there will be no seams in the connection area when the second expression model makes an expression. When transferring expressions to a new character model, the embodiment of the present application can verify the connection area between the expression display part and the non-expression display part, and if there are multiple boundaries in the connection area, the area is set to a non-deformed state and the model is reversed, so that the reverse result is added to the new expressionless character model, so that the final model has a real effect when making expressions and no seams are produced. At the same time, only the deformation target of the expression display part needs to be transferred, which ensures the efficiency of expression transmission.

[0035] In the embodiment of the present application, optionally, the following steps may also be included:

[0036] Step 105, obtaining second boundary data corresponding to the second connection area of ​​the second expression model;

[0037] Step 106, if the second boundary data indicates that the second connection area includes at least two boundaries, after setting the second connection area to an undeformed state, the second expression model is updated based on the inverse result of the second expression model and the expressionless initial character model until the second connection area corresponds to a boundary.

[0038] In the above embodiment, after the first deformation target is converted into the second deformation target and assigned to the expressionless initial character model, in order to ensure the expression display effect, the second expression model can be verified. Specifically, a method similar to the first expression model can be adopted to obtain the second boundary data corresponding to the second connection area between the expression display part and the non-expression display part in the second expression model, so as to determine whether the second connection area contains multiple boundaries based on the second boundary data. If it does, the second connection area is set to a non-deformed state, and the second expression model is reversed and the reverse result is assigned to the expressionless initial character model to obtain a new second expression model until the second connection area contains only one boundary at the same position.

[0039] Furthermore, the embodiment of the present application may further include the following steps, which are performed before step 101 or are performed separately, as follows:

[0040] Step 201, obtaining a third expression model and a fourth expression model, wherein the fourth expression model matches a model feature of the initial character model, the initial states of at least one model feature of the third expression model and the fourth expression model are different, and a deformation target corresponding to the fourth expression model is obtained by modifying a vertex position corresponding to the at least one model feature in the third expression model;

[0041] Step 202, adding the fourth expression model as a deformation target to the third expression model to obtain a fifth expression model;

[0042] Step 203, after setting the at least one model feature of the fifth expression model to a deformed state, reverse the expression display part corresponding to the fifth expression model to obtain the expression model to be transmitted, and the expression model to be transmitted corresponds to the first deformation target.

[0043] In the above embodiment, before transferring the template expression, the template expression can be made first. In the embodiment of the present application, the third expression model and the fourth expression model are two models with different initial states of at least one model feature. For example, the third expression model and the fourth expression model have different mouth features. The third expression model is an open-mouth model, and the fourth expression model is a closed-mouth model. Optionally, step 201 may specifically include: obtaining the third expression model; copying the third expression model, and adjusting the vertex position of at least one model feature corresponding to the third expression model to obtain the fourth expression model. Specifically, the third expression model may be copied to obtain the fourth expression model, and then the mouth may be closed without destroying the topological relationship. Specifically, the fourth expression model may be changed from an open mouth to a closed mouth by adjusting the vertex position of the model. Then, the fourth expression model is added to the third expression model as a deformation target, so that the closed-mouth expression model becomes a deformation target added to the open-mouth expression model, and a fifth expression model is obtained whose initial state is open-mouth and whose deformation target is closed-mouth. Finally, at least one of the above-mentioned model features is set to a deformation state. For example, the mouth closure value of the fifth expression model is set to 1, and the fifth expression model is reversed to obtain a first deformation target whose deformation target is closed-mouth. Then, the first deformation target is added to the fourth expression model. The open-mouth model animation can be changed to the closed-mouth model animation without the modeling personnel having to redraw the deformation target of the closed-mouth model. This is simple and convenient.

[0044] Further, as Figure 1 The specific implementation of the method, the embodiment of the present application provides a device for generating an expression model, such as Figure 4 As shown, the device comprises:

[0045] A first model generation module, used for adding a first deformation target corresponding to the expression model to be transferred to the initial character model to obtain a first expression model, wherein the initial character model is an expressionless model;

[0046] A boundary data acquisition module, used to acquire first boundary data corresponding to a first connection area of ​​the first expression model;

[0047] a first animation exporting module, configured to, if the first boundary data indicates that the first connection area includes at least two boundaries, set the first connection area to a non-deformed state, and then reverse the first expression model to obtain an intermediate expression model;

[0048] The second model generation module is used to add a second deformation target corresponding to the intermediate expression model to the initial character model without expression to obtain a second expression model.

[0049] Optionally, the boundary data acquisition module is specifically used to: reverse the expression display part of the first expression model to obtain the first boundary data, and display the first boundary data in the form of a wireframe view, so that the model boundary corresponding to the expression display part of the first expression model is displayed in the form of lines.

[0050] Optionally, the first animation export module is specifically used to: set the deformation weight corresponding to the first connection area to 0, so that the first connection area is not affected by the deformation of the first deformation target; reverse the first expression model to obtain the intermediate expression model, wherein the second deformation target corresponding to the intermediate expression model does not include the deformation target corresponding to the first connection area.

[0051] Optionally, the second model generation module is specifically used to: add a second deformation target corresponding to the intermediate expression model to the copy of the expressionless initial character model to obtain the intermediate expression model; or, after deleting the first deformation target of the first expression model, add a second deformation target corresponding to the intermediate expression model to the expressionless initial character model to obtain the second expression model.

[0052] Optionally, the device further comprises:

[0053] A verification module is used to add a second deformation target corresponding to the intermediate expression model to the expressionless initial character model, and after obtaining the second expression model, obtain second boundary data corresponding to the second connection area of ​​the second expression model; if the second boundary data indicates that the second connection area contains at least two boundaries, then after setting the second connection area to a non-deformed state, the second expression model is updated based on the inverse result of the second expression model and the expressionless initial character model until the second connection area corresponds to a boundary.

[0054] Optionally, the device further comprises:

[0055] The second animation export module is used for adding the first deformation target corresponding to the expression model to be transmitted to the initial character model, and obtaining the third expression model and the fourth expression model before obtaining the first expression model, wherein the fourth expression model matches the model feature of the initial character model, the initial states of at least one model feature of the third expression model and the fourth expression model are different, and the deformation target corresponding to the fourth expression model is obtained by modifying the vertex position corresponding to the at least one model feature in the third expression model; adding the fourth expression model as the deformation target to the third expression model to obtain the fifth expression model; after setting the at least one model feature of the fifth expression model to the deformation state, reversing the expression display part corresponding to the fifth expression model to obtain the expression model to be transmitted, and the expression model to be transmitted corresponds to the first deformation target.

[0056] It should be noted that for other corresponding descriptions of the functional units involved in the device for generating an expression model provided in the embodiment of the present application, reference can be made to Figure 1 The corresponding description in the method will not be repeated here.

[0057] Based on the above Figure 1 The method shown in the embodiment of the present application is accordingly provided with a storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above-mentioned Figure 1 The method for generating the expression model shown.

[0058] Based on this understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each implementation scenario of the present application.

[0059] Based on the above Figure 1 The method shown, and Figure 4 In order to achieve the above-mentioned purpose, the embodiment of the present application further provides a computer device, which can be a personal computer, a server, a network device, etc. The computer device includes a storage medium and a processor; the storage medium is used to store a computer program; the processor is used to execute the computer program to achieve the above-mentioned Figure 1 The method for generating the expression model shown.

[0060] Optionally, the computer device may further include a user interface, a network interface, a camera, a radio frequency (RF) circuit, a sensor, an audio circuit, a WI-FI module, etc. The user interface may include a display, an input unit such as a keyboard, etc., and the optional user interface may also include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (such as a Bluetooth interface, a WI-FI interface), etc.

[0061] Those skilled in the art will appreciate that the computer device structure provided in this embodiment does not limit the computer device, and may include more or fewer components, or a combination of certain components, or different component arrangements.

[0062] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages and saves the hardware and software resources of the computer device, and supports the operation of information processing programs and other software and / or programs. The network communication module is used to realize communication between the components inside the storage medium, and communication with other hardware and software in the physical device.

[0063] Through the description of the above implementation methods, technical personnel in this field can clearly understand that the present application can be implemented by means of software plus necessary general hardware platforms, and can also be implemented by hardware. When transferring expressions to the initial character model, first add the first deformation target corresponding to the expression model to be transferred to the initial character model to obtain the first expression model. If the expression display part of the first expression model and the first connection area corresponding to the non-expression display part have multiple boundaries, then after setting the first connection area to a non-deformed state, the first expression model is reversely operated to obtain an intermediate expression model with a second deformation target, so as to remove the vertex displacement of the first connection area in the deformation target of the original first expression model. Finally, the intermediate expression model is added as a deformation target to the expressionless initial character model to obtain the second expression model, so that there will be no seams in the connection area when the second expression model makes an expression. When transferring expressions to a new character model, the embodiment of the present application can verify the connection area between the expression display part and the non-expression display part, and if there are multiple boundaries in the connection area, set the area to a non-deformed state and perform a model inverse operation, thereby adding the inverse result to the new expressionless character model, so that the final model has a realistic and seamless effect when making expressions. At the same time, only the deformation target of the expression display part needs to be transferred, thereby ensuring the efficiency of expression transmission.

[0064] Those skilled in the art will appreciate that the accompanying drawings are only schematic diagrams of a preferred implementation scenario, and the modules or processes in the accompanying drawings are not necessarily necessary for implementing the present application. Those skilled in the art will appreciate that the modules in the devices in the implementation scenario can be distributed in the devices of the implementation scenario according to the description of the implementation scenario, or can be changed accordingly and located in one or more devices different from the present implementation scenario. The modules of the above-mentioned implementation scenario can be combined into one module, or can be further split into multiple submodules.

[0065] The above serial numbers of this application are only for description and do not represent the advantages and disadvantages of the implementation scenarios. The above disclosure is only a few specific implementation scenarios of this application, but this application is not limited to them, and any changes that can be thought of by technicians in this field should fall within the scope of protection of this application.

Claims

1. A method for generating an expression model, It is characterized in that include: Adding a first deformation target corresponding to the expression model to be transferred to the initial character model to obtain a first expression model, wherein the initial character model is an expressionless model including an expression display part and a non-expression display part; Acquire first boundary data corresponding to a first connection area of ​​the first expression model, where the first connection area corresponds to a connection area between an expression display part and a non-expression display part of the first expression model; If the first boundary data indicates that the first connection area includes at least two boundaries, after setting the first connection area to a non-deformed state, the first expression model is reversed to obtain an intermediate expression model; Adding a second deformation target corresponding to the intermediate expression model to the initial character model to obtain a second expression model, wherein the second deformation target is all deformation targets in the first expression model except the deformation target corresponding to the first connection area; Obtain second boundary data corresponding to a second connection area of ​​the second expression model, where the second connection area corresponds to a connection area between an expression display part and a non-expression display part of the second expression model; if the second boundary data indicates that the second connection area includes at least two boundaries, then after setting the second connection area to a non-deformed state, update the second expression model based on a reverse result of the second expression model and the initial character model until the second connection area corresponds to a boundary.

2. The method according to claim 1, It is characterized in that The obtaining of first boundary data corresponding to the first connection area of ​​the first expression model specifically includes: The expression display part of the first expression model is reversed to obtain the first boundary data, and the first boundary data is displayed in the form of a wireframe view, so that the model boundary corresponding to the expression display part of the first expression model is displayed in the form of lines.

3. The method according to claim 1, It is characterized in that After setting the first connection area to a non-deformed state, the first expression model is reversed to obtain an intermediate expression model, specifically comprising: Setting the deformation weight corresponding to the first connection area to 0, so that the first connection area is not affected by the deformation of the first deformation target; The first expression model is reversed to obtain the intermediate expression model.

4. The method according to claim 1, It is characterized in that The step of adding the second deformation target corresponding to the intermediate expression model to the initial character model to obtain the second expression model specifically includes: adding a second deformation target corresponding to the intermediate expression model to a copy of the initial character model to obtain the intermediate expression model; or, After deleting the first deformation target of the first expression model, adding the second deformation target corresponding to the intermediate expression model to the initial character model to obtain the second expression model.

5. The method according to any one of claims 1 to 4, It is characterized in that Before adding the first deformation target corresponding to the expression model to be transferred to the initial character model to obtain the first expression model, the method further includes: Acquire a third expression model and a fourth expression model, wherein the fourth expression model matches a model feature of the initial character model, the initial states of at least one model feature of the third expression model and the fourth expression model are different, and a deformation target corresponding to the fourth expression model is obtained by modifying a vertex position corresponding to the at least one model feature in the third expression model; adding the fourth expression model as a deformation target to the third expression model to obtain a fifth expression model; After setting the at least one model feature of the fifth expression model to a deformed state, the expression display part corresponding to the fifth expression model is reversed to obtain the expression model to be transmitted, and the expression model to be transmitted corresponds to the first deformation target.

6. A device for generating an expression model, It is characterized in that include: A first model generation module is used to add a first deformation target corresponding to the expression model to be transferred to the initial character model to obtain a first expression model, wherein the initial character model is an expressionless model including an expression display part and a non-expression display part; A boundary data acquisition module, used to acquire first boundary data corresponding to a first connection area of ​​the first expression model, wherein the first connection area corresponds to a connection area between an expression display part and a non-expression display part of the first expression model; a first animation exporting module, configured to, if the first boundary data indicates that the first connection area includes at least two boundaries, set the first connection area to a non-deformed state, and then reverse the first expression model to obtain an intermediate expression model; A second model generation module, configured to add a second deformation target corresponding to the intermediate expression model to the initial character model to obtain a second expression model, wherein the second deformation target is all deformation targets in the first expression model except the deformation target corresponding to the first connection area; A verification module is used to obtain second boundary data corresponding to a second connection area of ​​the second expression model, where the second connection area corresponds to a connection area between an expression display part and a non-expression display part of the second expression model; if the second boundary data indicates that the second connection area contains at least two boundaries, then after setting the second connection area to a non-deformed state, the second expression model is updated based on a reverse result of the second expression model and the initial character model until the second connection area corresponds to a boundary.

7. The device according to claim 6, It is characterized in that The boundary data acquisition module is specifically used to: reverse the expression display part of the first expression model to obtain the first boundary data, and display the first boundary data in the form of a wireframe view, so that the model boundary corresponding to the expression display part of the first expression model is displayed in the form of lines.

8. A storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the method for generating an expression model according to any one of claims 1 to 5 is implemented.

9. A computer device comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, It is characterized in that When the processor executes the computer program, the method for generating an expression model according to any one of claims 1 to 5 is implemented.

Images