Model expression redirection method and device, storage medium and electronic device

Abstract

The present disclosure relates to a model expression redirection method and device, storage medium and electronic equipment, and relates to the technical field of computers. The method comprises: obtaining a first linkage controller corresponding to a first linkage expression skeleton and a first secondary controller corresponding to a first secondary expression skeleton; creating a connection relationship between the first linkage controller and the first secondary controller, and calculating a mixing weight required for redirecting a first model expression from a first face model to a second face model according to the first secondary controller; calculating a constraint intermediate group required for redirecting the first model expression to the second face model based on the connection relationship, the mixing weight and the first secondary controller; generating a target skeleton based on the constraint intermediate group, and performing skin processing on the second face model according to the target skeleton to obtain a second model expression corresponding to the first model expression on the second face model. The present disclosure improves the redirection efficiency of model expressions.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and more specifically, to a method for redirecting model facial expressions, a device for redirecting model facial expressions, a computer-readable storage medium, and an electronic device. Background Technology

[0002] Virtual scenarios transcend the limitations of real life. Virtual characters exist within these scenarios, and these characters can possess various facial expressions to convey different emotions and meanings. Different virtual characters may use the same expressions, including joy, anger, and others.

[0003] The current approach involves complex skeletal binding operations to create facial expressions for a model. When other models also need to achieve the same expressions, the existing bindings must be deleted and re-bound.

[0004] However, the above solution has the following drawbacks: because it is necessary to delete the existing binding relationships in the newly added face model, the efficiency of model expression redirection is relatively low.

[0005] It should be noted that the information in the background section above is only used to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0006] The purpose of this disclosure is to provide a method, apparatus, computer-readable storage medium, and electronic device for redirecting model expressions, thereby overcoming, to at least some extent, the problem of low efficiency in redirecting model expressions due to limitations and defects in related technologies.

[0007] According to one aspect of this disclosure, a method for retargeting model facial expressions is provided, comprising:

[0008] Obtain the first linked expression bone and the first primary expression bone included in the first model expression of the first face model, and obtain the first linkage controller corresponding to the first linked expression bone and the first primary controller corresponding to the first primary expression bone;

[0009] Create a connection between the first linkage controller and the first primary controller, and calculate the blending weights required to redirect the first model expression from the first face model to the second face model based on the first primary controller;

[0010] Based on the connection relationship, the mixed weights, and the first-level controller, calculate the constraint intermediate set required to redirect the expression of the first model to the second face model;

[0011] Based on the constraint intermediate group, a target skeleton is generated, and the second face model is skinned according to the target skeleton, so that a second model expression corresponding to the expression of the first model can be obtained on the second face model.

[0012] In one exemplary embodiment of this disclosure, the calculation of the blending weights required to redirect the first model expression from the first face model to the second face model, based on the first-level controller, includes:

[0013] The first matrix information and the first level information included in the first-level controller are obtained; wherein, the first matrix information is used to characterize the movement and / or rotation of the first-level facial expression bone relative to the first linked facial expression bone, and the first level information is used to characterize the level of the first-level facial expression bone on the first face model.

[0014] Based on the first matrix information and the first level information, calculate the mixing weights required to redirect the first model expression from the first face model to the second face model.

[0015] In one exemplary embodiment of this disclosure, based on the connectivity, the hybrid weights, and the first-level controller, the calculation of the constraint intermediate set required to redirect the first model expression to the second face model includes:

[0016] Based on the connection relationship, the connection method between the first linked facial expression bone and the first primary facial expression bone is determined, and according to the connection method and the hybrid weight, the first target displacement information of the displacement level included in the first primary controller is determined;

[0017] A first attribute connection is established between the first target displacement information and the current displacement information to obtain the second target displacement information; wherein, the current displacement information is the displacement information included in the current constraint transmission process;

[0018] A second attribute connection is established between the first target position reverse information, the first target control information, and the current connection information to obtain target connection information; wherein, the first target position reverse information is the position reverse information of the position reverse layer included in the first-level controller, and the first target control information is the control information of the control layer included in the first-level controller;

[0019] Based on the second target displacement information and target connection information, the constraint intermediate group required to redirect the expression of the first model to the second face model is obtained.

[0020] In one exemplary embodiment of this disclosure, establishing a first attribute connection between the first target displacement information and the current displacement information to obtain second target displacement information includes:

[0021] Based on the first attribute connection, the first target displacement value of the first target displacement information is obtained, and the current displacement value including the current displacement information in the current constraint transmission intermediate group is replaced based on the first target displacement value to obtain the second target displacement information.

[0022] In one exemplary embodiment of this disclosure, a second attribute connection is established between the first target location reverse information and the first target control information and the current connection information to obtain target connection information, including:

[0023] Based on the second attribute connection, the first target position reversal information of the position reversal layer and the first target control information of the control layer included in the first primary controller are obtained;

[0024] Based on the first target position reverse information and the first target control information, the current connection information included in the current skin connection layer included in the current constraint transmission intermediate group is replaced to obtain the target connection information.

[0025] In one exemplary embodiment of this disclosure, generating a target skeleton based on the constraint intermediate set includes:

[0026] Based on the first linked expression bone and the first secondary expression bone, obtain the second linked expression bone and the second secondary expression bone required to generate the second model expression corresponding to the expression of the first model on the second face model;

[0027] Based on the aforementioned constraint intermediate group, parent-child constraints and / or scaling constraints are applied to the second linked facial expression bone and the second-level facial expression bone to obtain the target bone.

[0028] In one exemplary embodiment of this disclosure, skinning the second facial model based on the target skeleton allows for obtaining a second facial expression corresponding to the expression of the first model, including:

[0029] Based on the target skeleton, the first linkage controller, and the first primary controller, generate the skeletal topology required to generate the second model expression corresponding to the expression of the first model on the second face model;

[0030] The target skeleton is bound to the second face model, and based on the skeleton topology, the zeroth linkage control layer of the first linkage controller and the zeroth secondary control layer of the first primary controller are moved to a preset position corresponding to the second face model, thereby controlling the generation of a second model expression on the second face model that corresponds to the expression of the first model.

[0031] In one exemplary embodiment of this disclosure, obtaining the first linked expression bone and the first primary expression bone included in the first model expression of the first facial model, and obtaining the first linkage controller corresponding to the first linked expression bone and the first primary controller corresponding to the first primary expression bone, includes:

[0032] Based on historical facial models, basic facial expression skeletons and baseline facial expression groups are constructed. Then, based on the mesh lines of the basic facial expression skeletons and baseline facial expression groups, the standard linked facial expression skeletons and standard secondary skeletons required to generate the standard virtual facial expressions included in the baseline facial expression groups are calculated.

[0033] Configure a standard linkage controller for the standard linked facial expression skeleton and configure a standard secondary controller for the standard secondary skeleton; wherein, each standard linked facial expression skeleton corresponds to one standard linkage controller, each standard secondary skeleton corresponds to one standard secondary controller, and one standard linkage controller corresponds to one or more standard secondary controllers.

[0034] Establish a first association between the standard virtual expression and the standard linked expression skeleton, a second association between the standard virtual expression and the standard secondary skeleton, and establish a third association between the standard linked expression skeleton and the standard linked controller, and establish a fourth association between the standard secondary skeleton and the standard secondary controller;

[0035] Based on the first and second association relationships, the first linked expression skeleton and the first primary expression skeleton included in the first model expression are obtained, and based on the third and fourth association relationships, the first linkage controller corresponding to the first linked expression skeleton and the first primary controller corresponding to the first primary expression skeleton are obtained.

[0036] In one exemplary embodiment of this disclosure, a basic facial expression skeleton is constructed based on the historical facial model, including:

[0037] A real face image is acquired, and the real face image is processed based on a preset face image processing model to obtain the first position information of the facial bone feature points included in the real face image;

[0038] Based on the first position information of the facial bone feature points, obtain the model bone feature points corresponding to the historical facial model corresponding to the facial bone feature points;

[0039] The basic facial expression skeleton is constructed based on the second position information of the model's skeletal feature points.

[0040] According to one aspect of this disclosure, a model facial expression redirection device is provided, comprising:

[0041] The facial expression bone acquisition module is used to acquire the first linked facial expression bone and the first primary facial expression bone included in the first model expression of the first face model, and to acquire the first linkage controller corresponding to the first linked facial expression bone and the first primary controller corresponding to the first primary facial expression bone.

[0042] The hybrid weight calculation module is used to create a connection relationship between the first linkage controller and the first primary controller, and to calculate the hybrid weights required to redirect the first model expression from the first face model to the second face model based on the first primary controller.

[0043] The constraint intermediate group calculation module is used to calculate the constraint intermediate group required to redirect the expression of the first model to the second face model based on the connection relationship, the mixed weight and the first-level controller.

[0044] The model expression retargeting module is used to generate a target skeleton based on the constraint intermediate group, and to perform skinning processing on the second face model according to the target skeleton, so as to obtain a second model expression corresponding to the expression of the first model on the second face model.

[0045] According to one aspect of this disclosure, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the method for redirecting model facial expressions as described in any of the preceding claims.

[0046] According to one aspect of this disclosure, an electronic device is provided, comprising:

[0047] Processor; and

[0048] Memory for storing the executable instructions of the processor;

[0049] The processor is configured to execute the model expression redirection method described above by executing the executable instructions.

[0050] This disclosure provides a method for redirecting model expressions. On one hand, it can obtain the first linked expression bone and the first-level expression bone included in the first model expression of the first face model, and obtain the first linkage controller and the first-level controller corresponding to the first linked expression bone; then, it can create a connection relationship between the first linkage controller and the first-level controller, and calculate the mixing weight required to redirect the first model expression from the first face model to the second face model based on the first-level controller; then, based on the connection relationship, the mixing weight, and the first-level controller, it can calculate the constraint intermediate group required to redirect the first model expression to the second face model; finally, it can generate a target bone based on the constraint intermediate group, and perform skinning processing on the second face model based on the target bone to obtain a second model expression corresponding to the first model expression on the second face model. This solves the problem of low model expression redirection efficiency in the prior art due to the need to delete existing binding relationships in the newly added face model, and improves the model expression redirection efficiency. On the other hand, it can also solve the problem of loss of existing expression information due to the need to delete existing binding relationships.

[0051] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0052] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0053] Figure 1 The flowchart schematically illustrates a method for redirecting model facial expressions according to an exemplary embodiment of the present disclosure.

[0054] Figure 2 A schematic diagram illustrating a constraint according to an example embodiment of the present disclosure is shown.

[0055] Figure 3 The schematic diagram illustrates a property connection according to an example embodiment of the present disclosure.

[0056] Figure 4 The flowchart illustrates a method for acquiring an expression skeleton and a controller according to an exemplary embodiment of the present disclosure.

[0057] Figure 5 An example facial diagram illustrating a basic facial expression skeleton according to an exemplary embodiment of the present disclosure is shown schematically.

[0058] Figure 6 The diagram schematically illustrates a hierarchical example of a standard linkage controller configured for a standard linked facial expression skeleton according to an exemplary embodiment of the present disclosure.

[0059] Figure 7 The illustration schematically shows an example face of a standard linkage controller configured for each standard linked facial bone according to an example embodiment of the present disclosure.

[0060] Figure 8 The diagram schematically illustrates a hierarchical example of a standard secondary controller configured for a standard secondary skeleton according to an example embodiment of the present disclosure.

[0061] Figure 9 The illustration schematically depicts an example face of a standard secondary controller configured for each standard secondary skeleton according to an example embodiment of the present disclosure.

[0062] Figure 10 The diagram illustrates a scenario example of a specific calculation process for a constraint intermediate group according to an exemplary embodiment of the present disclosure.

[0063] Figure 11 A block diagram schematically illustrates a model facial expression redirection device according to an exemplary embodiment of the present disclosure.

[0064] Figure 12 An electronic device for implementing the above-described method for redirecting model facial expressions, according to an example embodiment of the present disclosure, is illustrated schematically. Detailed Implementation

[0065] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this disclosure more comprehensive and complete, and to fully convey the concept of the example embodiments to those skilled in the art. The described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a full understanding of embodiments of this disclosure. However, those skilled in the art will recognize that the technical solutions of this disclosure can be practiced with one or more of the specific details omitted, or other methods, components, apparatus, steps, etc., can be employed. In other instances, well-known technical solutions are not shown or described in detail to avoid obscuring various aspects of this disclosure.

[0066] Furthermore, the accompanying drawings are merely illustrative of this disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0067] Redirecting facial expressions requires precisely redirecting all expressions from an existing character's facial model to another character with different facial features and topology. In practical applications, the following problems arise: Firstly, because the facial features of the two characters are different, precise redirection cannot be achieved solely through deformers; secondly, because the topology of the two facial models is also different, direct deformation is not possible. To solve this problem, the rigging system can be reconstructed based on bone positions, thereby achieving facial expression redirection.

[0068] However, the above solution has the following drawbacks: On the one hand, the above expression retargeting solution will delete the binding files in the scene and then regenerate the binding files using the preserved bones. This method will cause the loss of previous custom modifications, such as newly added bone nodes, attribute connections, constraints, etc. On the other hand, due to the limitations of the software itself, this rapid automated operation may cause software crashes, file errors, and other problems.

[0069] Based on this, this exemplary embodiment first provides a method for redirecting model facial expressions. This method can run on terminal devices, servers, server clusters, or cloud servers, including those using the Maya engine. Of course, those skilled in the art can also run the method disclosed herein on other platforms as needed, and this exemplary embodiment does not impose any special limitations on this. Specifically, refer to... Figure 1 As shown, the method for redirecting facial expressions in this model may include the following steps:

[0070] Step S110. Obtain the first linked expression bone and the first primary expression bone included in the first model expression of the first face model, and obtain the first linkage controller corresponding to the first linked expression bone and the first primary controller corresponding to the first primary expression bone;

[0071] Step S120. Create a connection relationship between the first linkage controller and the first primary controller, and calculate the blending weights required to redirect the first model expression from the first face model to the second face model according to the first primary controller;

[0072] Step S130. Based on the connection relationship, the mixed weights, and the first-level controller, calculate the constraint intermediate group required to redirect the expression of the first model to the second face model;

[0073] Step S140. Generate a target skeleton based on the constraint intermediate group, and perform skinning processing on the second face model according to the target skeleton, so that a second model expression corresponding to the expression of the first model can be obtained on the second face model.

[0074] In the aforementioned method for redirecting model expressions, on the one hand, it can obtain the first linked expression bone and the first-level expression bone included in the first model expression of the first face model, and obtain the first linkage controller corresponding to the first linked expression bone and the first-level controller corresponding to the first-level expression bone; then, it can create a connection relationship between the first linkage controller and the first-level controller, and calculate the mixing weights required to redirect the first model expression from the first face model to the second face model based on the first-level controller; then, based on the connection relationship, the mixing weights, and the first-level controller, it can calculate the constraint intermediate group required to redirect the first model expression to the second face model; finally, it can generate the target bone based on the constraint intermediate group, and perform skinning processing on the second face model based on the target bone, so as to obtain the second model expression corresponding to the first model expression on the second face model. Without deleting the existing binding relationship, the second model expression corresponding to the first model expression can be generated on the second face model, which solves the problem of low model expression redirection efficiency in the prior art due to the need to delete the existing binding relationship in the newly added face model, and improves the model expression redirection efficiency; on the other hand, it can also solve the problem of loss of existing expression information due to the need to delete the existing binding relationship.

[0075] The following will provide a detailed explanation and description of the model facial expression redirection method of the present disclosure in conjunction with the accompanying drawings.

[0076] First, the terms used in the exemplary embodiments of this disclosure will be explained.

[0077] Constraints: In DCC (Digital Content Creation) software, constraints are a control method that links objects through matrices. Constraint attributes include translation, rotation, and scaling. In practical applications, if there is a constraint relationship between object A and object B (e.g., A constrains B or B is constrained by A), when object A undergoes a transformation based on the world matrix, object B will undergo a corresponding matrix transformation based on the constrained attributes. In scenarios involving retargeting model expressions, character rigging typically only constrains translation and rotation. For a detailed schematic diagram, please refer to [reference needed]. Figure 2 As shown;

[0078] Attribute Connection: If nodes M and N are attribute-connected, the values ​​between nodes M and N can be directly substituted (i.e., the attribute value of node N can be replaced by the attribute value of node M). In actual binding scenarios, when two transform nodes are connected, the specific application principle is similar to that of constraints; that is, constraints can be seen as the world matrix of an object being converted into translation and rotation values ​​and then connected, and will be affected by the parent object; while the attribute connection of transform nodes is only affected by the object itself, and the linked object will not be affected when the parent object moves; for a specific example diagram, please refer to... Figure 3 As shown.

[0079] Controllers: These are intermediaries that can be used to indirectly control bones. By binding controllers to bones, animators can quickly achieve the animation effects they want.

[0080] Driving keyframes: Another application of animation curve nodes, where the time of the input node is changed to a custom attribute, and the changes in the object's attributes are controlled by controlling the custom attribute.

[0081] Secondly, in the model expression redirection method described in the exemplary embodiments of this disclosure:

[0082] In step S110, the first linked expression bone and the first primary expression bone included in the first model expression of the first face model are obtained, and the first linkage controller corresponding to the first linked expression bone and the first primary controller corresponding to the first primary expression bone are obtained.

[0083] In this example embodiment, reference Figure 4 As shown, obtaining the first linked expression bone and the first primary expression bone included in the first model expression of the first facial model, and obtaining the first linkage controller corresponding to the first linked expression bone and the first primary controller corresponding to the first primary expression bone, may include the following steps:

[0084] Step S410: Construct basic facial expression skeletons and baseline facial expression groups based on historical facial models, and calculate and generate standard linked facial expression skeletons and standard secondary skeletons required for the standard virtual expressions included in the baseline facial expression groups according to the mesh lines of the basic facial expression skeletons and baseline facial expression groups.

[0085] In this example embodiment, firstly, a basic expression skeleton is constructed based on the historical face model. Specifically, this can be achieved as follows: First, a real face image is acquired, and the real face image is processed based on a preset face image processing model to obtain the first position information of the facial bone feature points included in the real face image; secondly, based on the first position information of the facial bone feature points, model bone feature points corresponding to the historical face model corresponding to the facial bone feature points are obtained; then, based on the second position information of the model bone feature points, the basic expression skeleton is constructed. That is, in practical applications, the basic expression skeleton can be determined by the bone points included in the real face image; wherein, the obtained basic expression skeleton can be referenced... Figure 5 As shown; further, in the method of obtaining the skeletal points included in a real face image, it can be implemented by a corresponding face image processing model; wherein, the face image processing model described herein may include convolutional neural network model, recurrent neural network model and deep neural network model, etc., and this example does not impose any special restrictions on it.

[0086] Secondly, a baseline expression set is constructed based on historical facial models. Specifically, real facial expressions can be obtained, and a real facial expression set can be constructed based on these real facial expressions. Then, a baseline expression set corresponding to the historical facial model can be generated based on the real facial expression set.

[0087] Furthermore, based on the mesh lines of the basic facial expression bones and the baseline facial expression group, the standard linked facial expression bones and standard secondary bones required for the standard virtual expressions included in the baseline facial expression group are calculated and generated. Specifically, in practical applications, the historical facial model can first be meshed to obtain multiple meshes. Then, based on the mesh to which each basic facial expression bone belongs and the mesh lines of the baseline facial expression group, the basic facial expression bones required for each standard virtual expression are determined, and subsequently, the standard linked facial expression bones and standard secondary bones required for each standard virtual expression are determined.

[0088] Step S420: Configure a standard linkage controller for the standard linked facial expression skeleton and configure a standard secondary controller for the standard secondary skeleton; wherein, each standard linked facial expression skeleton corresponds to one standard linkage controller, each standard secondary skeleton corresponds to one standard secondary controller, and one standard linkage controller corresponds to one or more standard secondary controllers.

[0089] Specifically, firstly, a standard linkage controller is configured for the standard linked facial expression skeleton; among which, reference Figure 6As shown, the standard linkage controller may include the following control layers: the zero linkage control layer: rt_brown_inn_ctrl_zero, the first reverse control layer: rt_brown_inn_ctrl_rivet, the second offset control layer: rt_brown_inn_ctrl_offset, the third rotation control layer: rt_brown_inn_ctrl_poivt, the fourth local control layer: rt_brown_inn_ctrl_local, the fifth identifier control layer: rt_brown_inn_ctrl0Id, the sixth neck control layer: rt_brown_inn_ctrl_neg, the seventh global control layer: rt_brown_inn_ctrl_local0Zero, and the eighth internal control layer: rt_brown_inn_ctrl.

[0090] In one example embodiment, the standard linkage controller configured for each standard linked facial expression skeleton can be found in [reference needed]. Figure 7 As shown. For details, please refer to... Figure 7 As shown, the standard linkage controller may include a standard linkage controller for the forehead bones, a standard linkage controller for the eye bones, a standard linkage controller for the nose bones, a standard linkage controller for the mouth bones, and a standard linkage controller for the chin bones.

[0091] Secondly, a standard secondary controller is configured for the standard secondary skeleton; among which, reference Figure 8 As shown, the standard secondary controller may include the following control layers: Zero secondary control layer: rt_Orbit_01_Sec_ctrl_zero, First displacement control layer: rt_Orbit_01_Sec_ctrl_movement, Second reverse control layer: rt_Orbit_01_Sec_ctrl_rivet, Third rotation control layer: rt_Orbit_01_Sec_ctrl_poivt, Fourth local control layer: rt_Orbit_01_Sec_ctrl_local, Fifth identifier control layer: rt_Orbit_01_Sec_ctrl_ctrl0ld, Sixth neck control layer: rt_Orbit_01_Sec_ctrl_neg, Seventh global control layer: rt_Orbit_01_Sec_ctrl_local0Zero, Eighth secondary control layer: rt_Orbit_01_Sec_ctrl, Ninth world matrix information layer: rt_Orbit_01_Sec_ctrl_matrix, and Tenth expression position information layer: rt_Orbit_01_Sec_ctrl_sdk.

[0092] In one example embodiment, the standard secondary controllers configured for each standard secondary skeleton can be specifically referred to... Figure 9 As shown. For details, please refer to... Figure 9 As shown, the standard secondary skeleton may include a standard secondary controller for the forehead skeleton, a standard secondary controller for the eye skeleton, a standard secondary controller for the nose skeleton, a standard secondary controller for the ear skeleton, a standard secondary controller for the mouth skeleton, and a standard secondary controller for the chin skeleton.

[0093] It should be noted that in practical applications, each standard linked facial expression skeleton corresponds to one standard linked controller, each standard secondary skeleton corresponds to one standard secondary controller, and one standard linked controller corresponds to one or more standard secondary controllers. That is, one standard linked controller can control one or more standard secondary controllers, and one standard virtual expression can correspond to one or more standard linked controllers. The specific standard linked controllers and standard secondary controllers required for each standard virtual expression can be determined based on the actual standard linked facial expression skeletons and / or standard secondary skeletons required to complete the standard virtual expression. This example does not impose any special restrictions on this.

[0094] Step S430: Establish a first association relationship between the standard virtual expression and the standard linked expression skeleton, a second association relationship between the standard virtual expression and the standard secondary skeleton, a third association relationship between the standard linked expression skeleton and the standard linked controller, and a fourth association relationship between the standard secondary skeleton and the standard secondary controller.

[0095] Specifically, in order to obtain the standard linked facial expression skeleton, standard secondary skeleton, standard linked controller, and standard secondary controller in a timely manner, corresponding associations can be established, and then the standard virtual expression, standard linked facial expression skeleton, standard secondary skeleton, standard linked controller, and standard secondary controller can be stored based on these associations.

[0096] Step S440: Based on the first association relationship and the second association relationship, obtain the first linked expression bone and the target secondary expression bone included in the first model expression, and based on the third association relationship and the fourth association relationship, obtain the first linkage controller corresponding to the first linked expression bone and the first secondary controller corresponding to the first secondary expression bone.

[0097] At this point, the first linkage controller and the first primary controller required to control the expression of the first model have all been acquired.

[0098] In step S120, a connection relationship is created between the first linkage controller and the first primary controller, and the mixing weights required to redirect the first model expression from the first face model to the second face model are calculated based on the first primary controller.

[0099] In this example embodiment, firstly, refer to Figure 10 As shown, a connection relationship is created between the first linkage controller and the first secondary controller. The connection relationship described here can be implemented using a bridge relationship. This bridge relationship can be used to add custom attributes, which can be used to drive keyframes. Custom attributes can include the first linkage facial skeleton, the first secondary facial skeleton, attribute connection information, and constraint information, etc.

[0100] Secondly, based on the secondary first-level controller, the blending weights required to redirect the first model expression from the first face model to the second face model are determined. Specifically, this can be achieved as follows: First, obtain the first matrix information and first level information included in the primary first-level controller; wherein, the first matrix information is used to characterize the movement and / or rotation of the primary first-level expression bone relative to the first linked expression bone, and the first level information is used to characterize the level of the primary first-level expression bone on the first face model; secondly, based on the first matrix information and the first level information, calculate the blending weights required to redirect the first model expression from the first face model to the second face model. (Continue to refer to...) Figure 10 As shown, the mixing weights required to redirect the first face model to the second face model can be determined based on the sec_ctrl_matrix and sec_ctrl_sdk included in the first-level control. That is, the mixing weights include first matrix information used to characterize the first-level skeletal expression response to the movement and / or rotation information of the first linked expression bone, and first level information used to characterize the hierarchical position of the first-level expression bone on the first face model. This facilitates the determination of the curve transformation basis required for the corresponding bones in the second face model based on the first matrix information and the first level information during the process of redirecting the first model expression to the second face model, thereby improving the accuracy of the obtained second model expression. In other words, it allows the first model expression to be generated in a way that fits the specific model structure of the second face model, making the second model expression smoother and more natural, and avoiding the problem of the second model expression being not smooth or having a poor appearance due to inaccurate curve transformation.

[0101] In step S130, based on the connection relationship, the mixed weights, and the first-level controller, the constraint intermediate group required to redirect the expression of the first model to the second face model is calculated.

[0102] In this example embodiment, based on the connection relationship, the hybrid weights, and the first-level controller, the constraint intermediate group required to redirect the first model expression to the second face model can be calculated as follows: First, based on the connection relationship, the connection method between the first linked expression skeleton and the first-level expression skeleton is determined, and according to the connection method and the hybrid weights, the first target displacement information of the displacement level included in the first-level controller is determined; second, a first attribute connection is established between the first target displacement information and the current displacement information to obtain the second target displacement information; wherein, the current displacement information is the displacement information included in the current constraint transfer intermediate; then, a second attribute connection is established between the first target position reverse information and the first target control information and the current connection information to obtain the target connection information; wherein, the first target position reverse information is the position reverse information of the position reverse level included in the first-level controller, and the first target control information is the control information of the control level included in the first-level controller; finally, based on the second target displacement information and the target connection information, the constraint intermediate group required to redirect the first model expression to the second face model is obtained.

[0103] In one example embodiment, establishing a first attribute connection between the first target displacement information and the current displacement information to obtain the second target displacement information can be achieved as follows: based on the first attribute connection, obtain the first target displacement value possessed by the first target displacement information, and replace the current displacement value including the current displacement information in the current constraint transmission intermediate group based on the first target displacement value to obtain the second target displacement information.

[0104] In one example embodiment, establishing a second attribute connection between the first target position reverse information, the first target control information, and the current connection information to obtain target connection information can be achieved as follows: First, based on the second attribute connection, obtain the first target position reverse information of the position reverse layer included in the first-level controller and the first target control information of the control layer; based on the first target position reverse information and the first target control information, replace the current connection information included in the current skin connection layer included in the current constraint transmission intermediate group to obtain the target connection information.

[0105] The following will combine Figure 10This section explains and illustrates the specific calculation process for the constraint intermediate group. For details, please refer to [link / reference]. Figure 10 As shown, in the process of calculating the constraint intermediate group, firstly, the displacement values ​​in the first displacement control layer rt_Orbit_01_Sec_ctrl_movement in the first-level controller can be assigned using blendWeight to obtain the first target displacement information. Then, a first attribute connection is established between the first target displacement information and the current displacement information (faceskin_movement) in the current constraint transfer intermediate group of the second face model (that is, replacing the value of the current displacement information with the value of the first target displacement information) to obtain the second target displacement information. Further, a second attribute connection is established between the first target position reverse information in the position reverse layer included in the first-level controller and the first target control information in the control layer and the current connection information (faceskin_connect) included in the current constraint transfer intermediate group (that is, replacing the information value of the current connection information with the first target position reverse information and the first target control information) to obtain the target connection information. Finally, the constraint intermediate group required to redirect the expression of the first model to the second face model is obtained based on the target connection information and the second target displacement information.

[0106] It should be noted that the rivet involved in this example embodiment is for adjusting the position of the controller, so that the controller can be located at the accurate position of the second face model, thereby achieving the purpose of precise control of the second face model. Its specific usage is as follows: multiply / divide node input1 -1, thereby achieving the goal of keeping the controller position unchanged.

[0107] In step S140, a target skeleton is generated based on the constraint intermediate group, and the second face model is skinned according to the target skeleton, so that a second model expression corresponding to the expression of the first model can be obtained on the second face model.

[0108] In this example embodiment, firstly, a target skeleton is generated based on the constraint intermediate group. Specifically, this can be achieved as follows: based on the first linked expression skeleton and the first-level expression skeleton, a second linked expression skeleton and a second-level expression skeleton are obtained to generate a second model expression corresponding to the first model expression on the second face model; parent-child constraints and / or scaling constraints are applied to the second linked expression skeleton and the second-level expression skeleton based on the constraint intermediate group to obtain the target skeleton. Secondly, skinning processing is performed on the second face model based on the target skeleton to obtain a second model expression corresponding to the first model expression on the second face model. Specifically, this can be achieved as follows: firstly, based on the target skeleton, the first linkage controller, and the first-level controller, a bone topology relationship is generated to generate a second model expression corresponding to the first model expression on the second face model; secondly, the target skeleton is bound to the second face model, and based on the bone topology relationship, the zeroth linkage control layer of the first linkage controller and the zeroth secondary control layer of the first-level controller are moved to a preset position corresponding to the second face model to control the generation of the second model expression corresponding to the first model expression on the second face model. In other words, in practical applications, when it is necessary to create a new expression binding (binding the first model expression on the existing first face model to the newly added second face model to obtain the second model expression corresponding to the newly added second face model), it is only necessary to move the layer named zero (the zero layer of the target linkage controller and the zero layer of the target secondary controller) to the appropriate position according to the model topology of the first model expression, and then copy the skinning weight (copy the target skeleton).

[0109] Thus, the method for redirecting model expressions described in the exemplary embodiments of this disclosure has been completed. Based on the foregoing description, it can be understood that the method for redirecting model expressions described in the exemplary embodiments of this disclosure can achieve rapid redirection while retaining custom modifications, and the resulting expression for the new model corresponding to the new face model is stable, which has significant practical implications and improves game development efficiency.

[0110] This disclosure also provides an example embodiment of a device for redirecting model facial expressions. Specifically, refer to... Figure 11 As shown, the model expression retargeting device may include an expression skeleton acquisition module 1110, a target hybrid weight calculation module 1120, a constraint intermediate group calculation module 1130, and a model expression retargeting module 1140. Wherein:

[0111] The facial expression bone acquisition module 1110 can be used to acquire the first linked facial expression bone and the first primary facial expression bone included in the first model expression of the first face model, and to acquire the first linkage controller corresponding to the first linked facial expression bone and the first primary controller corresponding to the first primary facial expression bone.

[0112] The target hybrid weight calculation module 1120 can be used to create a connection relationship between the first linkage controller and the first primary controller, and calculate the hybrid weight required to redirect the first model expression from the first face model to the second face model according to the first primary controller.

[0113] The target constraint transfer intermediate group calculation module 1130 can be used to calculate the constraint intermediate group required to redirect the expression of the first model to the second face model based on the connection relationship, the mixed weight and the first-level controller.

[0114] The model expression retargeting module 1140 can be used to generate a target skeleton based on the constraint intermediate group, and perform skinning processing on the second face model according to the target skeleton, so as to obtain a second model expression corresponding to the first model expression on the second face model.

[0115] In one exemplary embodiment of this disclosure, the calculation of the blending weights required to redirect the first model expression from the first face model to the second face model, based on the first-level controller, includes:

[0116] The first matrix information and the first level information included in the first-level controller are obtained; wherein, the first matrix information is used to characterize the movement and / or rotation of the first-level facial expression bone relative to the first linked facial expression bone, and the first level information is used to characterize the level of the first-level facial expression bone on the first face model.

[0117] Based on the first matrix information and the first level information, calculate the mixing weights required to redirect the first model expression from the first face model to the second face model.

[0118] In one exemplary embodiment of this disclosure, based on the connectivity, the hybrid weights, and the first-level controller, the calculation of the constraint intermediate set required to redirect the first model expression to the second face model includes:

[0119] Based on the connection relationship, the connection method between the first linked facial expression bone and the first primary facial expression bone is determined, and according to the connection method and the hybrid weight, the first target displacement information of the displacement level included in the first primary controller is determined;

[0120] A first attribute connection is established between the first target displacement information and the current displacement information to obtain the second target displacement information; wherein, the current displacement information is the displacement information included in the current constraint transmission process;

[0121] A second attribute connection is established between the first target position reverse information, the first target control information, and the current connection information to obtain target connection information; wherein, the first target position reverse information is the position reverse information of the position reverse layer included in the first-level controller, and the first target control information is the control information of the control layer included in the first-level controller;

[0122] Based on the second target displacement information and target connection information, the constraint intermediate group required to redirect the expression of the first model to the second face model is obtained.

[0123] In one exemplary embodiment of this disclosure, establishing a first attribute connection between the first target displacement information and the current displacement information to obtain second target displacement information includes:

[0124] Based on the first attribute connection, the first target displacement value of the first target displacement information is obtained, and the current displacement value including the current displacement information in the current constraint transmission intermediate group is replaced based on the first target displacement value to obtain the second target displacement information.

[0125] In one exemplary embodiment of this disclosure, a second attribute connection is established between the first target location reverse information and the first target control information and the current connection information to obtain target connection information, including:

[0126] Based on the second attribute connection, the first target position reversal information of the position reversal layer and the first target control information of the control layer included in the first primary controller are obtained;

[0127] Based on the first target position reverse information and the first target control information, the current connection information included in the current skin connection layer included in the current constraint transmission intermediate group is replaced to obtain the target connection information.

[0128] In one exemplary embodiment of this disclosure, generating a target skeleton based on the constraint intermediate set includes:

[0129] Based on the first linked expression bone and the first secondary expression bone, obtain the second linked expression bone and the second secondary expression bone required to generate the second model expression corresponding to the expression of the first model on the second face model;

[0130] Based on the aforementioned constraint intermediate group, parent-child constraints and / or scaling constraints are applied to the second linked facial expression bone and the second-level facial expression bone to obtain the target bone.

[0131] In one exemplary embodiment of this disclosure, skinning the second facial model based on the target skeleton allows for obtaining a second facial expression corresponding to the expression of the first model, including:

[0132] Based on the target skeleton, the first linkage controller, and the first primary controller, generate the skeletal topology required to generate the second model expression corresponding to the expression of the first model on the second face model;

[0133] The target skeleton is bound to the second face model, and based on the skeleton topology, the zeroth linkage control layer of the first linkage controller and the zeroth secondary control layer of the first primary controller are moved to a preset position corresponding to the second face model, thereby controlling the generation of a second model expression on the second face model that corresponds to the expression of the first model.

[0134] In one exemplary embodiment of this disclosure, obtaining the first linked expression bone and the first primary expression bone included in the first model expression of the first facial model, and obtaining the first linkage controller corresponding to the first linked expression bone and the first primary controller corresponding to the first primary expression bone, includes:

[0135] Based on historical facial models, basic facial expression skeletons and baseline facial expression groups are constructed. Then, based on the mesh lines of the basic facial expression skeletons and baseline facial expression groups, the standard linked facial expression skeletons and standard secondary skeletons required to generate the standard virtual facial expressions included in the baseline facial expression groups are calculated.

[0136] Configure a standard linkage controller for the standard linked facial expression skeleton and configure a standard secondary controller for the standard secondary skeleton; wherein, each standard linked facial expression skeleton corresponds to one standard linkage controller, each standard secondary skeleton corresponds to one standard secondary controller, and one standard linkage controller corresponds to one or more standard secondary controllers.

[0137] Establish a first association between the standard virtual expression and the standard linked expression skeleton, a second association between the standard virtual expression and the standard secondary skeleton, and establish a third association between the standard linked expression skeleton and the standard linked controller, and establish a fourth association between the standard secondary skeleton and the standard secondary controller;

[0138] Based on the first and second association relationships, the first linked expression skeleton and the first primary expression skeleton included in the first model expression are obtained, and based on the third and fourth association relationships, the first linkage controller corresponding to the first linked expression skeleton and the first primary controller corresponding to the first primary expression skeleton are obtained.

[0139] In one exemplary embodiment of this disclosure, a basic facial expression skeleton is constructed based on the historical facial model, including:

[0140] A real face image is acquired, and the real face image is processed based on a preset face image processing model to obtain the first position information of the facial bone feature points included in the real face image;

[0141] Based on the first position information of the facial bone feature points, obtain the model bone feature points corresponding to the historical facial model corresponding to the facial bone feature points;

[0142] The basic facial expression skeleton is constructed based on the second position information of the model's skeletal feature points.

[0143] The specific details of each module in the above-mentioned model expression redirection device have been described in detail in the corresponding model expression redirection method, so they will not be repeated here.

[0144] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0145] Furthermore, although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0146] In an exemplary embodiment of this disclosure, an electronic device capable of implementing the above-described method is also provided.

[0147] Those skilled in the art will understand that various aspects of this disclosure can be implemented as a system, method, or program product. Therefore, various aspects of this disclosure can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software aspects, collectively referred to herein as a "circuit," "module," or "system."

[0148] The following reference Figure 12 To describe an electronic device 1200 according to such an embodiment of the present disclosure. Figure 12 The electronic device 1200 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0149] like Figure 12 As shown, the electronic device 1200 is manifested in the form of a general-purpose computing device. The components of the electronic device 1200 may include, but are not limited to: at least one processing unit 1210, at least one storage unit 1220, a bus 1230 connecting different system components (including storage unit 1220 and processing unit 1210), and a display unit 1240.

[0150] The storage unit stores program code that can be executed by the processing unit 1210, causing the processing unit 1210 to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure. For example, the processing unit 1210 can perform actions such as... Figure 1 Step S110: Obtain the first linked expression bone and the first primary expression bone included in the first model expression of the first face model, and obtain the first linkage controller corresponding to the first linked expression bone and the first primary controller corresponding to the first primary expression bone; Step S120: Create the connection relationship between the first linkage controller and the first primary controller, and calculate the blending weights required to redirect the first model expression from the first face model to the second face model according to the first primary controller; Step S130: Calculate the constraint intermediate group required to redirect the first model expression to the second face model based on the connection relationship, the blending weights and the first primary controller; Step S140: Generate the target bone based on the constraint intermediate group, and perform skinning processing on the second face model according to the target bone, so that the second model expression corresponding to the first model expression can be obtained on the second face model.

[0151] Storage unit 1220 may include readable media in the form of volatile storage units, such as random access memory (RAM) 12201 and / or cache memory 12202, and may further include read-only memory (ROM) 12203.

[0152] Storage unit 1220 may also include a program / utility 12204 having a set (at least one) of program modules 12205, such program modules 12205 including but not limited to: operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0153] Bus 1230 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0154] Electronic device 1200 can also communicate with one or more external devices 1300 (e.g., keyboard, pointing device, Bluetooth device, etc.), one or more devices that enable a user to interact with electronic device 1200, and / or any device that enables electronic device 1200 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 1250. Furthermore, electronic device 1200 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 1260. As shown, network adapter 1260 communicates with other modules of electronic device 1200 via bus 1230. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 1200, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0155] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0156] In exemplary embodiments of this disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the methods described above is stored. In some possible implementations, various aspects of this disclosure may also be implemented as a program product including program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps of the various exemplary embodiments of this disclosure described in the "Exemplary Methods" section above.

[0157] The program product for implementing the above-described method according to embodiments of the present disclosure may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto. In this document, the readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0158] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0159] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0160] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0161] Program code for performing the operations of this disclosure can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0162] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of this disclosure and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0163] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention described herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not invented by this disclosure. The specification and embodiments are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the claims.

Claims

1. A method of redirecting a model expression, the method comprising: include: Obtain the first linked expression bone and the first primary expression bone included in the first model expression of the first face model, and obtain the first linkage controller corresponding to the first linked expression bone and the first primary controller corresponding to the first primary expression bone; Create a connection between the first linkage controller and the first primary controller, and calculate the blending weights required to redirect the first model expression from the first face model to the second face model based on the first primary controller; Based on the connection relationship, the connection method between the first-level facial bones of the first linked facial bone is determined, and according to the hybrid weight of the connection method, the first target displacement information of the displacement level included in the first-level controller is determined; a first attribute connection is established between the first target displacement information and the current displacement information to obtain the second target displacement information; Establish a second attribute connection between the first target location reverse information, the first target control information, and the current connection information to obtain the target connection information; Based on the second target displacement information and target connection information, the constraint intermediate group required to redirect the expression of the first model to the second face model is obtained; Based on the constraint intermediate group, a target skeleton is generated, and the second face model is skinned according to the target skeleton, so that a second model expression corresponding to the expression of the first model can be obtained on the second face model.

2. The method of claim 1, wherein, Based on the first-level controller, the required blending weights for redirecting the first model expression from the first face model to the second face model are calculated, including: The first matrix information and the first level information included in the first-level controller are obtained; wherein, the first matrix information is used to characterize the movement and / or rotation of the first-level facial expression bone relative to the first linked facial expression bone, and the first level information is used to characterize the level of the first-level facial expression bone on the first face model. Based on the first matrix information and the first level information, calculate the mixing weights required to redirect the first model expression from the first face model to the second face model.

3. The method of claim 1, wherein, The current displacement information is the displacement information included in the current constraint transmission process; The first target position reverse information is the position reverse information of the position reverse level included in the first-level controller, and the first target control information is the control information of the control level included in the first-level controller.

4. The method of claim 3, wherein, Establish a first attribute connection between the first target displacement information and the current displacement information to obtain the second target displacement information, including: Based on the first attribute connection, the first target displacement value of the first target displacement information is obtained, and the current displacement value including the current displacement information in the current constraint transmission intermediate group is replaced based on the first target displacement value to obtain the second target displacement information.

5. The method of claim 3, wherein, Establish a second attribute connection between the first target location reverse information, the first target control information, and the current connection information to obtain target connection information, including: Based on the second attribute connection, the first target position reversal information of the position reversal layer and the first target control information of the control layer included in the first primary controller are obtained; Based on the first target position reverse information and the first target control information, the current connection information included in the current skin connection layer included in the current constraint transmission intermediate group is replaced to obtain the target connection information.

6. The method of claim 1, wherein, Generate the target skeleton based on the aforementioned constraint intermediate group, including: Based on the first linked expression bone and the first secondary expression bone, obtain the second linked expression bone and the second secondary expression bone required to generate the second model expression corresponding to the expression of the first model on the second face model; Based on the aforementioned constraint intermediate group, parent-child constraints and / or scaling constraints are applied to the second linked facial expression bone and the second-level facial expression bone to obtain the target bone.

7. The method of claim 1, wherein, By performing skinning on the second facial model based on the target skeleton, a second facial expression corresponding to the expression of the first model can be obtained on the second facial model, including: Based on the target skeleton, the first linkage controller, and the first primary controller, generate the skeletal topology required to generate the second model expression corresponding to the expression of the first model on the second face model; The target skeleton is bound to the second face model, and based on the skeleton topology, the zeroth linkage control layer of the first linkage controller and the zeroth secondary control layer of the first primary controller are moved to a preset position corresponding to the second face model, thereby controlling the generation of a second model expression on the second face model that corresponds to the expression of the first model.

8. The method of claim 1, wherein, Obtaining the first linked expression bone and the first primary expression bone included in the first model expression of the first facial model, and obtaining the first linkage controller corresponding to the first linked expression bone and the first primary controller corresponding to the first primary expression bone, including: Based on historical facial models, basic facial expression skeletons and baseline facial expression groups are constructed. Then, based on the mesh lines of the basic facial expression skeletons and baseline facial expression groups, the standard linked facial expression skeletons and standard secondary skeletons required to generate the standard virtual facial expressions included in the baseline facial expression groups are calculated. Configure a standard linkage controller for the standard linked facial expression skeleton and configure a standard secondary controller for the standard secondary skeleton; wherein, each standard linked facial expression skeleton corresponds to one standard linkage controller, each standard secondary skeleton corresponds to one standard secondary controller, and one standard linkage controller corresponds to one or more standard secondary controllers. Establish a first association between the standard virtual expression and the standard linked expression skeleton, a second association between the standard virtual expression and the standard secondary skeleton, and establish a third association between the standard linked expression skeleton and the standard linked controller, and establish a fourth association between the standard secondary skeleton and the standard secondary controller; Based on the first and second association relationships, the first linked expression skeleton and the first primary expression skeleton included in the first model expression are obtained, and based on the third and fourth association relationships, the first linkage controller corresponding to the first linked expression skeleton and the first primary controller corresponding to the first primary expression skeleton are obtained.

9. The method of claim 8, wherein, Based on the historical facial model, a basic facial skeleton is constructed, including: A real face image is acquired, and the real face image is processed based on a preset face image processing model to obtain the first position information of the facial bone feature points included in the real face image; Based on the first position information of the facial bone feature points, obtain the model bone feature points corresponding to the historical facial model corresponding to the facial bone feature points; The basic facial expression skeleton is constructed based on the second position information of the model's skeletal feature points.

10. A model expression redirecting apparatus characterized by comprising: include: The facial expression bone acquisition module is used to acquire the first linked facial expression bone and the first primary facial expression bone included in the first model expression of the first face model, and to acquire the first linkage controller corresponding to the first linked facial expression bone and the first primary controller corresponding to the first primary facial expression bone. The hybrid weight calculation module is used to create a connection relationship between the first linkage controller and the first primary controller, and to calculate the hybrid weights required to redirect the first model expression from the first face model to the second face model based on the first primary controller. The constraint intermediate group calculation module is used to determine the connection method between the first linked facial bone and the first primary facial bone based on the connection relationship, and to determine the first target displacement information of the displacement level included in the first primary controller according to the hybrid weight of the connection method; and to establish a first attribute connection between the first target displacement information and the current displacement information to obtain the second target displacement information. Establish a second attribute connection between the first target location reverse information, the first target control information, and the current connection information to obtain the target connection information; Based on the second target displacement information and target connection information, the constraint intermediate group required to redirect the expression of the first model to the second face model is obtained; The model expression retargeting module is used to generate a target skeleton based on the constraint intermediate group, and to perform skinning processing on the second face model according to the target skeleton, so as to obtain a second model expression corresponding to the expression of the first model on the second face model.

11. A computer readable storage medium having stored thereon a computer program, characterized in that When the computer program is executed by the processor, it implements the method for redirecting model facial expressions as described in any one of claims 1-9.

12. An electronic device, comprising: include: processor; as well as Memory for storing the executable instructions of the processor; The processor is configured to execute the model expression redirection method according to any one of claims 1-9 by executing the executable instructions.

Images