Virtual character facial expression animation generation method and device, equipment and storage medium

Abstract

The invention provides a virtual character facial expression animation generation method and device, equipment and a storage medium. The method comprises the steps that firstly, facial shaping parameters of a target virtual character are acquired; the face of the target virtual character comprises a plurality of face areas, and the face shaping parameters comprise attribute parameters of all the face areas; obtaining animation parameters of a facial expression animation to be generated, and obtaining a fusion strategy of each facial region; and generating a facial expression animation corresponding to the target virtual character based on the animation parameter, the attribute parameter of each facial region and a fusion strategy, and by configuring different fusion strategies for different regions of the face, the expression fusion of the different regions of the face can be finely controlled, and the user experience is improved. The expression performance problem of a specific area of the face can be specifically repaired, the conflict between character face shaping and expression fusion is well solved, a fusion strategy can be configured according to muscle movement characteristics of different areas of the face, and the performance is accurately distributed.

Description

Technical Field

[0001] The present application relates to the technical field of methods for generating virtual character facial expression animations, and in particular to a method, device, equipment and storage medium for generating virtual character facial expression animations. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the application that are recited in the claims. No description herein is admitted to be prior art by inclusion in this section.

[0003] In game production, character facial shaping (also known as face pinching / character customization) is widely used. It is used for players to generate customized faces for virtual characters according to their own preferences, and is also used for differentiated production of game NPCs. In general, the ultimate goal of facial shaping is to give virtual characters the greatest possible freedom in face pinching, so as to meet players' customized needs for character appearance and increase the richness of the game.

[0004] The facial expressions of the characters in the game are based on the face pinching results as the facial shaping base, and the expression animation is played on it. In actual development, the expression animation files are usually produced for standard face shapes. Only by producing on a fixed face shape can the consistency of the facial animation effect be guaranteed.

[0005] When facial shaping and facial animation exist at the same time, the optimization goals of the two are naturally conflicting. The former emphasizes diversity, while the latter emphasizes consistency. If you want to get a better facial shaping experience, you need a greater degree of freedom in face pinching adjustment. If you want to get facial animation with better performance, you need as little freedom as possible in face pinching as the basis for playing expression animation. In response to the conflict between the two optimization goals, the current solution in related technologies is to directly superimpose and fuse the custom facial shaping base with the expression animation, and ensure the fusion result by weakening the strength of the expression animation. This method results in poor expression of facial expression animation playback. Summary of the invention

[0006] In view of this, the purpose of the present application is to propose a method, device, equipment and storage medium for generating virtual character facial expression animation, so as to solve or partially solve the problems in the above-mentioned background technology.

[0007] Based on the above purpose, the present application provides a method for generating a virtual character facial expression animation, comprising:

[0008] Acquire facial shaping parameters of a target virtual character; the face of the target virtual character includes a plurality of facial regions, and the facial shaping parameters include attribute parameters of each facial region;

[0009] Obtain animation parameters of the facial expression animation to be generated, and obtain fusion strategies for each facial region; different facial regions correspond to different fusion strategies; the fusion strategy is used to adjust the deformation amplitude of the attribute parameters of each facial region when the animation parameters are fused;

[0010] The facial expression animation corresponding to the target virtual character is generated based on the animation parameters, the attribute parameters of each facial area and the fusion strategy.

[0011] Based on the same inventive concept, the exemplary embodiment of the present application further provides a virtual character facial expression animation generating device, comprising:

[0012] A first acquisition module is used to acquire facial shaping parameters of a target virtual character; the face of the target virtual character includes a plurality of facial regions, and the facial shaping parameters include attribute parameters of each facial region;

[0013] The second acquisition module acquires the animation parameters of the facial expression animation to be generated, and acquires the fusion strategy of each facial area; different facial areas correspond to different fusion strategies; the fusion strategy is used to adjust the deformation amplitude of the attribute parameters of each facial area when the animation parameters are fused;

[0014] A generation module generates a facial expression animation corresponding to the target virtual character based on the animation parameters, the attribute parameters of each facial area and a fusion strategy.

[0015] Based on the same inventive concept, an exemplary embodiment of the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein when the processor executes the program, the method for generating facial expression animation of a virtual character as described above is implemented.

[0016] Based on the same inventive concept, an exemplary embodiment of the present application further provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the virtual character facial expression animation generation method as described above.

[0017] Based on the same inventive concept, an exemplary embodiment of the present application further provides a computer program product, which includes a computer program, and the computer program is executed by one or more processors so that the processor executes the virtual character facial expression animation generation method as described above.

[0018] As can be seen from the above, the method, device, equipment and storage medium for generating facial expression animation of a virtual character provided by the present application first obtain the facial shaping parameters of the target virtual character; the face of the target virtual character includes multiple facial areas, and the facial shaping parameters include attribute parameters of each facial area; the animation parameters of the facial expression animation to be generated are obtained, and the fusion strategy of each facial area is obtained; different facial areas correspond to different fusion strategies; based on the animation parameters, the attribute parameters of each facial area and the fusion strategy, the facial expression animation corresponding to the target virtual character is generated, and by configuring different fusion strategies for different areas of the face, the expression fusion of different areas of the face can be finely controlled, and the expression expression problem of specific areas of the face can be repaired in a targeted manner, which well solves the conflict between character facial shaping and expression fusion, and can configure the fusion strategy according to the muscle movement characteristics of different facial areas, accurately allocate performance, and reduce performance consumption while ensuring expression expression. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the present application or related technologies, the drawings required for use in the embodiments or related technical descriptions are briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 A schematic diagram of an application scenario in an embodiment of the present application;

[0021] Figure 2 A schematic diagram of a flow chart of a method for generating a virtual character facial expression animation in an embodiment of the present application;

[0022] Figure 3 A schematic diagram of dividing the facial area of ​​a virtual character in an embodiment of the present application;

[0023] Figure 4 A schematic diagram of a virtual character facial shaping base in an embodiment of the present application;

[0024] Figure 5 A schematic diagram of comparison between facial shaping parameters and facial expressions in an embodiment of the present application;

[0025] Figure 6 A schematic diagram of a facial expression after two facial attribute parameters are fused in an embodiment of the present application;

[0026] Figure 7 It is a schematic diagram of the fusion of a facial shaping base and expression animation in an embodiment of the present application;

[0027] Figure 8 A schematic diagram of a category feature division in an embodiment of the present application;

[0028] Fig. 9 A schematic diagram of the structure of a virtual character facial expression animation generation device according to an embodiment of the present application;

[0029] Fig.10 A schematic diagram of the structure of a specific electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0030] The principles and spirit of the present application will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement the present application, and are not intended to limit the scope of the present application in any way. On the contrary, these embodiments are provided to make the present application more thorough and complete, and to fully convey the scope of the present application to those skilled in the art.

[0031] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present disclosure should be understood by people with ordinary skills in the field to which the present disclosure belongs. The "first", "second" and similar words used in the embodiments of the present disclosure do not indicate any order, quantity or importance, but are only used to distinguish different components. "Including" or "comprising" and similar words mean that the elements or objects appearing in front of the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly. In addition, in the description of this application, unless otherwise specified, the term "several" refers to two or more. The term "and / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are in an "or" relationship.

[0032] According to the implementation manner of the present application, a method, apparatus, device and storage medium for generating virtual character facial expression animation are proposed.

[0033] It should be understood herein that any number of elements in the drawings is for illustration rather than limitation, and any naming is only for distinction rather than having any limiting meaning.

[0034] The principles and spirit of the present application are explained in detail below with reference to several representative implementations of the present application. SUMMARY OF THE INVENTION

[0036] In the current related technologies, the solution is to directly superimpose and fuse the custom facial shaping base and the expression animation, and to ensure the fusion result by weakening the strength of the expression animation. This method leads to poor expression of facial expression animation playback. In addition, the existing facial shaping and expression animation fusion solutions are simple and crude, and technically easy to implement, so they are widely used. However, there are widespread problems such as weak expression expression and poor controllability of expression fusion. In the practice of the engine's expression fusion technology, there is a lack of a production solution with stronger expressiveness, better controllability, significant personalization, and better conflict correction mechanism. Specifically, the main shortcomings of the current related technologies are as follows:

[0037] 1. Insufficient conflict correction mechanism: The existing technology does not have an effective conflict correction mechanism. It can only control the overall superposition and fusion strength of the whole face, but cannot finely control the fusion strength of different facial muscles, and cannot perform fine correction on local areas of blemishes. When blemishes occur only in some areas, the conflict can only be resolved by reducing the overall fusion ratio of expressions.

[0038] 2. Weak facial expression: Since the final facial expression effect is achieved by superimposing facial animation directly on the facial shaping base, in order to avoid serious facial animation errors such as unnatural or exaggerated expressions under extreme face-pinching conditions, the intensity of facial animation is often greatly weakened, resulting in the character's expression being stiff and lifeless, making it difficult for players to feel the realism and richness in the actual experience.

[0039] In order to solve the above problems, the present application provides a method for generating a virtual character facial expression animation, which specifically includes:

[0040] First, the facial shaping parameters of the target virtual character are obtained; the face of the target virtual character includes multiple facial areas, and the facial shaping parameters include attribute parameters of each facial area; the animation parameters of the facial expression animation to be generated are obtained, and the fusion strategy of each facial area is obtained; different facial areas correspond to different fusion strategies; based on the animation parameters, the attribute parameters of each facial area and the fusion strategy, the facial expression animation corresponding to the target virtual character is generated, and by configuring different fusion strategies for different facial areas, the expression fusion of different facial areas can be finely controlled, and the expression expression problem of specific facial areas can be repaired in a targeted manner, which well solves the conflict between the character's facial shaping and expression fusion, and the fusion strategy can be configured according to the muscle movement characteristics of different facial areas, and the performance is accurately allocated, so as to reduce performance consumption while ensuring the expression.

[0041] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application are described in detail below.

[0042] Application Scenario Overview

[0043] In some specific application scenarios, the virtual character facial expression animation generation method of the present application can be applied to various systems involving virtual character facial expression animation generation methods. Optionally, the system can be a game system. As an example, refer to Figure 1 , the application scenario includes at least one server 102 and at least one terminal 101. Terminal devices include but are not limited to desktop computers, mobile phones, mobile computers, tablet computers, media players, smart wearable devices, personal digital assistants (PDA) or other electronic devices that can realize the above functions. The server can be an independent physical server, or a server cluster or distributed system composed of several physical servers. It can also be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (content distribution network), and big data and artificial intelligence platforms. The server and the terminal can communicate through the network to realize data transmission. Among them, the network can be a wired network or a wireless network, which is not specifically limited in this application.

[0044] The server may be a server that provides various services. Specifically, the server may be used to provide background services for applications running on the terminal. Optionally, in some implementations, the method for generating facial expression animations of virtual characters provided in the embodiments of the present application may be executed by a terminal device or a server. When executed by the server, first obtain the facial shaping parameters of the target virtual character; the face of the target virtual character includes multiple facial areas, and the facial shaping parameters include attribute parameters of each facial area; obtain the animation parameters of the facial expression animation to be generated, and obtain the fusion strategy of each facial area; different facial areas correspond to different fusion strategies; based on the animation parameters, the attribute parameters of each facial area and the fusion strategy, generate the facial expression animation corresponding to the target virtual character. Optionally, the server may be hardware or software. When the server is hardware, it may be implemented as a distributed server cluster composed of several servers, or it may be implemented as a single server. When the server is software, it may be implemented as several software or software modules (for example, software or software modules used to provide distributed services), or it may be implemented as a single software or software module. The embodiments of the present application do not specifically limit this.

[0045] Optionally, the wireless network or wired network uses standard communication technology and / or protocol. The network is usually the Internet, but it can also be any network, including but not limited to a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a mobile, wired or wireless network, a dedicated network or any combination of a virtual private network). In some embodiments, the data exchanged through the network is represented by technologies and / or formats including hypertext mark-up language (HTML), extensible markup language (XML), etc. In addition, conventional encryption technologies such as secure socket layer (SSL), transport layer security (TLS), virtual private network (VPN), and Internet protocol security (IPsec) can be used to encrypt all or some links. In other embodiments, customized and / or dedicated data communication technologies can also be used to replace or supplement the above data communication technologies.

[0046] The following describes the method for generating virtual character facial expression animation according to the exemplary embodiment of the present application in conjunction with specific application scenarios. It should be noted that the above application scenarios are only shown to facilitate understanding of the spirit and principle of the present application, and the embodiments of the present application are not limited in this respect. On the contrary, the embodiments of the present application can be applied to any applicable scenario.

[0047] It should be understood that although Figure 2 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2 At least part of the steps may include several sub-steps or several stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0048] Exemplary Methods

[0049] refer to Figure 2 The present invention provides a method for generating a virtual character facial expression animation, the method comprising the following steps:

[0050] S101, obtaining facial shaping parameters of a target virtual character; the face of the target virtual character includes a plurality of facial regions, and the facial shaping parameters include attribute parameters of each facial region.

[0051] In specific implementation, the target virtual character is the virtual character for which facial expression animation is currently required to be generated. In theory, the target virtual character can be any virtual character, which can be a virtual character in a game or animation. In order to accurately control the muscle movement amplitude of each facial area when the virtual character integrates different facial expressions, in this embodiment, the face of the target virtual character is divided into multiple facial areas. In some embodiments, the facial area includes at least one of the following: forehead area, cheek area, eye area, mouth area, nose area and ear area.

[0052] In some embodiments, facial partitioning can be performed based on the facial expression coding system of FACS (Facial Action Coding System). FACS is a facial action coding system based on anatomical design, which can encode all visually recognizable facial movements. It decomposes facial expressions into multiple independent facial action units (AUs), each of which corresponds to the movement of specific facial muscles, and each expression can be composed of multiple AUs. Referring to the commonly used AUs of FACS for different expressions to perform facial partitioning, first of all, it conforms to the facial anatomical structure, and can well ensure the expressiveness and naturalness of the fused expression; it also allows each facial action unit to be controlled separately, ensuring the controllability of expression fusion; it can also adjust specific facial action units according to the respective characteristics of different NPCs to meet the needs of personalized expression customization; it can also ensure that the present invention has good compatibility, because the expression systems of many games are designed based on AUs. For the purpose of ensuring the expressiveness of expression and the controllability of expression fusion, this embodiment designs a facial partitioning method based on FACS, and divides the face into forehead area, cheek area, eye area, mouth area, nose area, and ear area. Each area corresponds to a set of bone points, and the partitioning results are as follows: Figure 3 shown.

[0053] It should be noted that the facial shaping parameters are used to determine the shape of the target virtual character's face after shaping. The facial shaping parameters include attribute parameters of each facial area, such as eye size attribute, nose size attribute, eye up and down displacement attribute, nose up and down displacement attribute, etc. The attribute parameters are the values ​​corresponding to these attributes. The facial shaping parameters are a summary of the attribute parameters of each facial area. Optionally, a general facial shaping system consists of a custom facial shaping base and a set of facial shaping parameters, where the facial shaping base is a character model bound to a face-pinching skeleton, such as Figure 4 As shown in the figure, facial shaping parameters are a set of dictionaries that store the displacement, scaling, and rotation attribute information of each bone in the face. This information is often a value between -1 and 1, where -1 and 1 correspond to two artificially set extreme shaping states of the indicator. Figure 5 As shown, the extreme shaping states of the eye's up and down displacement attributes and left and right displacement attributes are demonstrated, as well as the shaping effect constructed by superimposing these two attributes.

[0054] On the custom facial shaping base, by adjusting the displacement, rotation, and scaling properties of specific bones, the displacement, rotation, and scaling of the corresponding facial area of ​​the bones can be driven. Through fine adjustment of a large number of bones, a variety of facial shapes can be created with high flexibility, and the appearance constructed in this way is very stable, and the same shaping results can be stably reproduced through a set of the same parameters. Figure 6 Two facial sculpting results are shown, along with some of the facial sculpting parameters used.

[0055] In some embodiments, the number can be used as the region index and the bone name can be used as the bone index. A one-to-many mapping relationship from region to bone can be constructed in the game engine and stored in the DataTable of the rendering engine (or other table structures such as CSV). The mapping method is shown in Table 1.

[0056] Area No. Region Name Bone Name 0 Eye area eyebrow_l_jnt, eyebrow_r_jnt, eyeball_l_jnt, eyeball_r_jnt… 1 Forehead area forheadside_l_jnt, forheadside_r_jnt, temple_l_jnt, temple_r_jnt… …… …… …… 5 Mouth area lips_l_jnt,lips_r_jnt,lips_mid_jnt,lips_mid_jnt……

[0057] Table 1: Mapping table between facial regions and facial bones

[0058] In some embodiments, newly added bone points of virtual characters can be flexibly added to the index range of the corresponding area, making this implementation highly scalable. Indexing bones by name also ensures the reusability of this solution. Even if the positions of the bone points of two sets of character skeletons are different, as long as the same set of naming is followed, the expression fusion solution proposed in this embodiment can be applied.

[0059] S102, obtaining animation parameters of the facial expression animation to be generated, and obtaining a fusion strategy for each facial region; different facial regions correspond to different fusion strategies; the fusion strategy is used to adjust the deformation amplitude of the attribute parameters of each facial region when the animation parameters are fused.

[0060] In the specific implementation, the facial expression animation controls the changes of various bone parameters of the virtual character's face through animation parameters to control the virtual character's face to perform various expressions. The animation parameters of the facial expression animation to be generated, that is, the animation parameters of the facial expression animation currently to be generated, include the bone parameters corresponding to each facial area of ​​the target virtual character. Considering that the virtual character has different expressiveness in different facial areas when fusing expression animations, for example, the deformation amplitude of the forehead and nose is generally small, while the deformation amplitude of the eyes and mouth is large. In order to adapt to this differentiated deformation and avoid the overall weakening of facial expressions caused by a fusion strategy in the related art, in this embodiment, a fusion strategy is configured separately for each facial area. Optionally, the fusion strategy is used to control the deformation amplitude of the attribute parameters of each facial area when fusing animation parameters. Specifically, different fusion strategies can be set for different facial areas as needed.

[0061] S103: Generate a facial expression animation corresponding to the target virtual character based on the animation parameters, the attribute parameters of each facial region and a fusion strategy.

[0062] In specific implementation, after respectively obtaining the animation parameters of the facial expression animation to be generated, the attribute parameters of each facial region and the fusion strategy, the facial expression animation corresponding to the target virtual character can be generated according to the above three parameters. Figure 7, each facial region of the target virtual character corresponds to a fusion strategy, and then the attribute parameters and animation parameters of each facial region are superimposed and fused through the fusion strategy, and finally the fusion results of all facial regions are assembled together to obtain the facial expression animation.

[0063] In some embodiments, the fusion strategy adjusts the deformation amplitude of the attribute parameters of each facial area when the animation parameters are fused by mapping the animation fusion parameters corresponding to each facial area to a preset range; generating the facial expression animation corresponding to the target virtual character based on the animation parameters, the attribute parameters of each facial area and the fusion strategy specifically includes:

[0064] For each facial region, determining an animation fusion parameter corresponding to the facial region based on the animation parameter and the attribute parameter, and mapping the animation fusion parameter to a preset range based on the fusion strategy;

[0065] The facial expression animation corresponding to the target virtual character is generated based on the mapped animation fusion parameters corresponding to each facial area.

[0066] In the specific implementation, it is considered that the muscle movement amplitudes of different facial regions are inconsistent. For example, for expressions, the movement ranges of the forehead and ear regions are usually smaller than those of the mouth and eye regions. Therefore, a facial shaping fusion strategy with a smaller amplitude will be configured for the forehead and ear regions, while a fusion strategy with a larger amplitude will be configured for the mouth and eye regions. Optionally, in some embodiments, the fusion strategy can be set to a preset function, through which the animation fusion parameters determined based on the animation parameters and the attribute parameters can be mapped to a preset range, thereby avoiding serious expression animation errors such as unnatural or exaggerated expressions under extreme face pinching conditions, and the mapping amplitude can be adaptively adjusted according to different facial regions to achieve different effects of muscle movement amplitudes in different facial regions. Optionally, in some embodiments, the fusion strategy can be set to a two-dimensional curve graph, and the curve can be manually set with key points to ensure that the mapping value of the specified control range can be customized. Taking the eye region as an example, the horizontal axis is the coefficient of the expression amplitude, and the vertical axis is the shaping weight coefficient. By manually setting the mapping curve, the expression amplitude can be accurately controlled within the range of [0,1]. The same is true for other facial regions, and the weight control curve can be customized in different regions. After obtaining the mapped animation fusion parameters corresponding to each facial region, the facial expression animation corresponding to the target virtual character can be generated according to the mapped animation fusion parameters corresponding to all facial regions.

[0067] It should be noted that the animation parameters are the initial deformation parameters set by the target virtual character to realize the facial expression animation. The initial deformation parameters are used to determine the deformation amount of each facial area to realize a certain facial expression animation, for example, when realizing the laughing animation, the deformation amount of the mouth should occur. The attribute parameters determine the original deformation amount of each facial area of ​​the target virtual character under normal conditions. For example, under normal expression, the mouth of a certain target virtual character is larger, so the deformation amount corresponding to the mouth area of ​​the target virtual character will also be larger. If you want to generate the facial expression animation of the target virtual character, you need to merge the attribute parameters with the animation parameters to obtain the animation fusion parameters, which are the final deformation amounts of each facial area when the current target virtual character plays the facial expression animation. In this embodiment, in order to more accurately control the deformation degree of different areas when playing the animation, after obtaining the animation fusion parameters, the animation fusion parameters are first mapped to a preset range through a fusion strategy, and then the facial expression animation corresponding to the target virtual character is generated using the mapped animation fusion parameters.

[0068] In some embodiments, the fusion strategy adjusts the deformation amplitude of the attribute parameters of each facial area when the animation parameters are fused by controlling the expression adjustment coefficient of the animation parameters; the expression adjustment coefficient is used to adjust the animation parameters; based on the animation parameters, the attribute parameters of each facial area and the fusion strategy, the facial expression animation corresponding to the target virtual character is generated, specifically including:

[0069] For each facial region, determining an expression adjustment coefficient corresponding to the facial region based on the fusion strategy; and adjusting the animation parameter based on the expression adjustment coefficient;

[0070] Generate a facial expression animation corresponding to the target virtual character based on the adjusted animation parameters and the attribute parameters.

[0071] In specific implementation, in this embodiment, the expression adjustment coefficient corresponding to each facial area can be determined first according to the fusion strategy corresponding to each facial area. The fusion strategy adjusts the deformation amplitude of the attribute parameters of each facial area when the animation parameters are fused by controlling the expression adjustment coefficient of the animation parameters. Optionally, different expression adjustment coefficients can be set in advance for different fusion strategies. The expression adjustment coefficient is used to adjust the animation parameters. For example, if a certain animation parameter is an eye enlargement attribute parameter of 0.8 (where 1 is the maximum value of eye enlargement), the expression adjustment coefficient can be 0.5. Then, by multiplying the expression adjustment coefficient with the eye enlargement attribute parameter, the adjusted animation parameter can be 0.4. Then, the facial expression animation corresponding to the target virtual character is generated according to the adjusted animation parameter and the attribute parameter, ensuring that there is no conflict between facial shaping and expression fusion.

[0072] Optionally, in some embodiments, the fusion strategy is used to determine the expression amplitude of each facial region. For example, the expression amplitude of the mouth region is greater than the expression amplitude of the face region. The expression adjustment coefficient corresponding to the facial region is determined based on the fusion strategy, specifically including:

[0073] For each facial region, an expression adjustment coefficient corresponding to the facial region is determined based on the animation parameter, the fusion strategy and the attribute parameter.

[0074] Specifically, for each facial area, after the animation parameters are superimposed with the attribute parameters, the larger the value of the limit expression parameter corresponding to the facial area, the smaller the initial value of the corresponding expression adjustment coefficient, and the initial value is multiplied by the expression amplitude corresponding to the fusion strategy as the final expression adjustment coefficient.

[0075] In some embodiments, generating the facial expression animation corresponding to the target virtual character based on the animation parameters, the attribute parameters of each facial region and the fusion strategy specifically includes:

[0076] Acquiring the category characteristics of the target virtual character;

[0077] The facial expression animation corresponding to the target virtual character is generated based on the category features, the animation parameters, the attribute parameters of each facial area and the fusion strategy.

[0078] In the specific implementation, it is considered that if a "one-size-fits-all" approach is adopted, the same fusion mode is used for main characters, non-main characters, male and female characters, adult, youth and juvenile characters, and it is difficult to make differentiated designs according to the importance, gender and age of the characters. For example, in real life, the expression range of the elderly and children is somewhat different. Therefore, in order to achieve the personalized presentation of facial expression animation, in the embodiment of the present application, the category feature of the target virtual character is first obtained, and then the category feature is used together with the animation parameters, the attribute parameters of each facial area and the fusion strategy to generate the facial expression animation corresponding to the target virtual character.

[0079] In some embodiments, the category features include: role gender features, role age features, and importance features.

[0080] When implementing it, refer to Figure 8, is a schematic diagram of a category feature division in an embodiment of the present application. In this embodiment, the category features are mainly divided from three aspects: importance, gender and age. Optionally, the user can also select features in other aspects as category features to be divided as needed. Among them, importance features mainly include main roles and non-main roles, gender features mainly include males and females, and age features mainly include teenagers, young people and adults. Optionally, the specific division of each of the above features can be customized as needed, and there is no limitation on this. For example, the elderly, infants, etc. can be added to the age features.

[0081] In some embodiments, generating the facial expression animation corresponding to the target virtual character based on the category features, the animation parameters, the attribute parameters of each facial region and the fusion strategy specifically includes:

[0082] For each facial region, determining a target fusion strategy from a plurality of fusion strategies corresponding to the facial region based on the category feature, and generating an animation fusion parameter corresponding to the facial region based on the animation parameter, the attribute parameter and the target fusion strategy;

[0083] The facial expression animation corresponding to the target virtual character is generated based on the animation fusion parameters corresponding to each of the facial regions.

[0084] In the specific implementation, in order to improve the efficiency of character expression fusion, the character expression fusion template system is adopted in this embodiment. The template system can distinguish between main characters, non-main characters, male characters, female characters, adult characters, youth characters, and juvenile characters, and preset a set of expression fusion strategies for each facial area placed in the character expression fusion slot for each category according to characteristics such as gender, age, and importance. After determining the category characteristics of the target virtual character, the target fusion strategy can be determined from multiple fusion strategies corresponding to each facial area according to the category characteristics, and then the animation fusion parameters corresponding to each facial area are generated based on the animation parameters, the attribute parameters and the target fusion strategy. Finally, the facial expression animation corresponding to the target virtual character is generated according to the animation fusion parameters corresponding to all the facial areas. It should be noted that, under normal circumstances, only one fusion strategy can be set for each facial area of ​​the target virtual character. However, in this embodiment, in order to further perform personalized fusion adjustment according to the category characteristics, multiple fusion strategies can be configured for each facial area, and then each category feature can find the corresponding fusion strategy from them. The embodiment of the present application realizes differentiation of facial expressions according to different application objects through strategy processing methods, such as gender, age, and importance of characters, and ensures personalization of character expressions based on the same set of facial expression animation resources.

[0085] In some embodiments, generating the facial expression animation corresponding to the target virtual character based on the category features, the animation parameters, the attribute parameters of each facial region and the fusion strategy specifically includes:

[0086] Determining the expression amplitude parameter corresponding to the target virtual character based on the category feature;

[0087] For each facial region, determining the animation fusion parameter of the facial region based on the animation parameter, the attribute parameter and the fusion strategy, and adjusting the animation fusion parameter based on the expression amplitude parameter;

[0088] The facial expression animation corresponding to the target virtual character is generated based on the adjusted animation fusion parameters corresponding to each of the facial regions.

[0089] In the specific implementation, taking into account the different amplitudes or degrees of exaggeration of facial expressions of different types of virtual characters, therefore, in the embodiment of the present application, the expression amplitude parameter corresponding to the target virtual character can be first determined according to the category characteristics of the target virtual character; the expression amplitude parameter is mainly used to adjust the animation fusion parameters of each facial area, so that when playing the expression animation effect, each facial area can refer to different type characteristics and have different amplitude adjustments, thereby achieving differentiated expression expressions of different types of characteristics.

[0090] The method for generating facial expression animation of a virtual character provided by the present application comprises the following steps: obtaining facial shaping parameters of a target virtual character; the face of the target virtual character comprises a plurality of facial regions, and the facial shaping parameters comprise attribute parameters of each facial region; obtaining animation parameters of the facial expression animation to be generated, and obtaining fusion strategies of each facial region; different facial regions correspond to different fusion strategies; generating facial expression animation corresponding to the target virtual character based on the animation parameters, attribute parameters of each facial region and fusion strategy, and configuring different fusion strategies for different facial regions to finely control the expression fusion of different facial regions, and can repair the expression expression problem of a specific facial region in a targeted manner, and solve the conflict between facial shaping of the character and expression fusion well, and can configure fusion strategies according to the muscle movement characteristics of different facial regions, accurately allocate performance, and reduce performance consumption under the premise of ensuring expression expression. In addition, the method of the embodiment of the present application can distinguish the gender, age and importance of the virtual character, ensure the difference of the expression expression effect of the virtual character on the basis of using the same set of expression animation resources, and further enhance the expressiveness of the expression under the premise of ensuring that there is no conflict between facial shaping and expression fusion, so as to bring a better sense of immersion to the player.

[0091] It should be noted that the method of the embodiment of the present application can be performed by a single device, such as a computer or server. The method of this embodiment can also be applied to a distributed scenario and completed by multiple devices cooperating with each other. In the case of such a distributed scenario, one of the multiple devices can only perform one or several steps in the method of the embodiment of the present application, and the multiple devices will interact with each other to complete the described method.

[0092] It should be noted that the above describes some embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0093] Exemplary Devices

[0094] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a virtual character facial expression animation generation device.

[0095] refer to Fig. 9 , the virtual character facial expression animation generating device comprises:

[0096] The first acquisition module 201 acquires facial shaping parameters of a target virtual character; the face of the target virtual character includes multiple facial regions, and the facial shaping parameters include attribute parameters of each facial region;

[0097] The second acquisition module 202 acquires the animation parameters of the facial expression animation to be generated, and acquires the fusion strategy of each facial region; different facial regions correspond to different fusion strategies; the fusion strategy is used to adjust the deformation amplitude of the attribute parameters of each facial region when the animation parameters are fused;

[0098] The generation module 203 generates the facial expression animation corresponding to the target virtual character based on the animation parameters, the attribute parameters of each facial area and the fusion strategy.

[0099] In some embodiments, the facial region includes at least one of the following: a forehead region, a cheek region, an eye region, a mouth region, a nose region, and an ear region.

[0100] In some embodiments, the fusion strategy adjusts the deformation amplitude of the attribute parameters of each facial area when the animation parameters are fused by mapping the animation fusion parameters corresponding to each facial area to a preset range; the generation module is specifically used to:

[0101] For each facial region, determining an animation fusion parameter corresponding to the facial region based on the animation parameter and the attribute parameter, and mapping the animation fusion parameter to a preset range based on the fusion strategy;

[0102] The facial expression animation corresponding to the target virtual character is generated based on the mapped animation fusion parameters corresponding to each facial area.

[0103] In some embodiments, the fusion strategy adjusts the deformation amplitude of the attribute parameters of each facial area when the animation parameters are fused by controlling the expression adjustment coefficient of the animation parameters; the expression adjustment coefficient is used to adjust the animation parameters; the generation module is specifically used to:

[0104] For each facial region, determining an expression adjustment coefficient corresponding to the facial region based on the fusion strategy; and adjusting the animation parameter based on the expression adjustment coefficient;

[0105] Generate a facial expression animation corresponding to the target virtual character based on the adjusted animation parameters and the attribute parameters.

[0106] In some embodiments, the generating module specifically includes:

[0107] A category acquisition unit, which acquires the category characteristics of the target virtual character;

[0108] The animation generating unit generates the facial expression animation corresponding to the target virtual character based on the category features, the animation parameters, the attribute parameters of each facial area and the fusion strategy.

[0109] In some embodiments, the animation generation unit is specifically used to:

[0110] For each facial region, determining a target fusion strategy from a plurality of fusion strategies corresponding to the facial region based on the category feature, and generating an animation fusion parameter corresponding to the facial region based on the animation parameter, the attribute parameter and the target fusion strategy;

[0111] The facial expression animation corresponding to the target virtual character is generated based on the animation fusion parameters corresponding to each of the facial regions.

[0112] In some embodiments, the animation generation unit is specifically used to:

[0113] Determining the expression amplitude parameter corresponding to the target virtual character based on the category feature;

[0114] For each facial region, determining the animation fusion parameter of the facial region based on the animation parameter, the attribute parameter and the fusion strategy, and adjusting the animation fusion parameter based on the expression amplitude parameter;

[0115] The facial expression animation corresponding to the target virtual character is generated based on the adjusted animation fusion parameters corresponding to each of the facial regions.

[0116] In some embodiments, the category features include: role gender features, role age features, and importance features.

[0117] For the convenience of description, the above device is described in terms of functions divided into various modules. Of course, when implementing the present application, the functions of each module can be implemented in the same or multiple software and / or hardware.

[0118] The virtual character facial expression animation generation device of the above embodiment is used to implement the corresponding virtual character facial expression animation generation method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0119] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments, the present application also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method for generating facial expression animation of a virtual character described in any of the above embodiments is implemented.

[0120] Fig.10 A more specific schematic diagram of the hardware structure of an electronic device provided in this embodiment is shown, and the device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. The processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are connected to each other through the bus 1050 in the device.

[0121] The processor 1010 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0122] The memory 1020 may be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage device, dynamic storage device, etc. The memory 1020 may store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented by software or firmware, the relevant program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0123] The input / output interface 1030 is used to connect the input / output module to realize information input and output. The input / output module can be configured in the device as a component (not shown in the figure), or it can be externally connected to the device to provide corresponding functions. The input device may include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device may include a display, a speaker, a vibrator, an indicator light, etc.

[0124] The communication interface 1040 is used to connect a communication module (not shown) to realize communication interaction between the device and other devices. The communication module can realize communication through a wired mode (such as USB, network cable, etc.) or a wireless mode (such as mobile network, WIFI, Bluetooth, etc.).

[0125] The bus 1050 includes a path that transmits information between the various components of the device (eg, the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040).

[0126] It should be noted that, although the above device only shows the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040 and the bus 1050, in the specific implementation process, the device may also include other components necessary for normal operation. In addition, it can be understood by those skilled in the art that the above device may also only include the components necessary for implementing the embodiments of the present specification, and does not necessarily include all the components shown in the figure.

[0127] The electronic device of the above embodiment is used to implement the corresponding virtual character facial expression animation generation method in any of the above embodiments, and has the beneficial effects of the corresponding method embodiment, which will not be repeated here.

[0128] The memory 1020 stores machine-readable instructions executable by the processor 1010. When the electronic device is running, the processor 1010 communicates with the memory 1020 via the bus 1050, so that the processor 1010 executes the following instructions when running: obtaining facial shaping parameters of the target virtual character; the face of the target virtual character includes multiple facial areas, and the facial shaping parameters include attribute parameters of each facial area; the fusion strategy is used to adjust the deformation amplitude of the attribute parameters of each facial area when the animation parameters are fused; obtaining animation parameters of the facial expression animation to be generated, and obtaining the fusion strategy of each facial area; different facial areas correspond to different fusion strategies; based on the animation parameters, the attribute parameters of each facial area and the fusion strategy, the facial expression animation corresponding to the target virtual character is generated.

[0129] In a possible implementation, in the instructions executed by the processor 1010, the facial area includes at least one of the following: a forehead area, a cheek area, an eye area, a mouth area, a nose area, and an ear area.

[0130] In a possible implementation, in the instructions executed by the processor 1010, the fusion strategy adjusts the deformation amplitude of the attribute parameters of each facial area when the animation parameters are fused by mapping the animation fusion parameters corresponding to each facial area to a preset range; generating the facial expression animation corresponding to the target virtual character based on the animation parameters, the attribute parameters of each facial area and the fusion strategy specifically includes:

[0131] For each facial region, determining an animation fusion parameter corresponding to the facial region based on the animation parameter and the attribute parameter, and mapping the animation fusion parameter to a preset range based on the fusion strategy;

[0132] The facial expression animation corresponding to the target virtual character is generated based on the mapped animation fusion parameters corresponding to each facial area.

[0133] In a possible implementation, in the instructions executed by the processor 1010, the fusion strategy adjusts the deformation amplitude of the attribute parameters of each facial area when the animation parameters are fused by controlling the expression adjustment coefficient of the animation parameters; the expression adjustment coefficient is used to adjust the animation parameters; and generating the facial expression animation corresponding to the target virtual character based on the animation parameters, the attribute parameters of each facial area and the fusion strategy specifically includes:

[0134] For each facial region, determining an expression adjustment coefficient corresponding to the facial region based on the fusion strategy; and adjusting the animation parameter based on the expression adjustment coefficient;

[0135] Generate a facial expression animation corresponding to the target virtual character based on the adjusted animation parameters and the attribute parameters.

[0136] In a possible implementation, the instructions executed by the processor 1010, generating the facial expression animation corresponding to the target virtual character based on the animation parameters, the attribute parameters of each facial region and the fusion strategy, specifically includes:

[0137] Acquiring the category characteristics of the target virtual character;

[0138] The facial expression animation corresponding to the target virtual character is generated based on the category features, the animation parameters, the attribute parameters of each facial area and the fusion strategy.

[0139] In a possible implementation, the instructions executed by the processor 1010, generating the facial expression animation corresponding to the target virtual character based on the category features, the animation parameters, the attribute parameters of each facial region and the fusion strategy, specifically includes:

[0140] For each facial region, determining a target fusion strategy from a plurality of fusion strategies corresponding to the facial region based on the category feature, and generating an animation fusion parameter corresponding to the facial region based on the animation parameter, the attribute parameter and the target fusion strategy;

[0141] The facial expression animation corresponding to the target virtual character is generated based on the animation fusion parameters corresponding to each of the facial regions.

[0142] In a possible implementation, the instructions executed by the processor 1010, generating the facial expression animation corresponding to the target virtual character based on the category features, the animation parameters, the attribute parameters of each facial region and the fusion strategy, specifically includes:

[0143] Determining the expression amplitude parameter corresponding to the target virtual character based on the category feature;

[0144] For each facial region, determining the animation fusion parameter of the facial region based on the animation parameter, the attribute parameter and the fusion strategy, and adjusting the animation fusion parameter based on the expression amplitude parameter;

[0145] The facial expression animation corresponding to the target virtual character is generated based on the adjusted animation fusion parameters corresponding to each of the facial regions.

[0146] In a possible implementation, in the instructions executed by the processor 1010, the category features include: role gender features, role age features, and importance features.

[0147] Through the above method, when the electronic device is running, the facial shaping parameters of the target virtual character are first obtained; the face of the target virtual character includes multiple facial areas, and the facial shaping parameters include attribute parameters of each facial area; the animation parameters of the facial expression animation to be generated are obtained, and the fusion strategy of each facial area is obtained; different facial areas correspond to different fusion strategies; based on the animation parameters, the attribute parameters of each facial area and the fusion strategy, the facial expression animation corresponding to the target virtual character is generated, and by configuring different fusion strategies for different areas of the face, the expression fusion of different areas of the face can be finely controlled, and the expression expression problem of specific areas of the face can be repaired in a targeted manner, which well solves the conflict between the character's facial shaping and expression fusion, and can configure the fusion strategy according to the muscle movement characteristics of different facial areas, accurately allocate performance, and reduce performance consumption while ensuring expression expression.

[0148] Exemplary Program Products

[0149] Based on the same inventive concept, corresponding to any of the above-mentioned embodiment methods, the present application also provides a non-transitory computer-readable storage medium, wherein the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to enable the computer to execute the virtual character facial expression animation generation method as described in any of the above embodiments.

[0150] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0151] The computer instructions stored in the storage medium of the above embodiment are used to enable the computer to execute the virtual character facial expression animation generation method as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0152] Based on the same inventive concept, corresponding to any of the above-mentioned embodiments and methods, the present application also provides a computer program product, which includes a computer program. In some embodiments, the computer program instructions can be executed by one or more processors of a computer so that the computer and / or the processor execute the method for generating facial expression animation of a virtual character described in the above-mentioned embodiment. Corresponding to the execution subject corresponding to each step in each embodiment of the scene editing method, the processor that executes the corresponding step can belong to the corresponding execution subject.

[0153] The computer program product of the above embodiment is used to enable the computer and / or the processor to execute the virtual character facial expression animation generation method as described in any of the above embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be repeated here.

[0154] It is understandable that before using the technical solutions of each embodiment of the present application, the type, scope of use, usage scenarios, etc. of the personal information involved will be informed to the user in an appropriate manner, and the user's authorization will be obtained.

[0155] For example, in response to receiving an active request from a user, a prompt message is sent to the user to clearly remind the user that the operation requested to be performed will require obtaining and using the user's personal information. Thus, the user can independently choose whether to provide personal information to the electronic device, application, server, storage medium or other software or hardware that performs the operation of the technical solution of the present application according to the prompt message.

[0156] As an optional but non-limiting implementation, in response to receiving the user's active request, the prompt information may be sent to the user in the form of a pop-up window, in which the prompt information may be presented in text form. In addition, the pop-up window may also carry a selection control for the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0157] It is understandable that the above notification and the process of obtaining user authorization are merely illustrative and do not constitute a limitation on the implementation method of this application. Other methods that meet relevant laws and regulations may also be applied to the implementation method of this application.

[0158] It should be understood by those skilled in the art that the embodiments of the present application can be implemented as a system, method or computer program product. Therefore, the present application can be specifically implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software, generally referred to herein as "circuit", "module" or "system". In addition, in some embodiments, the present application can also be implemented in the form of a computer program product in one or more computer-readable media, which contains computer-readable program code.

[0159] Any combination of one or more computer-readable media can be used. Computer-readable media can be computer-readable signal media or computer-readable storage media. Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any combination of the above. More specific examples (non-exhaustive examples) of computer-readable storage media can include, for example: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device.

[0160] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0161] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0162] Computer program code for performing the operation of the present application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., using an Internet service provider to connect through the Internet).

[0163] It should be understood that each box in the flowchart and / or block diagram and the combination of boxes in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine, and these computer program instructions are executed by a computer or other programmable data processing device to produce a device that implements the functions / operations specified in the boxes in the flowchart and / or block diagram.

[0164] These computer program instructions may also be stored in a computer-readable medium that enables a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable medium produce a product that includes an instruction device that implements the functions / operations specified in the blocks in the flowchart and / or block diagram.

[0165] Computer program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby enabling the instructions executed on the computer or other programmable device to provide a process for implementing the functions / operations specified in the blocks in the flowchart and / or block diagram.

[0166] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Among them, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0167] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into several modules or units to be embodied.

[0168] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present application (including the claims) is limited to these examples; based on the concept of the present application, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other adjustments to the different aspects of the embodiments of the present application as described above, which are not provided in detail for the sake of simplicity.

[0169] In addition, to simplify the description and discussion, and in order not to make the embodiments of the present application difficult to understand, the known power supply / ground connection with the integrated circuit (IC) chip and other components may or may not be shown in the provided drawings. In addition, the device can be shown in the form of a block diagram to avoid making the embodiments of the present application difficult to understand, and this also takes into account the fact that the details of the implementation of these block diagram devices are highly dependent on the platform to be implemented in the embodiments of the present application (that is, these details should be fully within the scope of understanding of those skilled in the art). In the case of elaborating specific details (e.g., circuits) to describe exemplary embodiments of the present application, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details or when these specific details are adjusted. Therefore, these descriptions should be considered to be illustrative rather than restrictive.

[0170] Although the present application has been described in conjunction with specific embodiments of the present application, many replacements, modifications and variations of these embodiments will be apparent to those skilled in the art from the foregoing description. For example, other memory architectures (e.g., dynamic RAM (DRAM)) may use the embodiments discussed.

[0171] The embodiments of the present application are intended to cover all such substitutions, modifications and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present application should be included in the scope of protection of the present application.

Claims

1. A method for generating a virtual character facial expression animation, characterized in that: include: Acquire facial shaping parameters of a target virtual character; the face of the target virtual character includes a plurality of facial regions, and the facial shaping parameters include attribute parameters of each facial region; Obtain animation parameters of the facial expression animation to be generated, and obtain fusion strategies for each facial region; different facial regions correspond to different fusion strategies; the fusion strategy is used to adjust the deformation amplitude of the attribute parameters of each facial region when the animation parameters are fused; The facial expression animation corresponding to the target virtual character is generated based on the animation parameters, the attribute parameters of each facial area and the fusion strategy.

2. The method according to claim 1, characterized in that The facial area includes at least one of the following: a forehead area, a cheek area, an eye area, a mouth area, a nose area, and an ear area.

3. The method according to claim 1, characterized in that: The fusion strategy adjusts the deformation amplitude of the attribute parameters of each facial area when the animation parameters are fused by mapping the animation fusion parameters corresponding to each facial area to a preset range; Generating the facial expression animation corresponding to the target virtual character based on the animation parameters, the attribute parameters of each facial region and the fusion strategy specifically includes: For each facial region, determining an animation fusion parameter corresponding to the facial region based on the animation parameter and the attribute parameter, and mapping the animation fusion parameter to a preset range based on the fusion strategy; The facial expression animation corresponding to the target virtual character is generated based on the mapped animation fusion parameters corresponding to each facial area.

4. The method according to claim 1, characterized in that: The fusion strategy adjusts the deformation amplitude of the attribute parameters of each facial area when the animation parameters are fused by controlling the expression adjustment coefficient of the animation parameters; the expression adjustment coefficient is used to adjust the animation parameters; Generating the facial expression animation corresponding to the target virtual character based on the animation parameters, the attribute parameters of each facial region and the fusion strategy specifically includes: For each facial region, determining an expression adjustment coefficient corresponding to the facial region based on the fusion strategy; and adjusting the animation parameter based on the expression adjustment coefficient; Generate a facial expression animation corresponding to the target virtual character based on the adjusted animation parameters and the attribute parameters.

5. The method according to claim 1, characterized in that Generating the facial expression animation corresponding to the target virtual character based on the animation parameters, the attribute parameters of each facial region and the fusion strategy specifically includes: Acquiring the category characteristics of the target virtual character; The facial expression animation corresponding to the target virtual character is generated based on the category features, the animation parameters, the attribute parameters of each facial area and the fusion strategy.

6. The method according to claim 5, characterized in that Generating the facial expression animation corresponding to the target virtual character based on the category features, the animation parameters, the attribute parameters of each facial region and the fusion strategy specifically includes: For each facial region, determining a target fusion strategy from a plurality of fusion strategies corresponding to the facial region based on the category feature, and generating an animation fusion parameter corresponding to the facial region based on the animation parameter, the attribute parameter and the target fusion strategy; The facial expression animation corresponding to the target virtual character is generated based on the animation fusion parameters corresponding to each of the facial regions.

7. The method according to claim 5, characterized in that Generating the facial expression animation corresponding to the target virtual character based on the category features, the animation parameters, the attribute parameters of each facial region and the fusion strategy specifically includes: Determining the expression amplitude parameter corresponding to the target virtual character based on the category feature; For each facial region, determining the animation fusion parameter of the facial region based on the animation parameter, the attribute parameter and the fusion strategy, and adjusting the animation fusion parameter based on the expression amplitude parameter; The facial expression animation corresponding to the target virtual character is generated based on the adjusted animation fusion parameters corresponding to each of the facial regions.

8. The method according to claim 5, characterized in that The category characteristics include: role gender characteristics, role age characteristics and importance characteristics.

9. A virtual character facial expression animation generating device, characterized in that: include: A first acquisition module is used to acquire facial shaping parameters of a target virtual character; the face of the target virtual character includes a plurality of facial regions, and the facial shaping parameters include attribute parameters of each facial region; The second acquisition module acquires the animation parameters of the facial expression animation to be generated, and acquires the fusion strategy of each facial area; different facial areas correspond to different fusion strategies; the fusion strategy is used to adjust the deformation amplitude of the attribute parameters of each facial area when the animation parameters are fused; A generation module generates a facial expression animation corresponding to the target virtual character based on the animation parameters, the attribute parameters of each facial area and a fusion strategy.

10. An electronic device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable by the processor, wherein the processor implements the method according to any one of claims 1 to 8 when executing the program.

11. A non-transitory computer-readable storage medium, characterized in that: The non-transitory computer-readable storage medium stores computer instructions for causing a computer to execute the method according to any one of claims 1 to 8.

Images