Digital human processing method and apparatus

Abstract

The application relates to the field of digital people, in particular to a digital person processing method and device. The method comprises the following steps: acquiring a basic face model; determining basic face model data, wherein the basic face model data is obtained by decomposing the basic face model; acquiring preset custom face model data; modifying the basic face model data based on the custom face model data to obtain current basic face model data; combining the current basic face model data to obtain a current basic face model, so as to obtain a digital face according to the current basic face model. The application has the effects of improving the convenience in digital face construction, improving the speed of digital face processing, and improving the production speed of digital people.

Description

Technical Field

[0001] This application relates to the field of digital humans, and in particular to a method and apparatus for processing digital humans. Background Technology

[0002] "Digital human" refers to a detailed three-dimensional human structure synthesized in a computer, with all data derived from the real human body. It can simulate human metabolism, growth and development, pathophysiological changes, etc. In a narrow sense, digital human is a product of the integration of information science and life science, using information science methods to virtually simulate the human body's form and function at different levels. In a broad sense, digital human refers to the penetration of digital technology into all levels and stages of human anatomy, physics, physiology, and intelligence.

[0003] Furthermore, with the continuous development of mobile internet, live streaming technology has also advanced rapidly, and "digital humans" are gradually being applied to the live streaming industry. To enhance the fun and interactivity of live streams, virtual avatar live streaming, as a crucial part of live streaming projects, has been occupying an increasingly larger proportion in recent years. During live streaming, pre-set virtual avatars, such as lifelike human anchor avatars or cartoon characters, can be used to replace the actual appearance of a real anchor. In virtual live streaming rooms, certain messages need to be broadcast quickly, such as breaking news, timely sporting events, and even messages for audience interaction.

[0004] However, in the process of creating digital humans for live streaming, the production process is usually carried out for a specific character, or the face-shaping process of Metahuman is used to create digital humans. The former is often very inefficient, as the digital human production process relies mostly on complete customization, so all the data needs to be started from scratch; the latter, due to its imperfect face-shaping function and reliance on real scan models, is currently unable to achieve a digital human that fully meets expectations. Summary of the Invention

[0005] In order to improve the problems of low realism and slow production speed of digital human faces in related digital human production methods, this application provides a digital human processing method and apparatus.

[0006] The digital human processing method and apparatus provided in this application adopt the following technical solution:

[0007] A method for processing digital humans, applied in a terminal device, includes:

[0008] Obtain a basic face model;

[0009] Determine the basic face model data, which is obtained by decomposing the basic face model;

[0010] Obtain preset custom face model data;

[0011] Modify the base face model data based on the custom face model data to obtain the current base face model data;

[0012] Combine the current basic face model data to obtain the current basic face model, so as to obtain a digital face based on the current basic face model.

[0013] By adopting the above technical solution, when processing a digital human using the digital human processing method of this application, a basic face model can be obtained first, and then the basic face model can be decomposed to obtain basic face model data that represents the basic face model. Then, based on the data of the custom model to be generated, the basic face model data can be modified to make the basic face model similar to the custom face model. Thus, the construction of the custom model can be completed by modifying the basic model, which improves the convenience of digital human face construction, increases the speed of digital human face processing, and thus increases the production speed of digital humans.

[0014] Preferably, when decomposing the basic face model, the basic face model data is divided into adjustable model data and inherited model data. The adjustable model data includes a subjective adjustment part and a calibration part. The subjective adjustment part includes the shape of facial features, and the calibration part includes the facial proportions and the position of the mouth.

[0015] By adopting the above technical solution, the basic face model data is further divided because, in the process of processing digital humans, some data can be adjusted through feature points, such as the specific shapes of the eyes, nose, mouth, eyebrows, and ears, as well as the differences in the position of facial features due to the different lengths and widths of the face. The other part is completely consistent with the basic face model and is categorized as inherited model data. By continuously subdividing the basic face model data, the realism of the digital human face is increased.

[0016] Preferably, when modifying the base face model data based on the custom face model, the following steps are included:

[0017] Acquire feature points of the subjective adjustment portion, including positioning feature points and fine-tuning feature points;

[0018] Determine the feature points of the subjective adjustment portion and the feature points of the custom face model data;

[0019] The positioning feature points of the subjective adjustment part are adjusted based on the feature points of the custom face model data;

[0020] The position of the fine-tuning feature points is changed based on the adjustment results of the localized feature points.

[0021] By adopting the above technical solution, when modifying the basic face model data, modifications can be made through feature point localization. Feature points can be divided into localization feature points and fine-tuning feature points. For example, when modifying the eyes using feature points, the corners of the eyes and eyelids are used as localization feature points, which can basically determine the approximate shape of the entire eye. Fine-tuning feature points can represent the details of the eyes. After determining the localization feature points, fine-tuning can be completed, which improves the convenience and accuracy of modifying the basic face model data.

[0022] Preferably, the inherited model data includes UV information, which is used to locate the texture map of the face model.

[0023] By adopting the above technical solution, UV information records the relative position information of texture maps. The main function of UV information is to locate the texture position of the model. By inheriting UV information, the facial features in the basic face model and the custom face model can be relatively unified, thereby improving the accuracy of converting the basic face model into a custom face model.

[0024] Preferably, the inherited data of the basic face model is consistent with the inherited data of the custom face model.

[0025] By adopting the above technical solution, the inherited data of the basic face model is consistent with the inherited data of the custom face model. On the one hand, this improves the accuracy of converting the basic face model into a custom face model, and on the other hand, it increases the production speed of digital humans.

[0026] Preferably, the modification of the calibration section also includes the following steps:

[0027] Obtain the calibration data of the basic face model;

[0028] Compare the outline proportions of the base face model and the custom face model;

[0029] Obtain the inherited model data of the custom model;

[0030] The base face model is adjusted based on the custom inheritance model data.

[0031] By adopting the above technical solution, during the adjustment of calibration data, the data of the calibration part can be read in time when the contour ratio of the face changes. Since the UV information can locate the texture position of the model, the adjustable model data can be adjusted to the changed face contour, which further improves the similarity between the basic face model and the custom face model, thereby improving the realism of the digital human.

[0032] Preferably, the process of obtaining the basic face model further includes the following steps:

[0033] Obtain the UV information of the basic face model;

[0034] Compare the UV information of the base face model and the custom face model to obtain UV similarity parameters;

[0035] Compare the UV similarity parameters with a preset threshold;

[0036] If the UV similarity parameter is less than or equal to the threshold, the obtained base face model is selected.

[0037] By adopting the above technical solution, since the UV information is completely inherited, when selecting the basic face model, the UV information of the basic face model can be compared with the UV information of the custom model to select the UV model that is most similar to the custom face model. This makes the proportions of the basic face model and the custom face model closer, further improving the similarity between the produced digital human and the custom digital human.

[0038] Preferably, in comparing the UV similarity parameters with a preset threshold, the preset threshold is adjusted according to the custom face model.

[0039] By adopting the above technical solution and modifying the threshold, the proportions of facial features can be adjusted according to the usage environment of the digital human. Therefore, the digital human can not only appear in the image of a real person, but also be applied in various animations and games, thereby expanding the applicability of digital human production.

[0040] Preferably, a digital human processing device includes:

[0041] The digital human processing device includes an acquisition unit, a decomposition unit, a modification unit, and a combination unit;

[0042] The acquisition unit is used to acquire a basic face model;

[0043] The decomposition unit is used to decompose the basic face model after the acquisition unit acquires the basic face model to obtain basic face model data.

[0044] The modification unit is used to modify the basic face model data;

[0045] The combining unit is used to combine the modified basic face model data into a basic face model.

[0046] By adopting the above technical solution, when processing a digital human using the digital human processing method of this application, a basic face model can be obtained first through the acquisition unit, and then the basic face model can be decomposed through the decomposition unit to obtain basic face model data that represents the basic face model. Based on the data of the custom model to be generated, the basic face model data can be modified through the modification unit to make the basic face model similar to the custom face model. Subsequently, the construction of the custom model can be completed by modifying the basic model through the combination unit, which improves the convenience of digital human face construction, increases the speed of digital human face processing, and thus increases the production speed of digital humans.

[0047] In summary, this application includes at least one of the following beneficial technical effects:

[0048] 1. When processing a digital human using the digital human processing method of this application, a basic face model can be obtained first, and then the basic face model can be decomposed to obtain basic face model data that represents the basic face model. Then, based on the data of the custom model to be generated, the basic face model data can be modified to make the basic face model similar to the custom face model. Thus, the construction of the custom model can be completed by modifying the basic model, which improves the convenience of digital human face construction, increases the speed of digital human face processing, and thus increases the production speed of digital humans.

[0049] 2. When modifying basic facial model data, modifications can be made through feature point localization. Feature points can be divided into localization feature points and fine-tuning feature points. For example, when modifying the eyes using feature points, the corners of the eyes and eyelids are used as localization feature points, which can basically determine the approximate shape of the entire eye. Fine-tuning feature points can represent the details of the eyes. After determining the localization feature points, fine-tuning can be completed, which improves the convenience and accuracy of modifying basic facial model data.

[0050] 3. During the adjustment of calibration data, the data from the calibration section can be read in time to detect changes in the proportions of the face contour. Since UV information can locate the texture position of the model, the adjustable model data can be adjusted to the changed face contour, further improving the similarity between the basic face model and the custom face model, thereby enhancing the realism of the digital human. Attached Figure Description

[0051] Figure 1 This is a schematic diagram of the overall process provided in this application.

[0052] Figure 2 yes Figure 1 A schematic diagram of the unfolding process of step S100.

[0053] Figure 3 yes Figure 1 A schematic diagram of the unfolding process of step S103.

[0054] Figure 4 yes Figure 3 A schematic diagram of the unfolding process of step S203.

[0055] Figure 5 This is a schematic diagram of the overall structure of a digital human processing device according to this application.

[0056] Figure 6 This is a schematic diagram of the structure of the electronic device that implements the digital human processing flow in this application.

[0057] Explanation of reference numerals in the attached drawings: 1. Determine unit; 2. Modify unit; 3. Obtain unit; 4. Compare unit; 5. Combine unit; 6. Decompose unit; 1000. Electronic device; 1001. Processor; 1002. Communication bus; 1003. User interface; 1004. Network interface; 1005. Memory. Detailed Implementation

[0058] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0059] In the description of the embodiments in this application, words such as "illustrative," "for example," or "for example" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "illustrative," "for example," or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Rather, the use of words such as "illustrative," "for example," or "for example" is intended to present the relevant concepts in a specific manner.

[0060] In the description of the embodiments of this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, B existing alone, or A and B existing simultaneously. Furthermore, unless otherwise stated, the term "multiple" means two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the indicated technical features. Thus, a feature defined with "first" or "second" may explicitly or implicitly include one or more of that feature. The terms "comprising," "including," "having," and their variations all mean "including but not limited to," unless otherwise specifically emphasized.

[0061] The following is an explanation of some terms used in this application:

[0062] Base face model: denoted as the selected base face model body, specifically the selected model in MetahumanCreator in this embodiment.

[0063] Custom face model: A pre-created ideal model, which can be achieved through hand-drawing, animation, or simulation scanning. In this embodiment, it is the target model that needs to be modified from the base model.

[0064] Inherited model data: In this embodiment of the application, inherited model data refers to quantities that are not adjusted or changed in the transition from the basic face model to the custom face model, such as UV values.

[0065] UV information refers to UV coordinates, which means that all image files are two-dimensional planes. The horizontal direction is U, and the vertical direction is V. Through this two-dimensional UV coordinate system, any pixel on the image can be located.

[0066] The following is in conjunction with the appendix Figure 1-6 This application will be described in further detail.

[0067] This application discloses a method for processing digital humans. (Refer to...) Figure 1 It includes S100-S104:

[0068] S100, Obtain the basic face model;

[0069] In this embodiment of the application, Metahuman Creator is selected as the basis to complete the creation of digital humans. However, using Metahuman Creator as the basis is only one of the ways to create digital humans. Other software that can achieve similar effects to Metahuman Creator can also be applied to the digital human processing method of this application, which will not be elaborated here.

[0070] In Metahuman Creator, you can choose its preset digital human model as the base model.

[0071] Reference Figure 2 In one possible implementation, the process of obtaining the basic face model further includes steps S400-S403;

[0072] S400: Obtain the UV information of the basic face model;

[0073] However, due to the significant differences and rich variety of facial expressions, linear facial models in three-dimensional space are subject to many limitations. Therefore, a UV location map is used to map the three-dimensional coordinates of facial key points to UV coordinates in UV space, storing the three-dimensional coordinates on a two-dimensional image, thus achieving a three-dimensional to two-dimensional mapping. Therefore, the UV location map P(ui,vi) can be represented as...

[0074] P(ui,vi) = (xi,yi,zi)

[0075] Here, (ui,vi) represents the UV coordinates of the i-th vertex in the 3D face model, and (xi,yi,zi) represents the 3D spatial coordinates of that vertex; simultaneously, (xi,yi) represents the pixel position on the input 2D image, and zi represents the depth of that point. Since (ui,vi) and (xi,yi) correspond to the same point on the face model, this representation method can preserve alignment information.

[0076] When obtaining the UV information of the basic face model, the facial features of the basic face can be selected, and the basic face can be used as the UV space. The facial features of the basic face can be located by UV coordinates, and recorded as the UV information of the basic face model.

[0077] In addition to locating facial features, facial muscles and bones can also be used as references. Different references are determined based on the convenience and accuracy required in actual use, which will not be elaborated here.

[0078] S401. Compare the UV information of the basic face model and the custom face model to obtain UV similarity parameters;

[0079] The original UV space is transformed based on the ratio of the length to the width of the custom face model, so that the current UV space is suitable for the custom face model without changing the UV coordinates; the ratio of the current UV space to the original UV space is recorded as the UV similarity parameter.

[0080] S402. Compare the UV similarity parameters with the preset threshold.

[0081] The preset threshold can be changed according to the application scenario of the digital human. For example, when the digital human is required to be as close as possible to a real human image, the threshold is gradually reduced; when the digital human can be an anime character or a digital human character with exaggerated facial proportions, the threshold is gradually increased.

[0082] S403. If the UV similarity parameter is less than or equal to the threshold, then the obtained basic face model shall be selected.

[0083] S101. Decompose the basic face model to obtain basic face model data. The basic face model data is divided into adjustable model data and inherited model data. The adjustable model data includes subjective adjustment part and calibration part.

[0084] S102. Obtain preset custom face model data.

[0085] In acquiring custom face model data, the custom face model data can be mapped to the basic face model data. That is, the custom face model data is divided into adjustable model data and inherited model data. The adjustable model data is the target data for modifying the basic face model data, and the inherited model data is the UV coordinates. The custom face model data and the inherited model data of the basic face model data are consistent.

[0086] S103. Modify the basic face data based on the custom face model data to obtain the current basic face data;

[0087] Reference Figure 3 In one possible implementation, when modifying the subjective adjustment portion in the adjustable model data, steps S200-S203 are also included.

[0088] S200. Obtain the feature points of the subjective adjustment part, including the positioning feature points and the fine-tuning feature points.

[0089] In the basic face model, the adjustable model data includes facial features, which can be specifically divided into teeth and eyeballs, cornea and eyelashes, and facial bone information. In this embodiment, Houdini software is used to modify and adjust the adjustable model data. Houdini software can parametrically decompose facial features, breaking down the original facial feature model into multiple basic geometric shapes. These geometric shapes are then further decomposed into several polygonal units. Using conventional modeling methods, these polygonal units are further simplified into combinations of points, lines, and surfaces. By adjusting the corresponding nodes of each point, line, and surface, the overall shape of the geometric shape can be changed.

[0090] S201. Determine the feature points of the subjective adjustment part and the feature points of the custom face model data.

[0091] S202. Adjust the positioning feature points of the subjective adjustment part according to the feature points of the custom face model data.

[0092] In this application, the facial features of both the basic face model and the custom face model can be parametrically decomposed using Houdini software. By mapping each node on the basic face model to each node on the custom face model, changes to the adjustable model data on the basic face model can be quickly achieved.

[0093] S203. Adjust the position of the fine-tuning feature points based on the adjustment results of the localization feature points.

[0094] When Houdini software decomposes too many feature points, some feature points that determine the shape of facial features are adjusted. Specifically, when adjusting the eyes, only the corners of the eyes and the positions of the eyelids can be adjusted. At this time, the feature points that locate the corners of the eyes and the positions of the eyelids are the positioning feature points, and the remaining feature points are the fine-tuning specific points. After locating the general shape of the eyes, the fine-tuning feature points around the eyes are then adjusted, thereby reducing the system's calculation steps and speeding up the digital human production process.

[0095] Reference Figure 4 In one possible implementation, when modifying the calibration portion of the adjustable model data, steps S300-S302 are included.

[0096] S300: Obtain data from the calibration portion of the basic face model;

[0097] The calibration data of the basic face model is the UV coordinates of the basic face model, which are used to locate the facial features of the basic face model.

[0098] S301. Compare the outline proportions of the basic face model and the custom face model;

[0099] That is, the original UV space is transformed according to the ratio of the length and width of the custom face model, so that the current UV space is suitable for the custom face model while the UV coordinates remain unchanged.

[0100] S302. Adjust the basic face model based on the custom inherited model data.

[0101] While keeping the coordinates of the facial features unchanged, the UV space of the base face model is modified, that is, the face of the base face model is stretched while keeping the relative positions of the facial features unchanged.

[0102] S104. Combine the current basic face model data to obtain the current basic face model.

[0103] The digital human's face is recombined based on UV coordinates and facial features from the modified base face model to obtain a base face model that is similar to the custom face model. Metahuman Creator is then used to further modify the modified base face model to meet the digital human's facial requirements.

[0104] Reference Figure 5 A digital human processing device includes an acquisition unit 3, a decomposition unit 6, a modification unit 2, a combination unit 5, a comparison unit 4, and a determination unit 1.

[0105] Acquisition Unit 3 is used to acquire the basic face model;

[0106] Decomposition Unit 6: After the acquisition unit 3 acquires the basic face model data, the decomposition unit 6 decomposes the basic face model to obtain the basic face model data.

[0107] In one possible implementation, the acquisition unit 3 can also be used to acquire preset custom face model data;

[0108] Modify Unit 2, which can modify the base face model data based on the custom face model data to obtain the current base face model data;

[0109] Combination unit 5 combines the current basic face model data to obtain the current basic face model, so as to obtain a digital face based on the current basic face model.

[0110] The acquisition unit 3 can also be used to acquire feature points of the subjective adjustment part, including positioning feature points and fine-tuning feature points;

[0111] Unit 1 is used to determine the feature points of the subjective adjustment part and the feature points of the custom face model data;

[0112] Modify Unit 2. Modify Unit 2 can also adjust the positioning feature points of the subjective adjustment part according to the feature points of the custom face model data; and change the position of the fine-tuning feature points based on the adjustment results of the positioning feature points.

[0113] In one possible implementation, the acquisition unit 3 can also be used to acquire data from the calibration portion of the basic face model;

[0114] Comparison unit 4 is used to compare the contour ratios of the basic face model and the custom face model;

[0115] Unit 3 can also be used to obtain inherited model data of custom models;

[0116] Modification Unit 2 adjusts the basic face model based on custom inherited model data.

[0117] In one possible implementation, the acquisition unit 3 can also acquire the UV information of the basic face model;

[0118] Comparison unit 4 can be used to compare the UV information of a basic face model and a custom face model to obtain UV similarity parameters; comparison unit 4 can also compare the UV similarity parameters with a preset threshold.

[0119] If the UV similarity parameter is less than or equal to the threshold, then Unit 1 determines the acquired basic face model.

[0120] This application provides a schematic diagram of the structure of an electronic device. For example... Figure 6 As shown, the electronic device 1000 may include: at least one processor 1001, at least one network interface 1004, a user interface 1003, a memory 1005, and at least one communication bus 1002.

[0121] The communication bus 1002 is used to realize the connection and communication between these components.

[0122] The user interface 1003 may include a display screen and a camera. Optionally, the user interface 1003 may also include a standard wired interface and a wireless interface.

[0123] The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface).

[0124] The processor 1001 may include one or more processing cores. The processor 1001 connects to various parts within the server 1000 using various interfaces and lines, and performs various functions and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 1005, and by calling data stored in the memory 1005. Optionally, the processor 1001 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). The processor 1001 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content required for display; and the modem handles wireless communication. It is understood that the modem may also be implemented as a separate chip without being integrated into the processor 1001.

[0125] The memory 1005 may include random access memory (RAM) or read-only memory. Optionally, the memory 1005 may include a non-transitory computer-readable storage medium. The memory 1005 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 1005 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 1005 may also be at least one storage device located remotely from the aforementioned processor 1001. Figure 6 As shown, the memory 1005, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an application program for a digital human processing method.

[0126] It should be noted that the above embodiments of the apparatus are only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the apparatus and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process can be found in the method embodiments, which will not be repeated here.

[0127] exist Figure 6 In the electronic device 1000 shown, the user interface 1003 is mainly used to provide an input interface for the user and to obtain the user input data; while the processor 1001 can be used to call an application program stored in the memory 1005 for a digital human processing method. When executed by one or more processors, the electronic device performs one or more of the methods described in the above embodiments.

[0128] An electronic device readable storage medium stores instructions that, when executed by one or more processors, cause the electronic device to perform one or more of the methods described in the above embodiments.

[0129] Those skilled in the art will clearly understand that the technical solutions of this application can be implemented using software and / or hardware. In this specification, "unit" and "module" refer to software and / or hardware capable of independently performing or cooperating with other components to perform specific functions. Hardware may include, for example, a Field-Programmable Gate Array (FPGA), an Integrated Circuit (IC), etc.

[0130] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0131] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0132] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some service interface; the indirect coupling or communication connection between devices or units may be electrical or other forms.

[0133] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0134] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0135] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0136] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc.

[0137] The foregoing description is merely an exemplary embodiment of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. Other embodiments of this disclosure will be readily apparent to those skilled in the art upon consideration of the specification and practice of the disclosure 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 described herein. The specification and embodiments are to be considered exemplary only, and the scope and spirit of this disclosure are defined by the claims.

[0138] The above are all preferred embodiments of this application, and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the structure, shape and principle of this application should be covered within the scope of protection of this application.

Claims

1. A method for processing digital humans, applied in a terminal device, characterized in that: include: Obtain a basic face model; Determine the basic face model data, which is obtained by decomposing the basic face model; Obtain preset custom face model data; Modify the base face model data based on the custom face model data to obtain the current base face model data; Combine the current basic face model data to obtain the current basic face model, so as to obtain a digital face based on the current basic face model; When decomposing the basic face model, the basic face model data is divided into adjustable model data and inherited model data. The adjustable model data includes a subjective adjustment part and a calibration part. The subjective adjustment part includes the shape of facial features, and the calibration part includes the facial proportions and the position of the mouth. When modifying the base face model data based on the custom face model, the following steps are included: Acquire feature points of the subjective adjustment portion, including positioning feature points and fine-tuning feature points; Determine the feature points of the subjective adjustment portion and the feature points of the custom face model data; The positioning feature points of the subjective adjustment part are adjusted based on the feature points of the custom face model data; The position of the fine-tuning feature points is changed based on the adjustment results of the localized feature points. The process of obtaining the basic face model also includes the following steps: Obtain the UV information of the basic face model; Compare the UV information of the base face model and the custom face model to obtain UV similarity parameters; Compare the UV similarity parameters with a preset threshold; If the UV similarity parameter is less than or equal to the threshold, the obtained base face model is selected. The inherited model data includes UV information, which is used to locate the texture map of the face model.

2. The method for processing a digital human according to claim 1, characterized in that: The inherited data of the basic face model is consistent with the inherited data of the custom face model.

3. The method for processing a digital human according to claim 1, characterized in that: In comparing the UV similarity parameters with a preset threshold, the preset threshold is adjusted according to the custom face model.

4. A digital human processing device, applied in any one of claims 1-3, comprising: The digital human processing device includes an acquisition unit (3), a decomposition unit (6), a modification unit (2), and a combination unit (5); The acquisition unit (3) is used to acquire a basic face model; The decomposition unit (6) is used to decompose the basic face model after the acquisition unit (3) acquires the basic face model to obtain the basic face model data. The modification unit (2) is used to modify the basic face model data; The combination unit (5) is used to combine the modified basic face model data into a basic face model.

5. An electronic device (1000), characterized in that, The device includes a processor (1001), a memory (1005), and a transceiver. The memory (1005) is used to store instructions, the transceiver is used to communicate with other devices, and the processor (1001) is used to execute the instructions stored in the memory (1005) to cause the electronic device (1000) to perform the method as described in any one of claims 1-3.

Images