CN114998554A - Three-dimensional cartoon face modeling method and device - Google Patents

Abstract

The present application discloses a three-dimensional cartoon face modeling method and device, wherein the method includes: extracting two-dimensional face features of a target person's face in a two-dimensional image; Face features; fuse 2D face features, 3D face features and preset cartoon style features to generate a 3D cartoon face model of the target face. As a result, the technical problem of the cartoon image modeling of the real face based on the neural network in the related art, resulting in a single style and low recognition degree of the generated cartoon image, is solved.

Description

Three-dimensional cartoon face modeling method and device

technical field

The present application relates to the technical field of computer graphics and deep learning, and in particular, to a method and device for modeling a three-dimensional cartoon face.

Background technique

3D reconstruction has a wide range of applications in 3D games, animation, movies and many other fields. As one of the main and most recognizable parts, the demand for 3D face reconstruction is getting higher and higher.

Thanks to the improvement of computing power of computers and mobile terminals, the extraction technology of real face features using deep learning tends to mature, and related technologies can generate cartoon images of real faces based on neural networks.

However, the related technology can only be manually modeled by professional technicians, which is difficult to popularize, and the generated 3D cartoon face models are similar in style, unable to achieve diversification, and have no real face recognition, which needs improvement.

SUMMARY OF THE INVENTION

The present application provides a three-dimensional cartoon face modeling method and device to solve the technical problem in the related art that the cartoon image modeling of the real face based on the neural network results in a single style and low recognition degree of the generated cartoon image.

The embodiment of the first aspect of the present application provides a three-dimensional cartoon face modeling method, including the following steps: extracting two-dimensional face features of a target person's face in a two-dimensional image; The three-dimensional face feature of the face; and the three-dimensional cartoon face model of the target face is generated by fusing the two-dimensional face feature, the three-dimensional face feature and the preset cartoon style feature.

Optionally, in an embodiment of the present application, the generating the 3D cartoon face model of the target face includes: The fusion feature obtained by fusion of style features generates an initial three-dimensional cartoon face model of the target face; calculates the degree of presentation of the initial three-dimensional cartoon face model, and when the degree of presentation is less than a preset threshold, based on a preset standard Linearly weighting at least one of the two-dimensional face feature, the three-dimensional face feature and the preset cartoon style feature to generate a new three-dimensional cartoon face model, and iteratively optimize until the new three-dimensional cartoon face The presentation degree of the model is greater than or equal to the preset threshold, and a final three-dimensional cartoon face model is obtained.

Optionally, in an embodiment of the present application, after generating the new three-dimensional cartoon face model, the method further includes: acquiring a current feature weight value of at least one feature under the current iteration round; according to the current feature weight value and the presentation degree of the new 3D cartoon face model in the previous iteration round to obtain the presentation degree of the new 3D cartoon face model in the current iteration round.

Optionally, in an embodiment of the present application, the calculation formula of the presentation degree is:

Among them, K represents the total number of features strongly related to character recognition, M represents the total number of features strongly related to the character satisfaction index, T _V is the degree to which the original features are presented in the model before the V-th iteration, and a represents the character recognition The proportion of the final feature presentation, 1-a represents the proportion of the character satisfaction to the final feature presentation, D _V (k) is the proportion of each feature in the V round of recognition, S _V (m) is the proportion of each feature in the satisfaction in the V round.

Optionally, in an embodiment of the present application, the preset cartoon style features include at least one of at least one Disney cartoon style feature, at least one Japanese cartoon style feature, and at least one Meta cartoon style feature.

An embodiment of the second aspect of the present application provides a three-dimensional cartoon face modeling device, including: a first extraction module for extracting two-dimensional face features of a target person's face in a two-dimensional image; a second extraction module for using extracting the three-dimensional face feature of the face according to the three-dimensional depth map of the target person; and a modeling module for fusing the two-dimensional face feature, the three-dimensional face feature and the preset cartoon style feature, A three-dimensional cartoon face model of the target face is generated.

Optionally, in an embodiment of the present application, the modeling module includes: a fusion unit, which is configured to obtain according to the fusion of the two-dimensional face feature, the three-dimensional face feature and the preset cartoon style feature. Fusing the features to generate an initial three-dimensional cartoon face model of the target face; a computing unit for calculating the presentation degree of the initial three-dimensional cartoon face model, and when the presentation degree is less than a preset threshold, based on a preset standard Linearly weighting at least one of the two-dimensional face feature, the three-dimensional face feature and the preset cartoon style feature to generate a new three-dimensional cartoon face model, and iteratively optimize until the new three-dimensional cartoon face The presentation degree of the model is greater than or equal to the preset threshold, and a final three-dimensional cartoon face model is obtained.

Optionally, in an embodiment of the present application, the modeling module is further configured to obtain a current feature weight value of at least one feature under the current iteration round; according to the current feature weight value and the previous iteration The presentation degree of the new 3D cartoon face model under the round is obtained from the presentation degree of the new 3D cartoon face model of the current iteration round.

Optionally, in an embodiment of the present application, the calculation formula of the presentation degree is:

Among them, K represents the total number of features strongly related to character recognition, M represents the total number of features strongly related to the character satisfaction index, T _V is the degree to which the original features are presented in the model before the V-th iteration, and a represents the character recognition The proportion of the final feature presentation, 1-a represents the proportion of the character satisfaction to the final feature presentation, D _V (k) is the proportion of each feature in the V round of recognition, S _V (m) is the proportion of each feature in the satisfaction in the V round.

Optionally, in an embodiment of the present application, the preset cartoon style features include at least one of at least one Disney cartoon style feature, at least one Japanese cartoon style feature, and at least one Meta cartoon style feature.

An embodiment of a third aspect of the present application provides an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the program to achieve The three-dimensional cartoon face modeling method described in the above embodiment.

Embodiments of the fourth aspect of the present application provide a computer-readable storage medium, where the computer-readable storage medium stores computer instructions, and the computer instructions are used to cause the computer to execute the three-dimensional cartoon face reconstruction method described in the foregoing embodiments. model method.

In the embodiment of the present application, the three-dimensional face feature of the target person can be extracted by using the three-dimensional depth map, and the two-dimensional face feature and cartoon style feature in the two-dimensional image of the target person can be combined to generate a three-dimensional cartoon face model of the target face, so that The generated 3D face model has a higher degree of recognition, and can change the style with the change of cartoon style, with higher flexibility, which can effectively meet the modeling needs and improve the user experience. As a result, the technical problem of the cartoon image modeling of the real face based on the neural network in the related art, resulting in a single style and low recognition degree of the generated cartoon image, is solved.

Additional aspects and advantages of the present application will be set forth, in part, in the following description, and in part will be apparent from the following description, or learned by practice of the present application.

Description of drawings

The above and/or additional aspects and advantages of the present application will become apparent and readily understood from the following description of embodiments taken in conjunction with the accompanying drawings, wherein:

1 is a flowchart of a method for modeling a three-dimensional cartoon face according to an embodiment of the present application;

2 is a schematic diagram of a Meta cartoon style according to an embodiment of the present application;

3 is a flowchart of a method for modeling a three-dimensional cartoon face according to an embodiment of the present application;

4 is a schematic structural diagram of a three-dimensional cartoon face modeling apparatus provided according to an embodiment of the present application;

FIG. 5 is a schematic structural diagram of an electronic device provided according to an embodiment of the present application.

Detailed ways

The following describes in detail the embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary, and are intended to be used to explain the present application, but should not be construed as a limitation to the present application.

The following describes the three-dimensional cartoon face modeling method and apparatus according to the embodiments of the present application with reference to the accompanying drawings. Aiming at the technical problem that the cartoon image modeling of the real human face based on the neural network in the related art mentioned by the above-mentioned background technology center leads to the single style of the generated cartoon image and the low recognition degree, the present application provides a three-dimensional cartoon human face. Modeling method, in this method, the three-dimensional face features of the target person can be extracted by using the three-dimensional depth map, and the two-dimensional face features and cartoon style features in the two-dimensional image of the target person can be fused to generate a three-dimensional cartoon of the target face. The face model makes the generated 3D face model more recognizable, and can change the style with the change of cartoon style, which is more flexible, effectively meets the modeling needs and improves the user experience. As a result, the technical problem of the cartoon image modeling of the real face based on the neural network in the related art, resulting in a single style and low recognition degree of the generated cartoon image, is solved.

Specifically, FIG. 1 is a schematic flowchart of a three-dimensional cartoon face modeling method provided by an embodiment of the present application.

As shown in Figure 1, the three-dimensional cartoon face modeling method includes the following steps:

In step S101, two-dimensional face features of the target person's face in the two-dimensional image are extracted.

It can be understood that the facial features can be in the form of vectors extracted by the neural network, as well as the features representing the styles of various facial organs, representing the characteristics of a certain type of person and an organ. The extraction method, for example, can be based on deep learning. It is obtained from model training and learning, or from modeling the detailed features of facial organs. Specifically, taking eyebrows as an example, eyebrows can have long eyebrows, short eyebrows, thick eyebrows, thin eyebrows, thin eyebrows, splayed eyebrows, and raised eyebrows according to the shape of the eyebrows. Eyebrows, straight eyebrows, crescent eyebrows, corner eyebrows, frown eyebrows, etc.

In the actual execution process, the embodiment of the present application can use neural network or traditional computer graphics to extract the two-dimensional face features of the target person's face in the two-dimensional image and the two-dimensional feature operator in traditional graphics, which can be obtained from The extraction of face features from the plane angle is conducive to the subsequent fusion with 3D face features, thereby generating a more recognizable 3D face cartoon model.

In step S102, three-dimensional face features of the face are extracted according to the three-dimensional depth map of the target person.

It can be understood that the face is three-dimensional, and it is difficult to present all the facial features of the target person only by conventional two-dimensional facial feature extraction. Especially, the two-dimensional image may be limited by light and shadow effects, resulting in The recognition degree of the contour is poor. The three-dimensional feature refers to the feature obtained after processing the three-dimensional depth map. The extraction method is similar to the two-dimensional feature. Representation techniques for feature extraction, the form is slightly different from 2D.

Therefore, the embodiment of the present application uses traditional computer graphics to extract the three-dimensional face features of the target person according to the three-dimensional depth map of the target person, that is, the three-dimensional feature operator in traditional graphics, which can effectively remove the face feature extraction from the two-dimensional image. The limitation of , which is convenient for the subsequent generation of a more recognizable 3D face cartoon model.

In step S103, the two-dimensional face feature, the three-dimensional face feature and the preset cartoon style feature are combined to generate a three-dimensional cartoon face model of the target face.

As a possible way of implementation, the embodiment of the present application can extract corresponding key features from two-dimensional face features and three-dimensional face features, respectively, and combine the key features extracted from the two-dimensional face features and the three-dimensional face features. The corresponding key features extracted from the face features and the preset cartoon style features are fused to obtain a three-dimensional cartoon face model with a specific style of the target face that is more in line with the target character image.

Among them, the key feature refers to a feature that has higher character recognition and character satisfaction for the final presented 3D cartoon face model, and is consistent with the cartoon style. The three features, namely 2D facial features, 3D facial features and preset cartoon style features, each contain different specific feature families, each feature represents a certain feature of the facial organs of the human face, and the specific fusion method is through The weighting method controls the degree of display of different features in the final face modeling results, so that the representative features of a certain person are prominently displayed, and other secondary features are relatively weakened, which meets the requirements of the identification index.

In the embodiment of the present application, by fusing two-dimensional face features, three-dimensional face features and preset cartoon style features, the generated three-dimensional face model has a higher degree of recognition, and can change the style according to the change of cartoon style, flexibly The higher the degree, the higher the character satisfaction.

Optionally, in an embodiment of the present application, generating a 3D cartoon face model of the target face includes: generating according to fusion features obtained by fusing 2D face features, 3D face features and preset cartoon style features. The initial 3D cartoon face model of the target face; calculate the presentation degree of the initial 3D cartoon face model, and when the presentation degree is less than a preset threshold, analyze the 2D face features, 3D face features and presets based on preset criteria At least one feature in the cartoon style features is linearly weighted to generate a new three-dimensional cartoon face model, and iteratively optimizes until the rendering degree of the new three-dimensional cartoon face model is greater than or equal to a preset threshold, and the final three-dimensional cartoon face model is obtained.

In the actual execution process, the embodiment of the present application can obtain the fusion feature by fusing the two-dimensional face feature, the three-dimensional face feature and the preset cartoon style feature, thereby generating the initial three-dimensional cartoon face model of the target character.

Further, the embodiment of the present application can optimize the initial three-dimensional cartoon face model by calculation. Specifically, the embodiment of the present application can calculate the presentation degree of the initial three-dimensional cartoon face model. When the presentation degree is less than a preset threshold, the present application The embodiment can linearly weight at least one of the two-dimensional face features, the three-dimensional face features, and the preset cartoon style features based on preset criteria, and then generate a new three-dimensional cartoon face model, and realize iterative optimization until the new three-dimensional The rendering degree of the cartoon face model is greater than or equal to the preset threshold, and the final three-dimensional cartoon face model is obtained.

Among them, the preset standard can be the standard of character recognition and character satisfaction. Specifically, the level of recognition and satisfaction is to serve the target group, and the former is measured by the loss of the key features of the input image and the output model. , the latter is based on the research of the target group, such as the score of the results on the questionnaire, in addition, when the two contradict each other, the character satisfaction is the main factor.

It should be noted that the preset threshold can be set correspondingly by those skilled in the art according to the actual situation; the preset standard can be set correspondingly by those skilled in the art according to the application scene of the 3D cartoon face model and the research results of the target audience, which is not described here. make specific restrictions.

Optionally, in an embodiment of the present application, the calculation formula of the presentation degree is:

Among them, K represents the total number of features strongly related to character recognition, M represents the total number of features strongly related to the character satisfaction index, T _V is the degree to which the original features are presented in the model before the V-th iteration, and a represents the character recognition The proportion of the final feature presentation, 1-a represents the proportion of the character satisfaction to the final feature presentation, D _V (k) is the proportion of each feature in the V round of recognition, S _V (m) is the proportion of each feature in the satisfaction in the V round.

Further, the items in parentheses, namely:

is the updated value of the weight occupied by each facial feature in the Vth round. After applying the updated value of each feature weight to the feature presentation degree T _V of the previous round, the degree t of the original feature in the model after the V round of iteration is obtained. _V.

Optionally, in an embodiment of the present application, after generating a new three-dimensional cartoon face model, the method further includes: acquiring a current feature weight value of at least one feature under the current iteration round; The presentation degree of the new 3D cartoon face model in the iteration round is obtained from the presentation degree of the new 3D cartoon face model in the current iteration round.

Specifically, with reference to the above formula, in the embodiment of the present application, the linear weighting of the V-th round of iterations can be performed according to the criteria of character recognition and character satisfaction for each key feature, and then each feature weight value under the V-th round can be obtained, and further , in this embodiment of the present application, the change value may be multiplied by the degree presentation value of the previous round to obtain the presentation value of the next round.

Optionally, in an embodiment of the present application, the preset cartoon style features include at least one of at least one Disney cartoon style feature, at least one Japanese cartoon style feature, and at least one Meta cartoon style feature.

In some embodiments, the preset cartoon style may be, but is not limited to, Disney cartoon style, Japanese cartoon style or Meta cartoon style. For example, as shown in FIG. 2 , it is Meta cartoon style, Zuckerberg on the right side, and Zuckerberg on the left side. The side is a cartoon image generated based on Zuckerberg's facial features.

In this embodiment of the present application, corresponding style features can be extracted from the above styles as preset cartoon style features, and fused with 2D face features and 3D face features, thereby generating a 3D face cartoon model with a specific style.

It should be noted that the preset cartoon style features can be set correspondingly by those skilled in the art according to actual needs, such as application scenarios of the 3D face cartoon model or group survey results, etc., which are not specifically limited here.

The working principle of the three-dimensional cartoon face modeling method according to the embodiment of the present application will be described in detail below with reference to FIG. 3 .

As shown in Figure 3, the embodiment of the present application includes the following steps:

Step S301: Extract the two-dimensional image features of the target person. It can be understood that the facial features can be in the form of vectors extracted by the neural network, as well as the features representing the styles of various facial organs, representing the characteristics of a certain type of person and an organ. The extraction method, for example, can be based on deep learning. It is obtained from model training and learning, or from modeling the detailed features of facial organs. Specifically, taking eyebrows as an example, eyebrows can have long eyebrows, short eyebrows, thick eyebrows, thin eyebrows, thin eyebrows, splayed eyebrows, and raised eyebrows according to the shape of the eyebrows. Eyebrows, straight eyebrows, crescent eyebrows, corner eyebrows, frown eyebrows, etc.

In the actual execution process, the embodiment of the present application can use neural network or traditional computer graphics to extract the two-dimensional face features of the target person's face in the two-dimensional image and the two-dimensional feature operator in traditional graphics, which can be obtained from The extraction of face features from the plane angle is conducive to the subsequent fusion with 3D face features, thereby generating a more recognizable 3D face cartoon model.

Step S302: Extract the three-dimensional image features of the target person. It can be understood that the face is three-dimensional, and it is difficult to present all the facial features of the target person only by conventional two-dimensional facial feature extraction. Especially, the two-dimensional image may be limited by light and shadow effects, resulting in The recognition degree of the contour is poor. The three-dimensional feature refers to the feature obtained after processing the three-dimensional depth map. The extraction method is similar to the two-dimensional feature. Representation techniques for feature extraction, the form is slightly different from 2D.

Therefore, the embodiment of the present application uses traditional computer graphics to extract the three-dimensional face features of the target person according to the three-dimensional depth map of the target person, that is, the three-dimensional feature operator in traditional graphics, which can effectively remove the face feature extraction from the two-dimensional image. The limitation of , which is convenient for the subsequent generation of a more recognizable 3D face cartoon model.

Step S303: Extract cartoon style features. In some embodiments, the cartoon style may be Disney cartoon style, Japanese cartoon style or Meta cartoon style, etc. For example, as shown in FIG. 2 , it is Meta cartoon style, the right side is Zuckerberg, the left side is the A cartoon image of Zuckerberg's facial features. In this embodiment of the present application, corresponding style features can be extracted from the above styles as preset cartoon style features, and fused with 2D face features and 3D face features, thereby generating a 3D face cartoon model with a specific style.

It should be noted that the cartoon style can be set accordingly by those skilled in the art according to actual needs, such as the application scenarios of the three-dimensional face cartoon model or the results of group research, etc., which is not specifically limited here.

Step S304: Feature fusion to generate an initial three-dimensional face cartoon model. As a possible way of implementation, the embodiment of the present application can extract corresponding key features from two-dimensional face features and three-dimensional face features, respectively, and combine the key features extracted from the two-dimensional face features and the three-dimensional face features. The corresponding key features extracted from the face features and the preset cartoon style features are fused to obtain a three-dimensional cartoon face model with a specific style of the target face that is more in line with the target character image.

Among them, the key feature refers to a feature that has higher character recognition and character satisfaction for the final presented 3D cartoon face model, and is consistent with the cartoon style. The three features, namely 2D facial features, 3D facial features and preset cartoon style features, each contain different specific feature families, each feature represents a certain feature of the facial organs of the human face, and the specific fusion method is through The weighting method controls the degree of display of different features in the final face modeling results, so that the representative features of a certain person are prominently displayed, and other secondary features are relatively weakened, which meets the requirements of the identification index.

In the embodiment of the present application, by fusing two-dimensional face features, three-dimensional face features and preset cartoon style features, the generated three-dimensional face model has a higher degree of recognition, and can change the style according to the change of cartoon style, flexibly The higher the degree, the higher the character satisfaction.

Step S305: Perform iterative optimization on the initial three-dimensional face cartoon model to obtain a final three-dimensional face cartoon model. Further, the embodiment of the present application can optimize the initial three-dimensional cartoon face model by calculation. Specifically, the embodiment of the present application can calculate the presentation degree of the initial three-dimensional cartoon face model. When the presentation degree is less than a preset threshold, the present application The embodiment can linearly weight at least one of the two-dimensional face features, the three-dimensional face features, and the preset cartoon style features based on preset criteria, and then generate a new three-dimensional cartoon face model, and realize iterative optimization until the new three-dimensional The rendering degree of the cartoon face model is greater than or equal to the preset threshold, and the final three-dimensional cartoon face model is obtained.

Among them, the preset standard can be the standard of character recognition and character satisfaction. Specifically, the level of recognition and satisfaction is to serve the target group, and the former is measured by the loss of the key features of the input image and the output model. , the latter is based on the research of the target group, such as the score of the results on the questionnaire, in addition, when the two contradict each other, the character satisfaction is the main factor.

The formula for calculating the degree of presentation is:

Among them, K represents the total number of features strongly related to character recognition, M represents the total number of features strongly related to the character satisfaction index, T _V is the degree to which the original features are presented in the model before the V-th iteration, and a represents the character recognition The proportion of the final feature presentation, 1-a represents the proportion of the character satisfaction to the final feature presentation, D _V (k) is the proportion of each feature in the V round of recognition, S _V (m) is the proportion of each feature in the satisfaction in the V round.

Further, the items in parentheses, namely:

is the updated value of the weight occupied by each facial feature in the Vth round. After applying the updated value of each feature weight to the feature presentation degree T _V of the previous round, the degree t of the original feature in the model after the V round of iteration is obtained. _V.

Further, in this embodiment of the present application, the linear weighting of the V-th round of iterations can be performed according to the criteria of character recognition degree and character satisfaction for each key feature, and then each feature weight value under the V-th round can be obtained. Further, the present application implements For example, this change value can be multiplied by the degree present value of the previous round to obtain the present value of the next round.

It should be noted that the preset threshold can be set correspondingly by those skilled in the art according to the actual situation; the preset standard can be set correspondingly by those skilled in the art according to the application scene of the 3D cartoon face model and the research results of the target audience, which is not described here. make specific restrictions.

According to the 3D cartoon face modeling method proposed in this embodiment of the present application, the 3D depth map can be used to extract the 3D facial features of the target person, and the 2D facial features and cartoon style features in the 2D image of the target person can be fused to generate The 3D cartoon face model of the target face makes the generated 3D face model more recognizable, and can change the style with the change of cartoon style, which is more flexible, effectively meets the modeling needs and improves the user experience. . As a result, the technical problem of the cartoon image modeling of the real face based on the neural network in the related art, resulting in a single style and low recognition degree of the generated cartoon image, is solved.

Next, the three-dimensional cartoon face modeling apparatus proposed according to the embodiments of the present application will be described with reference to the accompanying drawings.

FIG. 4 is a schematic block diagram of a three-dimensional cartoon face modeling apparatus according to an embodiment of the present application.

As shown in FIG. 4 , the three-dimensional cartoon face modeling apparatus 10 includes: a first extraction module 100 , a second extraction module 200 and a modeling module 300 .

Specifically, the first extraction module 100 is configured to extract the two-dimensional face features of the target person's face in the two-dimensional image.

The second extraction module 200 is configured to extract the three-dimensional face features of the face according to the three-dimensional depth map of the target person.

The modeling module 300 is used for fusing two-dimensional face features, three-dimensional face features and preset cartoon style features to generate a three-dimensional cartoon face model of the target face.

Optionally, in an embodiment of the present application, the modeling module 300 includes: a fusion unit and a computing unit.

Wherein, the fusion unit is used to generate an initial 3D cartoon face model of the target face according to the fusion feature obtained by fusing the 2D face feature, the 3D face feature and the preset cartoon style feature.

The calculation unit is used to calculate the presentation degree of the initial three-dimensional cartoon face model, and when the presentation degree is less than the preset threshold, based on the preset standard, at least one of the two-dimensional face features, the three-dimensional face features and the preset cartoon style features is evaluated. A feature is linearly weighted to generate a new 3D cartoon face model, and iteratively optimize until the rendering degree of the new 3D cartoon face model is greater than or equal to a preset threshold, and the final 3D cartoon face model is obtained.

Optionally, in an embodiment of the present application, the modeling module 300 is further configured to obtain the current feature weight value of at least one feature under the current iteration round; The presentation degree of the 3D cartoon face model is obtained from the presentation degree of the new 3D cartoon face model in the current iteration round.

Optionally, in an embodiment of the present application, the calculation formula of the presentation degree is:

Among them, K represents the total number of features strongly related to character recognition, M represents the total number of features strongly related to the character satisfaction index, T _V is the degree to which the original features are presented in the model before the V-th iteration, and a represents the character recognition The proportion of the final feature presentation, 1-a represents the proportion of the character satisfaction to the final feature presentation, D _V (k) is the proportion of each feature in the V round of recognition, S _V (m) is the proportion of each feature in the satisfaction in the V round.

Optionally, in an embodiment of the present application, the preset cartoon style features include at least one of at least one Disney cartoon style feature, at least one Japanese cartoon style feature, and at least one Meta cartoon style feature.

It should be noted that, the foregoing explanations on the embodiment of the three-dimensional cartoon face modeling method are also applicable to the three-dimensional cartoon face modeling apparatus of this embodiment, which will not be repeated here.

According to the 3D cartoon face modeling device proposed in the embodiment of the present application, the 3D face feature of the target person can be extracted by using the 3D depth map, and the 2D face feature and cartoon style feature in the 2D image of the target person can be fused to generate The 3D cartoon face model of the target face makes the generated 3D face model more recognizable, and can change the style with the change of cartoon style, which is more flexible, effectively meets the modeling needs and improves the user experience. . As a result, the technical problem of the cartoon image modeling of the real face based on the neural network in the related art, resulting in a single style and low recognition degree of the generated cartoon image, is solved.

FIG. 5 is a schematic structural diagram of an electronic device provided by an embodiment of the present application. The electronic device may include:

Memory 501 , processor 502 , and computer programs stored on memory 501 and executable on processor 502 .

When the processor 502 executes the program, the three-dimensional cartoon face modeling method provided in the above embodiment is implemented.

Further, the electronic device also includes:

The communication interface 503 is used for communication between the memory 501 and the processor 502 .

The memory 501 is used to store computer programs that can be executed on the processor 502 .

The memory 501 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk memory.

If the memory 501, the processor 502, and the communication interface 503 are independently implemented, the communication interface 503, the memory 501, and the processor 502 can be connected to each other through a bus and complete communication with each other. The bus may be an Industry Standard Architecture (referred to as ISA) bus, a Peripheral Component (referred to as PCI) bus, or an Extended Industry Standard Architecture (referred to as EISA) bus or the like. The bus can be divided into address bus, data bus, control bus and so on. For ease of presentation, only one thick line is used in FIG. 5, but it does not mean that there is only one bus or one type of bus.

Optionally, in terms of specific implementation, if the memory 501, the processor 502 and the communication interface 503 are integrated on one chip, the memory 501, the processor 502 and the communication interface 503 can communicate with each other through an internal interface.

The processor 502 may be a central processing unit (Central Processing Unit, CPU for short), or a specific integrated circuit (Application Specific Integrated Circuit, ASIC for short), or is configured to implement one or more of the embodiments of the present application integrated circuit.

This embodiment also provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by the processor, implements the above three-dimensional cartoon face modeling method.

In the description of this specification, description with reference to the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples", etc., mean specific features described in connection with the embodiment or example , structure, material or feature is included in at least one embodiment or example of the present application. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials or characteristics described may be combined in any suitable manner in any one or N of the embodiments or examples. Furthermore, those skilled in the art may combine and combine the different embodiments or examples described in this specification, as well as the features of the different embodiments or examples, without conflicting each other.

In addition, the terms "first" and "second" are only used for descriptive purposes, and should not be construed as indicating or implying relative importance or implying the number of indicated technical features. Thus, a feature delimited with "first", "second" may expressly or implicitly include at least one of that feature. In the description of the present application, "N" means at least two, such as two, three, etc., unless otherwise expressly and specifically defined.

Any process or method description in the flowcharts or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or N executable instructions for implementing custom logical functions or steps of the process, And the scope of the preferred embodiments of the present application includes alternative implementations in which the functions may be performed out of the order shown or discussed, including performing the functions in a substantially simultaneous manner or in the reverse order depending upon the functions involved, which should be Those skilled in the art to which the embodiments of the present application pertain will be understood.

The logic and/or steps represented in flowcharts or otherwise described herein, for example, may be considered an ordered listing of executable instructions for implementing the logical functions, may be embodied in any computer-readable medium, For use with, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other system that can fetch instructions from and execute instructions from an instruction execution system, apparatus, or apparatus) or equipment. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport the program for use by or in connection with an instruction execution system, apparatus, or apparatus. More specific examples (non-exhaustive list) of computer readable media include the following: electrical connections (electronic devices) with one or N wires, portable computer disk cartridges (magnetic devices), random access memory (RAM), Read Only Memory (ROM), Erasable Editable Read Only Memory (EPROM or Flash Memory), Fiber Optic Devices, and Portable Compact Disc Read Only Memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program may be printed, as the paper or other medium may be optically scanned, for example, followed by editing, interpretation, or other suitable medium as necessary process to obtain the program electronically and then store it in computer memory.

It should be understood that various parts of this application may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the N steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented by any one of the following techniques known in the art, or a combination thereof: discrete with logic gates for implementing logic functions on data signals Logic circuits, application specific integrated circuits with suitable combinational logic gates, Programmable Gate Arrays (PGA), Field Programmable Gate Arrays (FPGA), etc.

Those skilled in the art can understand that all or part of the steps carried by the methods of the above embodiments can be completed by instructing the relevant hardware through a program, and the program can be stored in a computer-readable storage medium, and the program can be stored in a computer-readable storage medium. When executed, one or a combination of the steps of the method embodiment is included.

In addition, each functional unit in each embodiment of the present application may be integrated into one processing module, or each unit may exist physically alone, or two or more units may be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware, and can also be implemented in the form of software function modules. If the integrated modules are implemented in the form of software functional modules and sold or used as independent products, they may also be stored in a computer-readable storage medium.

The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, and the like. Although the embodiments of the present application have been shown and described above, it should be understood that the above embodiments are exemplary and should not be construed as limitations to the present application. Embodiments are subject to variations, modifications, substitutions and variations.

Claims (10)

1. A three-dimensional cartoon face modeling method is characterized by comprising the following steps:

extracting two-dimensional face features of the face of a target person in the two-dimensional image;

extracting three-dimensional face features of the face according to the three-dimensional depth map of the target person; and

and fusing the two-dimensional face features, the three-dimensional face features and preset cartoon style features to generate a three-dimensional cartoon face model of the target face.

2. The method of claim 1, wherein the generating the three-dimensional cartoon face model of the target face comprises:

generating an initial three-dimensional cartoon face model of the target face according to fusion characteristics obtained by fusing the two-dimensional face characteristics, the three-dimensional face characteristics and preset cartoon style characteristics;

and calculating the presenting degree of the initial three-dimensional cartoon face model, linearly weighting at least one of the two-dimensional face features, the three-dimensional face features and the preset cartoon style features based on a preset standard when the presenting degree is smaller than a preset threshold value, generating a new three-dimensional cartoon face model, and performing iterative optimization until the presenting degree of the new three-dimensional cartoon face model is larger than or equal to the preset threshold value, so as to obtain a final three-dimensional cartoon face model.

3. The method of claim 2, further comprising, after generating the new three-dimensional cartoon face model:

obtaining a current feature weight value of at least one feature under a current iteration round;

and obtaining the presentation degree of the new three-dimensional cartoon face model of the current iteration round according to the current characteristic weight value and the presentation degree of the new three-dimensional cartoon face model of the previous iteration round.

4. A method according to claim 2 or 3, characterized in that the calculation formula of the degree of presentation is:

wherein, K represents the total characteristic quantity strongly related to the character identification degree, M represents the total characteristic quantity strongly related to the character satisfaction degree index, T _V The degree of the original characteristics in the model before the V-th iteration is represented, a represents the proportion of the character identification degree to the final characteristic presentation, 1-a represents the proportion of the character satisfaction degree to the final characteristic presentation, and D _V (k) Is the proportion of each characteristic in the V-th wheel in the identification degree, S _V (m) is a V-th wheelThe characteristics of the Chinese character take the proportion of satisfaction.

5. The method of any of claims 1-4, wherein the preset cartoon style features comprise at least one of at least one Disney cartoon style feature, at least one Japanese cartoon style feature, and at least one Meta cartoon style feature.

6. A three-dimensional cartoon face modeling device is characterized by comprising:

the first extraction module is used for extracting two-dimensional face features of the face of a target person in the two-dimensional image;

the second extraction module is used for extracting the three-dimensional face features of the face according to the three-dimensional depth map of the target person; and

and the modeling module is used for fusing the two-dimensional face features, the three-dimensional face features and preset cartoon style features to generate a three-dimensional cartoon face model of the target face.

7. The apparatus of claim 6, wherein the modeling module comprises:

the fusion unit is used for generating an initial three-dimensional cartoon face model of the target face according to fusion characteristics obtained by fusing the two-dimensional face characteristics, the three-dimensional face characteristics and preset cartoon style characteristics;

and the calculating unit is used for calculating the presenting degree of the initial three-dimensional cartoon face model, linearly weighting at least one of the two-dimensional face feature, the three-dimensional face feature and the preset cartoon style feature based on a preset standard when the presenting degree is smaller than a preset threshold value, generating a new three-dimensional cartoon face model, and performing iterative optimization until the presenting degree of the new three-dimensional cartoon face model is larger than or equal to the preset threshold value to obtain a final three-dimensional cartoon face model.

8. The apparatus of claim 7, wherein the modeling module is further configured to obtain a current feature weight value of the at least one feature at a current iteration; and obtaining the presentation degree of the new three-dimensional cartoon face model of the current iteration round according to the current characteristic weight value and the presentation degree of the new three-dimensional cartoon face model of the previous iteration round.

9. An electronic device, comprising: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the program to implement the three-dimensional cartoon face modeling method of any one of claims 1-5.

10. A computer-readable storage medium, on which a computer program is stored, the program being executable by a processor for implementing a method for modeling a three-dimensional cartoon face according to any one of claims 1-5.

Images