3D human model output device, program, and 3D human model output method

Abstract

To provide a three-dimensional human model generating device that enables a designer to generate a three-dimensional human model with as little effort as possible. [Solution] A 3D human model generation device having an evaluation learning unit 111 that machine-learns evaluation criteria for 3D human models, a generation unit 112 that can generate multiple types of generated 3D human models, an evaluation unit 113 that can evaluate the generated 3D human models using evaluation criteria and attribute information, an output unit 114 that can output an output 3D human model that has been given a predetermined evaluation by the evaluation unit 113 from among the generated 3D human models, a receiving unit 115 that can receive user evaluation information regarding the output 3D human model, an update unit 116 that can update human model configuration information and evaluation information using the output 3D human model and user evaluation information, and a machine learning unit 117 that can perform machine learning using unsupervised learning.

Description

[Technical Field]

[0001] The present disclosure relates to a three-dimensional human model generating device, and more particularly to a device that enables a designer involved in computer graphics to generate a desired three-dimensional human model with little effort. [Background technology]

[0002] In the technical field of computer graphics, there is an increasing demand for the use of a large number of polygons to display 3D people in high detail. However, displaying 3D people in high detail requires a great deal of effort. In order to meet this growing demand and provide more 3D human models in high detail, there is a need to reduce the effort required to generate each 3D human model.

[0003] As a technology that can reduce the labor, a technology has been proposed that can automatically generate data related to the color and texture of the surface of three-dimensional model data (also called "texture") by performing a coloring process based on a trained neural network model that has been trained in advance using training data as a model (see Patent Document 1). According to the technology described in Patent Document 1, texture is automatically generated using a trained neural network model, which can reduce the labor required to set the color and texture to be applied to the surface of a three-dimensional model. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Publication No. 2020-013390 Summary of the Invention [Problem to be solved by the invention]

[0005] In generating 3D human models, it is important that the designer can easily generate a 3D human model that meets the needs of the client, matching the attributes and shapes required by the client. However, the technology in Patent Document 1 only automatically generates data related to the color and texture of the surface of the 3D model data, and there is still room for improvement in terms of automating the process of meeting the client's needs.

[0006] More specifically, in the machine learning of a neural network using training data described in Patent Document 1, the designer prepares model training data. A neural network that generates a 3D human model with attributes desired by a client of the designer requires training data corresponding to each of the client's desired attributes. This requires the designer to put in a great deal of effort to prepare a large amount of training data. In order for the designer to generate the desired 3D human model with minimal effort, it is important to reduce the effort required for neural network training.

[0007] The present disclosure has been made in light of these circumstances, and its purpose is to provide a 3D human model generation device that enables a designer involved in computer graphics to generate a 3D human model desired by a client with as little effort as possible. [Means for solving the problem]

[0008] As a result of extensive research into solving the above problems, the inventors of the present application have discovered that the above object can be achieved by performing unsupervised learning of a neural network, and have completed the present disclosure. Specifically, the present disclosure provides the following:

[0009] The first disclosure provides an evaluation learning unit capable of using person model configuration information capable of configuring a three-dimensional human model, evaluation information for each of a plurality of types of three-dimensional human models configured by the person model configuration information, and attribute information for the plurality of types of three-dimensional human models to machine-learn evaluation criteria for the plurality of types of three-dimensional human models in a first neural network; a generation unit capable of generating a plurality of types of generated three-dimensional human models using a second neural network and the attribute information; an evaluation unit capable of evaluating the plurality of types of generated three-dimensional human models using the evaluation criteria and the attribute information; The present invention provides a 3D human model generation device comprising: an output unit capable of outputting a single type of output 3D human model evaluated by the evaluation unit, or a plurality of types of output 3D human models evaluated, from among a plurality of types of generated 3D human models; a receiving unit capable of receiving user evaluation information regarding the output 3D human model; an update unit capable of updating the human model configuration information using the output 3D human model and updating the evaluation information using the user evaluation information; and a machine learning unit capable of performing machine learning by unsupervised learning for at least the second neural network.

[0010] According to the first disclosure, a first neural network can be machine-learned to acquire evaluation criteria related to attributes that a user (a graphic designer who is an orderer) desires in a 3D human model. The generation unit can generate a plurality of generated 3D human models having the attributes that the user desires in a 3D human model. The output unit can select and output a plurality of types of output 3D human models that satisfy the evaluation criteria related to the attributes, i.e., are deemed to be desired 3D human models, from the plurality of generated 3D human models generated by the generation unit. Because a series of processes related to the output of the output 3D human models is performed automatically, the designer can output the 3D human model desired by the user (orderer) with less effort.

[0011] In the evaluation learning unit, the character model configuration information, evaluation information, and attribute information serve as training data that serve as a model for machine learning. Because the update unit can update the character model configuration information and evaluation information, designers can prepare training data with little effort. In other words, designers can obtain evaluation criteria that better reflect the attributes that users (those who order designers) require in 3D character models with little effort. This allows designers to output 3D character models that users (those who order designers) desire with little effort.

[0012] According to the first disclosure, the generation unit can generate a more detailed 3D human model desired by a user (a person who orders a designer) by using the second neural network that has been machine-learned. Because unsupervised machine learning can be performed without externally provided model training data, a more detailed 3D human model desired by a user (a person who orders a designer) can be generated without increasing the designer's workload.

[0013] Therefore, according to the first disclosure, it is possible to provide a three-dimensional human model generating device that enables a designer involved in computer graphics to generate a three-dimensional human model desired by a user (orderer) with as little effort as possible.

[0014] In addition to the first disclosure, the second disclosure provides a three-dimensional human model generation device, in which the machine learning unit is capable of performing the machine learning by unsupervised learning for both the first neural network and the second neural network.

[0015] According to the second disclosure, since machine learning is performed by unsupervised learning, the evaluation learning unit can cause the first neural network to learn evaluation criteria based on updated human model configuration information and evaluation information, even without training data provided by the designer. Therefore, a three-dimensional human model desired by the user (orderer) can be output in a more vivid state without increasing the designer's efforts.

[0016] A third disclosure provides a 3D human model generation device according to the first or second disclosure, wherein the unsupervised learning is learning using a generative adversarial network.

[0017] According to the third disclosure, machine learning can be performed using a generative adversarial network, with the second neural network serving as a generator of the generative adversarial network and the first neural network serving as a classifier of the generative adversarial network. In machine learning using a generative adversarial network, the generator generates data, and the classifier classifies the generated data. The generator then performs machine learning with the objective of having the classifier classify the generated data as correct data.

[0018] In machine learning using a generative adversarial network, where the generator is a second neural network related to the generation of a generated 3D human model and the classifier is a first neural network that has learned evaluation criteria for the 3D human model through machine learning, the classifier's identification of generated data as correct data corresponds to the first neural network that has learned the evaluation criteria through machine learning evaluating the generated 3D human model generated by the second neural network as a 3D human model that has the attributes desired by the user (orderer). In other words, the second neural network performs machine learning with the aim of generating a generated 3D human model that will be evaluated by the first neural network as having the attributes desired by the user (orderer). This enables the generation unit using the second neural network to generate a desired 3D human model with greater detail.

[0019] Since the machine learning using the above-mentioned generative adversarial network is unsupervised learning, it does not increase the designer's workload. Therefore, according to the third disclosure, it is possible to provide a 3D human model generation device that enables a designer involved in computer graphics to generate a 3D human model desired by a user (client) with little effort.

[0020] A fourth disclosure provides a three-dimensional human model generation device according to any one of the first to third disclosures, wherein the attribute information includes information on characteristics of the person.

[0021] According to the fourth disclosure, the first neural network can be trained to learn evaluation criteria related to the characteristics of a person desired by a user (orderer). As a result, the first neural network can learn the evaluation criteria of a 3D human model by machine learning so as to evaluate the evaluation criteria by focusing on parts corresponding to the characteristics of a person desired by a user who uses the 3D human model (a customer who orders a 3D human model from a designer). Furthermore, a designer can easily generate and output a 3D human model that captures the characteristics of a person desired by a user (customer) of the 3D human model, via information related to the characteristics of the person contained in the attribute information.

[0022] A fifth disclosure provides a three-dimensional human model generation device according to any one of the first to fourth disclosures, wherein the attribute information includes information relating to a purpose of use of the three-dimensional human model.

[0023] According to the fifth disclosure, the first neural network can be made to machine-learn evaluation criteria related to the intended use of a 3D human model. Furthermore, the generation unit can generate a 3D human model to be generated according to the intended use. Therefore, a designer can generate a 3D human model desired by a user (client) simply by specifying the intended use, without having to laboriously specify attribute information of the 3D human model according to the intended use. Therefore, a designer working in computer graphics can generate a 3D human model desired by a user (client) with less labor.

[0024] A sixth disclosure provides a 3D human model generation device according to any one of the first to fifth disclosures, wherein the attribute information includes identification information that enables identification of the single type of output 3D human model or multiple types of output 3D human models.

[0025] According to the sixth disclosure, instead of using the updated human model configuration information, the evaluation information updated by the user evaluation information can be associated with the output 3D human model using the identification information included in the attribute information. This allows the first neural network to learn the evaluation criteria for the output 3D model by machine learning, even without updating the human model configuration information. If the human model configuration information is not updated, the designer will not have to wait for the update of the human model configuration information, and the designer's workload can be reduced.

[0026] The seventh disclosure is a change in the category of configurations related to the first disclosure. [Effects of the Invention]

[0027] According to the present disclosure, it is possible to provide a three-dimensional human model generation device that enables a designer involved in computer graphics to generate a three-dimensional human model desired by a user (orderer) of the three-dimensional human model with as little effort as possible. [Brief explanation of the drawings]

[0028] [Figure 1] 1 is a block diagram showing an example of the configuration of a three-dimensional human model generating device according to an embodiment of the present invention. [Figure 2] FIG. 10 is a diagram illustrating an example of a character model information table. [Figure 3] FIG. 10 is a diagram illustrating an example of a neural network table. [Figure 4] 1 is a flowchart showing an example of a three-dimensional human model generation process using the three-dimensional human model generation device of this embodiment. [Figure 5] 10 is a flowchart illustrating an example of machine learning processing when a generative adversarial network is used. [Figure 6] FIG. 10 is an explanatory diagram showing an example of generating a three-dimensional human model using attribute information. [Figure 7] FIG. 10 is an explanatory diagram showing an example of machine learning using user evaluation information. DETAILED DESCRIPTION OF THE INVENTION

[0029] Hereinafter, an example of a preferred embodiment for carrying out the present disclosure will be described with reference to the drawings. Note that this is merely an example, and the technical scope of the present disclosure is not limited to this example.

[0030] <3D human model generation device 1> 1 is a block diagram showing an example of the configuration of a 3D human model generating device 1 (hereinafter simply referred to as "generating device 1") according to this embodiment. The generating device 1 includes at least a control unit 11, a storage unit 12, a display unit 13, and an input unit 14.

[0031] [Control unit 11] The control unit 11 includes a CPU (Central Processing Unit), a RAM (Random Access Memory), a ROM (Read Only Memory), and the like.

[0032] The control unit 11 reads a predetermined program, and as necessary, the memory unit 12, display unit 13, and input unit 14 work together to realize the software configuration elements of the generation device 1, such as the evaluation learning unit 111, generation unit 112, evaluation unit 113, output unit 114, receiving unit 115, update unit 116, and machine learning unit 117.

[0033] [Storage section 12] The storage unit 12 is a device in which data and files are stored, and has a data storage unit such as a hard disk, semiconductor memory, recording medium, memory card, etc. The storage unit 12 may have a mechanism that enables connection to storage devices or storage systems such as NAS (Network Attached Storage), SAN (Storage Area Network), cloud storage, file server, and distributed file system via a network.

[0034] The storage unit 12 stores a control program executed by the microcomputer, a human model information table 121, a neural network table 122, etc. Signals and information are input to the storage unit 12 from the output unit 114 of the control unit 11. In addition, signals and information are transmitted from the storage unit 12 to the receiving unit 115 of the control unit 11.

[0035] [Character model information table 121] Fig. 2 is a diagram showing an example of the character model information table 121. The character model information table 121 shown in Fig. 2 stores information linking an "ID" for identifying character model information, "character model configuration information" having the shape, the surface texture, and the surface color of the three-dimensional character model, "evaluation information" regarding the three-dimensional character model configured by the character model configuration information, and "attribute information" of the three-dimensional character model.

[0036] Furthermore, the human model information table 121 is configured to allow addition of information linking an ID, human model configuration information, and attribute information. Since the human model information table 121 is configured to allow addition of information, the update unit 116 can update the human model configuration information using the output three-dimensional human model.

[0037] (Personal model configuration information) The character model configuration information is information that can configure a three-dimensional character model. The three-dimensional character model is not particularly limited as long as it is a three-dimensional model that visually represents a person or part of a person. The three-dimensional character model may be either male or female, and may include at least one of three-dimensional models of clothing, accessories, and props worn by the person. The format of the character model configuration information is not particularly limited, and character model configuration information in a conventional format can be stored.

[0038] The human model configuration information preferably includes at least one of information regarding the three-dimensional shape of the three-dimensional human model, information regarding the texture of the surface of the three-dimensional human model, and information regarding the color of the surface of the three-dimensional human model. By including this information, model training data can be provided to the first neural network N1, which will be described later. This allows the first neural network N1 to machine-learn evaluation criteria regarding at least one of the three-dimensional shape of the three-dimensional human model, the surface color of the three-dimensional human model, and the surface color of the three-dimensional human model.

[0039] Furthermore, by including various information related to these three-dimensional human models, the human model information table 121 can provide model training data to the second neural network N2, which will be described later. This allows the second neural network N2 to machine-learn a generation algorithm related to at least one of the three-dimensional shape of the three-dimensional human model, the surface color of the three-dimensional human model, and the surface color of the three-dimensional human model. For example, the row with ID "M1" stores human model configuration information for a three-dimensional human model having a shape of an elongated face, and a surface color and texture of light-colored hair, beard, and light-colored skin.

[0040] The character model configuration information may include information capable of configuring an output three-dimensional character model to be output by the output unit 114, which will be described later. The information capable of configuring an output three-dimensional character model is not particularly limited as long as it is capable of configuring an output three-dimensional character model, and similar to the character model configuration information, configuration information capable of configuring an output three-dimensional character model in a format of the conventional technology can be stored. Since the character model configuration information may include information capable of configuring an output three-dimensional character model, the update unit 116, which will be described later, can update the character model configuration information using the output three-dimensional character model.

[0041] (Evaluation information) The evaluation information is information about an evaluation made by a user on a three-dimensional human model configured by the human model configuration information. In the example shown in Fig. 2, an evaluation indicating the degree to which the three-dimensional human model conforms to the evaluation criteria desired by the user on a scale of 100 points is stored as the evaluation information. The format of the evaluation information is not limited to an evaluation indicating the degree to which the three-dimensional human model conforms to the evaluation criteria on a scale of 100 points, and may include, for example, information about the score given by the user to the three-dimensional human model, information listing the attributes that the three-dimensional human model has, information listing the attributes that the three-dimensional human model does not have, etc.

[0042] The evaluation criteria may also include a history of the 3D human model that the user has purchased since placing an order. The routes by which the user's evaluation is input to the receiving unit 115 include a route from the input unit 14 to the receiving unit 115 and a route by which the evaluation is input to the receiving unit 115 via the external device 120 and the communication unit 15. The user is an orderer who orders a 3D human model from a designer.

[0043] (Attribute information) The attribute information is information about the attributes of the three-dimensional human model configured by the human model configuration information. The format of the attribute information is not particularly limited, and may include any information related to the attributes of the three-dimensional human model.

[0044] The attribute information preferably includes information about "characteristics of a person desired by a user." In the example shown in FIG. 2, information about characteristics of a person, such as "light-colored hair," "long, thin face," and "beard," is stored as attribute information associated with the ID "M1." By including information about the characteristics of a person, the first neural network N1 (described later) can learn by machine learning evaluation criteria related to the characteristics of a person desired by a user (client). This allows the first neural network N1 to learn by machine learning evaluation criteria for a 3D human model so that the evaluation focuses on features corresponding to the characteristics of a person desired by a user (client who orders a 3D human model from a designer) who uses the 3D human model. Furthermore, a designer can easily generate and output a 3D human model that captures the characteristics of a person desired by a user (client) of the 3D human model, using the information about the characteristics of a person included in the attribute information.

[0045] The attribute information preferably includes information regarding the intended use of the three-dimensional human model. In the example shown in FIG. 2, information regarding the intended use of the three-dimensional human model, "for advertising in North America," is stored as attribute information linked to ID "M1." By including information regarding the intended use of the three-dimensional human model, it is possible to allow the first neural network N1, described below, to machine-learn evaluation criteria regarding the intended use of the three-dimensional human model desired by the user (client). The intended use includes the region of advertising, such as "for advertising in North America," "for advertising in Asia," "for advertising in Europe," or "for advertising in Africa."

[0046] As a result, the first neural network N1 can machine-learn evaluation criteria for the three-dimensional human model so as to evaluate whether the three-dimensional human model is suitable for the intended use desired by the user who uses the three-dimensional human model (the client who orders the three-dimensional human model from the designer). Furthermore, the designer can easily generate and output a three-dimensional human model suitable for the intended use desired by the user (client) of the three-dimensional human model, via information regarding the intended use of the three-dimensional human model contained in the attribute information.

[0047] Since the attribute information includes information regarding the intended use of the 3D human model, the generating device 1 can receive the intended use of the 3D human model via the attribute information. Therefore, the designer can generate a generated 3D human model that matches the intended use simply by specifying the intended use, without having to take the effort of specifying attribute information for the 3D human model that matches the intended use. Therefore, a designer involved in computer graphics can generate a 3D human model that a user (orderer) desires with less effort.

[0048] The attribute information preferably includes identification information that enables identification of the three-dimensional human model to be output. In the example shown in FIG. 2, information that enables identification of the three-dimensional human model to be output, "three-dimensional human model to be output: P1," is stored as attribute information linked to the ID "M5." This allows the evaluation information updated by the user evaluation information to be associated with the three-dimensional human model to be output, using the identification information included in the attribute information instead of the updated human model configuration information. This allows the first neural network N1 to machine-learn the evaluation criteria for the three-dimensional model to be generated, without updating the human model configuration information stored in the human model information table 121. If the human model configuration information is not updated, the designer will not have to wait for the update of the human model configuration information, thereby reducing the designer's workload.

[0049] Since IDs are stored in the human model information table 121 shown in FIG. 2, it is easy to obtain and update the information stored in the human model information table 121. Since evaluation information is stored, model training data can be provided to the first neural network N1, which will be described later. This allows the first neural network N1 to learn evaluation criteria for three-dimensional human models by machine learning. Since attribute information is stored, the evaluation learning unit 111 allows the first neural network N1 to learn evaluation criteria related to attributes that a user of the three-dimensional human model, who is an orderer to a graphic designer, desires for in the three-dimensional human model.

[0050] The generation unit 112 can generate a plurality of 3D human model objects having the attributes that the user desires for in a 3D human model. The output unit 114 can then select and output a plurality of types of 3D human model objects that satisfy the evaluation criteria for the attributes, i.e., are recognized as desired 3D human model objects, from the plurality of 3D human model objects generated by the generation unit 112.

[0051] For example, the row of ID "M1" stores character model configuration information for a three-dimensional character model having a long, thin face and a surface color and texture of light hair, a beard, and light skin, evaluation information "90" for the three-dimensional character model configured using this character model configuration information, and attribute information for the three-dimensional character model configured using this character model configuration information: "light hair," "long, thin face," "beard," "light skin," and "for advertising in North America." In this way, the character model information table 121 can store character model configuration information, evaluation information, and attribute information in association with each other.

[0052] [Neural Network Table 122] 3 is a diagram showing an example of the neural network table 122. The neural network table 122 stores at least a first neural network N1 (corresponding to ID "N1") related to evaluation criteria for three-dimensional human models and a second neural network N2 (corresponding to ID "N2") related to generation of three-dimensional human models.

[0053] The formats of the first neural network N1 and the second neural network N2 are not particularly limited, and may include a data structure including information on an activation function that determines the presence or absence of a signal output by an artificial neuron (also referred to as a node) of the neural network, or the strength of the signal, information on a weight matrix (also referred to as a weight parameter) that expresses the weighting of a signal input to an artificial neuron of the neural network (also referred to as a synaptic connection strength or simply connection strength), information on a bias vector that assigns a reference weight (also referred to as a bias parameter or simply bias) to a signal input to an artificial neuron of the neural network, information on the connection relationship between the artificial neurons of the neural network, etc.

[0054] The types of the first neural network N1 and the second neural network N2 stored in the neural network table 122 are not particularly limited, and various types of neural networks of the prior art, such as a feedforward neural network (also referred to as an FFNN), a convolutional neural network (also referred to as a CNN or ConvNet), a deep stacking network (also referred to as a DSN), an RBF network (also referred to as a radial basis function network), a recurrent neural network (also referred to as an RNN), and a modular neural network, can be stored in the neural network table 122 as the first neural network N1 and the second neural network N2.

[0055] Looking more closely at the configuration of the neural network table 122, the neural network table 122 shown in Fig. 3 stores an "ID" that identifies a neural network and weight matrices A and B of the neural network, linked together. Storing the ID makes it easy to obtain and update the information stored in the neural network table 122. Storing the weight matrices A and B of the neural network makes it possible to generate or evaluate a neural network and to have the neural network perform machine learning.

[0056] The row with ID "N1" stores a first neural network N1 represented by a weight matrix A1 (a matrix including elements a111 to a179) and a weight matrix B1 (a matrix including elements b111 to b194). By storing the weight matrix A1 and the weight matrix B1, the evaluation learning unit 111 can have the first neural network N1 learn the evaluation criteria by machine learning. Furthermore, by storing the weight matrix A1 and the weight matrix B1, the evaluation unit 113 can evaluate the three-dimensional human model to be generated.

[0057] The row with ID "N2" stores a second neural network N2 represented by a weight matrix A2 (a matrix including elements a211 to a249) and a weight matrix B2 (a matrix including elements b211 to b297). By storing the weight matrix A2 and the weight matrix B2 in the neural network table 122, the generation unit 112 can generate a generated 3D human model. Furthermore, by storing the weight matrix A2 and the weight matrix B2, the machine learning unit 117 can perform machine learning on the second neural network N2.

[0058] By storing the first neural network N1 in the neural network table 122, the evaluation learning unit 111 can cause the first neural network N1 to learn evaluation criteria for 3D human models. By storing the second neural network N2 in the neural network table 122, the generation unit 112 can generate multiple types of generated 3D models. Furthermore, by storing the second neural network N2 in the neural network table 122, the machine learning unit 117 can perform unsupervised machine learning on the second neural network N2. Machine learning is a technique in which learning data is trained without providing a correct answer.

[0059] [Display section 13] There is no particular limitation on the type of the display unit 13. Examples of the display unit 13 include a monitor, a touch panel, a projector, and a video card that displays the output 3D human model on the external device 120. The display unit 13 receives signals and information output from the output unit 114 of the control unit 11.

[0060] [Input section 14] There is no particular limitation on the type of input unit 14. Examples of the input unit 14 include a keyboard, a mouse, a touch panel, and a communication device that receives input from an external device 120. The signals and information input from the input unit 14 are input to a receiving unit 115 of the control unit 11. The user's order information input to the input unit 14 is sent to the receiving unit 115.

[0061] [Communications Section 15] The generating device 1 may include a communication unit 15 that communicates between the generating device 1 and the external device 120. The communication unit 15 and the external device 120 are connected via a network 123. The network 123 may be constructed wirelessly or wired. The external device 120 may be either singular or plural. By including the communication unit 15, the generating device 1 can transmit the output 3D human model output by the output unit 114 to the external device 120. By including the communication unit 15, the generating device 1 can receive commands related to the generation of the 3D human model from the external device 120. By including the communication unit 15, the generating device 1 can receive and use human model configuration information, evaluation information, attribute information, user evaluation information, etc. from the external device 120.

[0062] [External device 120] The external device 120 may be either a mobile terminal or a fixed terminal. The external device 120 is operated by a user and includes a control circuit 125, an input unit 126, a display unit 127, a memory unit 128, and a communication unit 129. The control circuit 125 is a computer having an input port, an output port, and a central processing circuit. The control circuit 125 is connected to the input unit 126, the display unit 127, the memory unit 128, and the communication unit 129 so as to be able to transmit and receive signals. Examples of the input unit 126 include a keyboard, a mouse, a touch panel, and a communication device that receives input from the external device 120. Examples of the display unit 127 include a monitor, a touch panel, a projector, and a video card that displays a 3D human model to be output on the external device 120. The memory unit 128 is a device that stores data and files and includes a data storage unit such as a hard disk, semiconductor memory, recording medium, or memory card. The communication unit 129 is connected to the network 123.

[0063] <Main Flowchart of Generation Process Executed by Generation Device 1> 4 is an example of a main flowchart showing the procedure of the generation process in this modified example. A preferred procedure of the generation process performed by the generation device 1 will be described below with reference to FIG.

[0064] [Step S1: Machine learning of evaluation criteria] First, the control unit 11 executes the evaluation learning unit 111 in cooperation with the storage unit 12, refers to the human model information table 121, and executes a process of having the first neural network N1 learn evaluation criteria for multiple types of three-dimensional human models by machine learning (step S1).

[0065] The algorithm for machine learning the evaluation criteria in step S1 is not particularly limited, and any known machine learning algorithm for supervised learning of neural networks can be used, such as backpropagation, stochastic gradient descent such as the Widrow-Hoff method (also known as the delta rule), gradient descent, online learning, batch learning, logistic function, sigmoid function, maximum function, etc.

[0066] The control unit 11 executes the evaluation learning unit 111 and acquires person model configuration information, evaluation information, and attribute information from the person model information table 121. Then, the control unit 11 causes the first neural network N1 stored in the neural network table 122 to machine-learn the evaluation criteria using the person model configuration information, evaluation information, and attribute information, and updates the first neural network N1 stored in the neural network table 122. In other words, the control unit 11 acquires the person model configuration information, evaluation information, and attribute information from the person model information table 121, and causes the first neural network N1 to machine-learn the evaluation criteria using the person model configuration information, evaluation information, and attribute information as example training data.

[0067] As a result, the first neural network N1 can learn by machine learning evaluation criteria related to attributes that a client, who is a user of the 3D human model, requests of the 3D human model from a graphic designer. After completing the process of step S1, the control unit 11 performs a determination of step S2.

[0068] [Step S2: Determine whether attribute information has been received] The control unit 11 executes the generation unit 112 in cooperation with the storage unit 12 and the input unit 14, and determines whether or not the attribute information has been received by the receiving unit 115 (step S2). If the attribute information has been received, the control unit 11 determines Yes in step S2 and performs the process of step S3. If the attribute information has not been received, the control unit 11 determines No in step S2 and performs the determination of step S7.

[0069] [Step S3: Generate a 3D human model to be generated] The control unit 11 executes the generation unit 112 in cooperation with the storage unit 12, and acquires the second neural network N2 stored in the neural network table 122. Then, the control unit 11 generates a plurality of types of three-dimensional human models to be generated using the attribute information received in step S2 and the second neural network N2 (step S3).

[0070] The generation unit 112 can generate multiple random 3D human model instances using the attribute information received in step S2 and the second neural network N2 represented by weighting matrices A2 and B2. This allows the designer to generate multiple 3D human model instances with attributes desired by the user (orderer) of the 3D human model with minimal effort. After processing step S3, the control unit 11 proceeds to step S4.

[0071] [Step S4: Evaluate the generated 3D human model] The control unit 11 executes the evaluation unit 113 in cooperation with the storage unit 12, and acquires the first neural network N1 stored in the neural network table 122. Then, the control unit 11 evaluates the multiple types of generated 3D human models generated in step S3 using the attribute information received in step S2 and the first neural network N1 (step S4).

[0072] In this way, the control unit 11 evaluates the multiple types of generated 3D human models generated in step S3 using the attribute information received in step S2 and the first neural network N1 that has machine-learned the evaluation criteria in step S1. Therefore, an evaluation regarding the attributes indicated by the attribute information received in step S2 is given to the multiple types of generated 3D human models generated by the generation unit 112. After processing step S4, the control unit 11 proceeds to step S5.

[0073] [Step S5: Output the output 3D person model] The control unit 11 executes the output unit 114 in cooperation with the memory unit 12 and the display unit 13, and outputs, as an output three-dimensional human model, a three-dimensional human model that has undergone a predetermined evaluation in step S4 from among the multiple types of three-dimensional human models generated in step S3 (step S5).

[0074] The output unit 114 can select and output a three-dimensional human model to be output that has undergone a predetermined evaluation regarding the attributes indicated by the attribute information received in step S2. Because a series of processes related to the output of the three-dimensional human model to be output is performed automatically, the designer can output the three-dimensional human model desired by the user (orderer) with less effort. After processing step S5, the control unit 11 proceeds to step S6.

[0075] [Step S6: Update person model configuration information] The control unit 11 executes the update unit 116 in cooperation with the storage unit 12, and adds the new ID, the person model configuration information including information capable of configuring the output three-dimensional human model output in step S5, and the attribute information including information capable of identifying the output three-dimensional human model to the person model information table 121 (step S6).

[0076] The updating unit 116 links the new ID with the character model configuration information including information capable of configuring the output 3D human model output in step S5, and attribute information including information capable of identifying the output 3D human model, and adds the linked information to the character model information table 121, thereby updating the character model configuration information stored in the character model information table 121. This allows the designer to prepare, with little effort, training data that serves as a model to be used in the process executed in step S1 and the process executed in step S9, which will be described later. That is, the designer can obtain, with little effort, evaluation criteria that better reflect the attributes that the user (the person ordering the designer) desires in a 3D human model. This allows the designer to output, with little effort, a 3D human model that the user (the person ordering the designer) desires.

[0077] In this way, the control unit 11 determines whether or not attribute information has been received in step S2, and performs the subsequent processing. When attribute information has not been received, the control unit 11 can skip the processing executed in steps S3 to S5, which generate, evaluate, and output a three-dimensional human model according to the attribute information. Furthermore, the control unit 11 can skip step S6, which relates to updating the human model configuration information. This reduces the amount of processing executed by the control unit 11. After processing step S6, the control unit 11 proceeds to step S7.

[0078] [Step S7: Determine whether evaluation information has been received from the user] The control unit 11 executes the receiving unit 115 in cooperation with the storage unit 12 and the input unit 14 to determine whether or not evaluation information has been received from the user (step S7). If evaluation information has been received from the user, the control unit 11 determines "Yes" in step S7 and proceeds to step S8. If evaluation information has not been received from the user, the control unit 11 determines "No" in step S7 and returns to step S1.

[0079] [Step S8: Update evaluation information] The control unit 11 executes the update unit 116 in cooperation with the storage unit 12, and updates the evaluation information about the output three-dimensional human model output in S5, which is stored in the human model information table 121, based on the evaluation information received from the user (step S8).

[0080] By updating the evaluation information stored in the human model information table 121 with the evaluation information, the designer can prepare, with little effort, training data that will serve as a model to be used in the process executed in step S1 and the process executed in step S9, which will be described later. That is, the designer can obtain, with little effort, evaluation criteria that better reflect the attributes that the user (the person ordering the designer) desires in a three-dimensional human model. This allows the designer to output, with little effort, a three-dimensional human model that the user (the person ordering the designer) desires. After processing step S8, the control unit 11 proceeds to step S9.

[0081] [Step S9: Perform unsupervised machine learning] The control unit 11 executes the machine learning unit 117 in cooperation with the storage unit 12, and acquires the person model configuration information, evaluation information, and attribute information from the person model information table 121. Then, using the person model configuration information, evaluation information, and attribute information, the control unit 11 causes the second neural network N2 stored in the neural network table 122 to perform unsupervised machine learning to generate a three-dimensional person model, thereby updating the second neural network N2 stored in the neural network table 122 (step S9).

[0082] The algorithm for performing machine learning in step S9 is not particularly limited as long as it is unsupervised learning, and any known machine learning algorithm for unsupervised learning of neural networks can be used, such as one or more of cluster analysis, principal component analysis, vector quantization, self-organizing map, generative adversarial network (also called GAN), deep belief network (also called DBN), Hebb's law, etc.

[0083] The machine learning performed in step S9 enables the second neural network N2 to generate a more detailed 3D human model related to the attribute information. As a result, in step S3, the generation unit 112 can use the second neural network N2 that has undergone machine learning to generate a more detailed 3D human model desired by the user (the person ordering the designer). The unsupervised machine learning performed in step S9 can be performed without externally provided model training data, so the generation device 1 can generate a more detailed 3D human model desired by the user (the person ordering the designer) without increasing the designer's workload.

[0084] Therefore, by executing the processes from step S1 to step S9, it is possible to provide a 3D human model generation device 1 that enables a designer involved in computer graphics to generate a 3D human model desired by a user (orderer) with as little effort as possible. After processing step S9, the control unit 11 returns to step S1.

[0085] In this way, the control unit 11 determines whether or not evaluation information has been received from a user, and when the control unit 11 receives evaluation information from a user, the control unit 11 can perform "unsupervised machine learning." Note that "unsupervised machine learning" will be described later. Furthermore, when the control unit 11 has not received evaluation information from a user, the control unit 11 can repeat the 3D human model generation process without performing "unsupervised machine learning."

[0086] It is preferable that the algorithm used for machine learning in step S9 includes a generative adversarial network, since this can reduce the variability in the output from the neural network relative to the input to the neural network, and various functions, including the generation and evaluation of three-dimensional human models, can be realized on the neural network.

[0087] In generating a 3D human model to be generated using the second neural network N2, the received attribute information corresponds to the input to the second neural network N2, and the generated 3D human model corresponds to the output from the second neural network N2. Since it is possible to suppress the variation in output relative to the input, the second neural network N2 can generate only the desired 3D human model in a high-quality state for the received attribute information, and can avoid generating 3D human models that are similar but different from the desired 3D human model. In other words, it becomes possible to generate a 3D human model related to the attribute information in a high-quality state.

[0088] Fig. 5 is a flowchart showing an example of the flow of the machine learning process when a generative adversarial network is used, which is executed in step S9. Below, with reference to Fig. 5, a preferred procedure of the machine learning process executed in step S9 of Fig. 4 will be described, taking as an example a case where the algorithm for performing machine learning includes a generative adversarial network.

[0089] [Step S11: Obtain attribute information] The control unit 11 executes the machine learning unit 117 in cooperation with the storage unit 12, and sets the number of updates indicating the number of times the second neural network N2 has been updated to 0. The control unit 11 further acquires attribute information (step S11). By setting the number of updates to 0, the control unit 11 can execute machine learning a predetermined number of times in succession. By acquiring the attribute information, the control unit 11 can execute machine learning according to the attribute information. After processing step S11, the control unit 11 proceeds to step S12.

[0090] [Step S12: Generate a 3D human model to be generated] The control unit 11 cooperates with the storage unit 12 to execute the machine learning unit 117, and generates a person model to be generated using the second neural network N2 (step S12).

[0091] In machine learning using a generative adversarial network, a generator generates data and a discriminator discriminates the generated data. The generator then performs machine learning with the objective of having the discriminator discriminate the generated data as correct data. The control unit 11 generates a generated person model using the second neural network N2, thereby enabling the second neural network N2 to function as a generator in the generative adversarial network. After processing step S12, the control unit 11 proceeds to step S13.

[0092] [Step S13: Evaluate the generated 3D human model] The control unit 11 cooperates with the storage unit 12 to execute the machine learning unit 117, and evaluates the generated person model generated in step S12 using the first neural network N1 (step S13).

[0093] In step S13, the control unit 11 evaluates the generated person model generated in step S12 by the machine learning unit 117 using the first neural network N1. Therefore, the first neural network N1 can be used as a classifier in the generative adversarial network. Therefore, the machine learning unit 117 can perform machine learning using a generative adversarial network, with the second neural network N2 as the generator in the generative adversarial network and the first neural network N1 as the classifier in the generative adversarial network. After processing in step S13, the control unit 11 makes a determination in step S14.

[0094] [Step S14: Determine whether the attribute-related evaluation criteria are met] The control unit 11 executes the machine learning unit 117 in cooperation with the storage unit 12, and determines whether the 3D human model generated in step S12 satisfies the evaluation criteria for attributes (step S14). If the evaluation criteria for attributes are satisfied, the control unit 11 determines Yes in step S14 and proceeds to step S15. On the other hand, if the evaluation criteria for attributes are not satisfied, the control unit 11 determines No in step S14 and proceeds to step S16.

[0095] [Step S15: Update the second neural network N2 to generate more similar generated 3D human models] The control unit 11 executes the machine learning unit 117 in cooperation with the memory unit 12, and updates the second neural network N2 so as to generate more three-dimensional human models similar to the human model generated in step S12 (step S15).

[0096] By updating the second neural network N2 so that the machine learning unit 117 generates more three-dimensional human model models similar to the human model generated in step S12, the generation unit 112 using the second neural network N2 generates more three-dimensional human model models similar to the three-dimensional human model that received a predetermined evaluation in step S13. In other words, the generation unit 112 can generate a more vivid three-dimensional human model desired by the user (orderer). After processing step S15, the control unit 11 proceeds to step S17.

[0097] [Step S16: Update the second neural network N2 to generate fewer similar generated 3D human models] The control unit 11 executes the machine learning unit 117 in cooperation with the memory unit 12, and updates the second neural network N2 so as to generate fewer three-dimensional human models similar to the human model generated in step S12 (step S16).

[0098] By updating the second neural network N2 so that the machine learning unit 117 generates fewer three-dimensional human model models similar to the human model generated in step S12, the generation unit 112 using the second neural network N2 generates fewer three-dimensional human model models similar to the three-dimensional human model that did not obtain the predetermined evaluation in step S13. In other words, the generation unit 112 can generate a three-dimensional human model desired by the user (orderer) in a more vivid state.

[0099] In this way, the control unit 11 determines in step S14 whether the 3D human model to be generated generated in step S12 satisfies the evaluation criteria for attributes. Then, the machine learning unit 117 can update the second neural network N2 so as to change the rate at which similar 3D human models to be generated are generated, depending on whether the evaluation criteria for attributes are satisfied. After processing step S15 or step S16, the control unit 11 proceeds to step S17.

[0100] [Step S17: Increase the update count by 1] Control unit 11, in cooperation with storage unit 12, executes machine learning unit 117 and increments the number of updates by 1 (step S17). By incrementing the number of updates by 1, the number of times the second neural network N2 has been updated is reflected in the number of updates. After processing step S17, control unit 11 proceeds to step S18.

[0101] [Step S18: Determine whether the number of updates is equal to or greater than a predetermined number] The control unit 11 executes the machine learning unit 117 in cooperation with the storage unit 12, and determines whether the number of updates is equal to or greater than a predetermined number (step S18). If the number of updates is less than the predetermined number, the control unit 11 determines No in step S18, Return to step S12. If the number of updates is equal to or greater than the predetermined number, the control unit 11 determines "Yes" in step S18, and returns to step S1 in FIG.

[0102] In this way, the control unit 11 can continuously perform machine learning using a generative adversarial network exactly the same number of times as the predetermined number of times by determining whether the number of updates is greater than or equal to the predetermined number and changing the processing accordingly.

[0103] The control unit 11 executes the processes of steps S11 to S18, allowing the machine learning unit 117 to perform machine learning using a generative adversarial network, with the second neural network N2 as a generator of the generative adversarial network and the first neural network N1 as a classifier of the generative adversarial network. In machine learning using a generative adversarial network, the generator generates data, and the classifier classifies the generated data. The generator then performs machine learning with the objective of having the classifier classify the generated data as correct data.

[0104] In machine learning using a generative adversarial network, where the generator is a second neural network N2 related to generating a generated 3D human model and the classifier is a first neural network N1 that has learned evaluation criteria for the 3D human model through machine learning, the classifier's identification of generated data as correct data corresponds to the first neural network N1 that has learned the evaluation criteria through machine learning evaluating the generated 3D human model generated by the second neural network N2 as a 3D human model having the attributes desired by the user (orderer). In other words, the second neural network N2 performs machine learning with the aim of generating a generated 3D human model that is evaluated by the first neural network N1 as having the attributes desired by the user (orderer). This enables the generation unit 112 using the second neural network N2 to generate a desired 3D human model with greater detail.

[0105] The machine learning using the above-mentioned generative adversarial network is unsupervised learning, so it does not increase the designer's workload. Therefore, it is possible to provide a 3D human model generation device 1 that allows designers involved in computer graphics to generate 3D human models desired by users (clients) with little effort.

[0106] The control unit 11 causes the second neural network N2 stored in the neural network table 122 to perform unsupervised machine learning to generate a three-dimensional human model, and after updating the second neural network N2 stored in the neural network table 122, returns the process to step S1 in Figure 4.

[0107] <Example of use of the 3D human model generation device 1> Next, an example of how to use the three-dimensional human model generating device 1 according to this embodiment will be described with reference to FIGS.

[0108] [Learn the evaluation criteria] A designer who has received an order from a user (orderer) to generate a three-dimensional human model with desired attributes causes the generation device 1 to execute a three-dimensional human model generation process. The generation device 1 executes the evaluation learning unit 111, and causes the first neural network N1 to machine-learn evaluation criteria using the human model configuration information, evaluation information, and attribute information stored in the human model information table 121.

[0109] An example of evaluation criteria for machine learning by the first neural network N1 will be described with reference to Fig. 2. The human model information table 121 shown in Fig. 2 stores, with regard to attribute information relating to the shape of a three-dimensional human model, human model configuration information M1 and M3 having attribute information "long and thin face" and human model configuration information M2 and M4 having attribute information "wide face".

[0110] The evaluation learning unit 111 trains the first neural network N1 to learn the characteristics of the person model configuration information common to the person model configuration information M1 and M3, namely, "long and thin face" and "light skin," as evaluation criteria for the attribute information "long and thin face," and trains the first neural network N1 to learn the characteristics of the person model configuration information common to the person model configuration information M2 and M4, namely, "wide face," "dark skin," "no beard," and "dark hair," as evaluation criteria for the attribute information "wide face."

[0111] [Receive attribute information] FIG. 6 is an explanatory diagram showing an example of generating a three-dimensional human model using attribute information. Using the example shown in FIG. 6, three-dimensional human model generation using attribute information will be described. The designer transmits (inputs) attributes desired by a user (orderer) to the generating device 1 as attribute information. In the example shown in FIG. 6, the description will be given assuming that the attribute desired by the user (orderer) is the attribute information "wide face." The generating device 1 executes the generating unit 112 in step S2 of FIG. 4, and receives the attribute information "wide face" transmitted by the designer.

[0112] [Output the output 3D human model] The generation unit 112 generates random three-dimensional models G1 to G4 to be generated using the second neural network N2 and the attribute information "wide face."

[0113] The evaluation unit 113 evaluates each of the generated three-dimensional models G1 to G4 using the evaluation criteria learned by machine learning by the first neural network N1 and the attribute information "wide face."

[0114] The generated 3D model G1 satisfies four of the four evaluation criteria for a "wide face" - "wide face," "dark skin," "no beard," and "dark hair" - and therefore receives a high rating of "100" out of 100. The generated 3D model G3 also receives a high rating of "50" out of 100, as it satisfies two of the four evaluation criteria for a "wide face" - "wide face" and "dark hair."

[0115] On the other hand, the generated 3D model G2 only satisfies the "no beard" criteria out of the four criteria for a "wide face," so it receives a low score of "25." Also, the generated 3D model G4 only satisfies the "dark skin" criteria out of the four criteria for a "wide face," so it receives a low score of "25."

[0116] The output unit 114 outputs the generated three-dimensional models G1 and G3 that have received a predetermined evaluation as output three-dimensional human models P1 and P2. The generation unit 112 generates a generated three-dimensional model having the attribute information "wide face", and the evaluation unit 113 evaluates it, and the generated three-dimensional models G1 and G3 that have received a predetermined evaluation are output, so that output three-dimensional human models P1 and P2, which are desired three-dimensional human models having wide facial features, are output, as shown in Fig. 6.

[0117] In this way, the entire process of outputting the output 3D human model is carried out automatically, allowing the designer to output a 3D human model with the attribute information "wide face" desired by the user (client) with less effort.

[0118] [Receive user evaluation information] FIG. 7 is an explanatory diagram showing an example of machine learning using user evaluation information. Machine learning using user evaluation information will be described using the example shown in FIG. 7. A user (orderer) transmits (inputs) evaluations of the output three-dimensional human models P1 and P2 to the generating device 1 as user evaluation information. In the example shown in FIG. 7, the user (orderer) gave the output three-dimensional human model P1 an evaluation of "80" points and the output three-dimensional human model P2 an evaluation of "90" points. That is, the user (orderer) gave a higher evaluation to the output three-dimensional human model P2, which has a wider face shape, which is an evaluation different from the evaluation using the evaluation criteria. Then, the user (orderer) transmitted these evaluations to the generating device 1 as user evaluation information S1 and S2. The generating device 1 executes the receiving unit 115 and the updating unit 116, and executes receiving the user evaluation information and updating the human model information table 121.

[0119] [Perform unsupervised machine learning] The generating device 1 executes the machine learning unit 117, and causes the second neural network N2 to generate a 3D human model by unsupervised learning. The machine learning unit 117 then updates the second neural network N2 stored in the neural network table 122.

[0120] As described above, the evaluation unit 113 gave a higher evaluation to the output three-dimensional human model P1 than to the output three-dimensional human model P2 based on the information stored in the original human model information table 121 shown in FIG.

[0121] However, as shown in FIG. 7(a), the generating device 1 received user evaluation information S1 that gave an evaluation of "80" points to the output three-dimensional human model P1, and user evaluation information S2 that gave an evaluation of "90" points to the output three-dimensional human model P1. In other words, the user (orderer) gave a higher evaluation to the output three-dimensional human model P2, which has a wider face shape, which was different from the evaluation using the evaluation criteria. This is because the evaluation criteria based on machine learning using the initial human model information table 121 shown in FIG. 2 included "dark skin," "no beard," and "dark hair," which are characteristics of the three-dimensional human model configuration information that are not directly related to "wide face," in the evaluation criteria for the attribute information "wide face."

[0122] The update unit 116 updates the human model information table 121 using the output three-dimensional human models P1 and P2 and the user evaluation information S1 and S2. Then, the machine learning unit 117 performs unsupervised machine learning on the second neural network N2 using the updated human model information table 121. As a result, the second neural network N2 performs machine learning on the features of the three-dimensional human model related to the attribute information "wide face" based on the above-mentioned evaluation. Then, the second neural network N2 becomes a neural network that has more deeply learned the features of the three-dimensional human model configuration information related to "wide face."

[0123] As shown in FIG. 7(b), the generation unit 112 after the machine learning generates three-dimensional human models G11, G12, G13, and G14 to be generated, each having various skin colors, beards, hair colors, and wide faces. That is, the unsupervised machine learning performed by the machine learning unit 117 enables the generation of a more vivid three-dimensional human model desired by a user (a person who orders a designer). Because unsupervised machine learning can be performed without externally provided model training data, the generation device 1 can generate a more vivid three-dimensional human model desired by a user (a person who orders a designer) without increasing the designer's workload.

[0124] Therefore, according to the three-dimensional human model generating device 1 of this embodiment, a designer involved in computer graphics can generate a three-dimensional human model desired by a user (orderer) with as little effort as possible.

[0125] [Another example of information stored in the person model information table 121] The attribute information stored in the character model information table 121 may include the following information. The character model information table 121 can store, for example, the body shape of a 3D character model desired by a user. Furthermore, when the 3D character model desired by a user is to be displayed on the display unit 13 or the display unit of the external device 120, the character model information table 121 can store background information suitable for the 3D character model desired by the user. The character model information table 121 can store the type, design, color, and pattern of clothing suitable for the 3D character model desired by the user. Furthermore, the character model information table 121 can store the type, design, and pattern of bags suitable for the 3D character model desired by the user. Furthermore, the character model information table 121 can store the type and color of accessories suitable for the 3D character model desired by the user. Furthermore, the character model information table 121 can store hair and makeup suitable for the 3D character model desired by the user. Furthermore, the character model information table 121 can store footwear suitable for the body shape, clothing, and the like of the 3D character model desired by the user. Footwear includes shoes, geta (wooden clogs), sandals, boots, pumps, mules, sandals, etc. Furthermore, the human model information table 121 can store the facial expression, age, gender (male or female), and face and body angles of the 3D human model desired by the user. Gender information can also include masculine or feminine elements. The face angle includes, for example, the angle of the face centerline relative to the torso centerline. The body angle includes, for example, the pose.

[0126] The body shapes of the 3D human model include, for example, thin, normal, and plump. The backgrounds of the 3D human model include, for example, mountains, the sea, urban areas, indoors, outdoors, and the sky. The types of clothing worn by the human model include shirts, blouses, sweaters, knitwear, jackets, skirts, cardigans, vests, and pants. The accessories include necklaces, earrings, bracelets, sunglasses, and hats. The hair and makeup options include short cuts, bobs, long hair, perms, and straight hair.

[0127] The type of clothing worn by a 3D character model, the design, color, and pattern of the clothing, the type of bag carried by the 3D character model, the design of the bag, the type of accessories worn by the 3D character model, the color of the accessories, the hair and makeup of the 3D character model, footwear, the facial expression of the 3D character model, age, gender (male or female), and the angle of the face and body can all be created by a person using Apparel 3D. With Apparel 3D, a person analyzes the ordered 3D character model and generates the 3D character model by switching and changing various pre-prepared patterns on the basic model.

[0128] The type of clothing, design, color, pattern, bag type, design, accessory type, color, hair and makeup, shoes, facial expression, age, gender (male or female), and face and body angle of the 3D character model desired by the user may be generated by an AI system. The AI ​​system analyzes the ordered 3D character model and generates images of clothing and other items designed to match the preferences of the orderer. The apparel 3D system and AI system may be constructed by the 3D character model generation device 1 or may be constructed using an external device 120.

[0129] [Methods for using other examples of information in the flowcharts of Figures 4, 5, 6, and 7(a) and (b)] In the flowcharts of Figures 4, 5, 6, 7(a) and 7(b), it is possible to process and make decisions at each step using information contained in the attribute information, such as the model's body shape, the model's background, the type of clothes worn by the human model, the design of the clothes, the color of the clothes, the pattern of the clothes, the type of bag carried by the human model, the design of the bag, the type of accessories worn by the human model, the color of the accessories, the human model's hair and makeup, footwear, the facial expression of the three-dimensional human model, the age, gender (male or female), and the angle of the face and body.

[0130] [supplementary explanation] Although the embodiments and various modifications of the present disclosure have been described above, the present disclosure is not limited to these above-described embodiments and various modifications. Furthermore, the effects described in the embodiments and various modifications of the present disclosure are merely a list of the most preferable effects resulting from the present disclosure, and the effects of the present disclosure are not limited to those described in the embodiments and various modifications of the present disclosure.

[0131] Furthermore, the above-described embodiments have been described in detail to clearly explain the present disclosure, and are not necessarily limited to those including all of the described configurations. Furthermore, it is possible to replace part of the configuration of one embodiment with the configuration of another embodiment, or to add the configuration of another embodiment to the configuration of one embodiment. Furthermore, the control unit 11 can improve the image quality and accuracy of the image of the 3D human model displayed on the display unit 13 or the display unit 127 by increasing the accuracy of image encoding and the number of times and amount of information for machine learning. Step S1 in FIG. 4 is a machine learning step. Step S6 is an update step. Determining Yes in step S7 is a receiving step. Step S5 is an output step. Step S3 is a generation step. Step S4 is an evaluation step. Step S1 is an evaluation learning step. [Explanation of symbols]

[0132] 1 generator 11 Control section 111 Evaluation and Learning Department 112 Generation part 113 Evaluation Department 114 Output section 115 Receiving unit 116 Update Department 117 Machine Learning Department 12 Storage section 121 Person Model Information Table 122 Neural Network Table 13 Display section 14 Input section G1, G2, G3, G4 Generated 3D human model G11, G12, G13, G14 Generated 3D human model P1, P2 3D human model to be output S1, S2 user evaluation information N1 First Neural Network N2 Second Neural Network

Claims

1. A database that stores attribute information of a three-dimensional human model and evaluation criteria for the attributes of a generated three-dimensional human model generated using a neural network for each of the attribute information; an evaluation unit that receives the attribute information desired by a user, and evaluates the plurality of types of generated three-dimensional human models using the evaluation criteria corresponding to the attribute information and the attribute information associated with each of the plurality of types of generated three-dimensional human models; an output unit that outputs, as an output three-dimensional human model, one or more types of the three-dimensional human model that have received a relatively high predetermined evaluation by the evaluation unit from among the plurality of types of the three-dimensional human model to be generated; A three-dimensional human model output device comprising:

2. an update unit that registers, for each of the output three-dimensional human models, human model configuration information capable of configuring a three-dimensional human model for the output three-dimensional human model and human model information associated with the attribute information; The three-dimensional human model output device according to claim 1 , further comprising: an evaluation learning unit that performs machine learning of the evaluation criteria based on the attribute information linked to each of the plurality of registered human model information.

3. The three-dimensional human model output device described in Claim 2, wherein the evaluation learning unit learns one or more attribute information that is commonly linked to the registered multiple human model information to which specific attribute information is linked, as an evaluation criterion for the specific attribute information.

4. The method further includes a generation unit that receives the attribute information desired by a user and generates the generated three-dimensional human model to which multiple pieces of attribute information are linked, The three-dimensional human model output device according to claim 2 , wherein the update unit links and registers the output three-dimensional human model and the attribute information used in generating the three-dimensional human model to be generated.

5. The three-dimensional human model output device according to claim 2 , further comprising a machine learning unit capable of performing the machine learning by unsupervised learning for both the neural network used to generate the three-dimensional human model and the machine learning of the evaluation criterion.

6. The three-dimensional human model output device according to claim 1 , wherein the attribute information includes information relating to characteristics of the person of the three-dimensional human model.

7. The three-dimensional human model output device according to claim 1 , wherein the attribute information includes information relating to a purpose of use of the three-dimensional human model.

8. 3D human model output device, a storing step of storing attribute information of the three-dimensional human model and evaluation criteria relating to the attributes of the generated three-dimensional human model generated using the neural network in a database for each of the attribute information; an evaluation step of receiving the attribute information desired by a user, and evaluating the plurality of types of three-dimensional human models to be generated in accordance with the evaluation criteria corresponding to the attribute information and the attribute information associated with each of the plurality of types of three-dimensional human models to be generated; an output step of outputting, as an output three-dimensional human model, one or more types of the three-dimensional human model to be generated that have relatively high predetermined evaluations made in the evaluation step, from among the plurality of types of the three-dimensional human model to be generated; A program that executes the following.

9. The computer a storage process for storing attribute information of the three-dimensional human model and evaluation criteria related to the attributes of the generated three-dimensional human model generated using the neural network in a database for each of the attribute information; an evaluation process of receiving the attribute information desired by a user, and evaluating the plurality of types of three-dimensional human models to be generated according to the evaluation criteria corresponding to the attribute information and the attribute information associated with each of the plurality of types of three-dimensional human models to be generated; an output process of outputting, as an output three-dimensional human model, one or more types of the three-dimensional human model that have received a relatively high predetermined evaluation in the evaluation process from among the plurality of types of the three-dimensional human model to be generated; A three-dimensional human model output method that executes the above.

Images