KR102579684B1 - Method for modeling a digital human by using the neural network trianing model - Google Patents

Abstract

In accordance with one embodiment of the present disclosure, a method for digital human modeling, performed by one or more processors of a computing device, is disclosed. The method includes identifying digital human information and differences based on modeling target information using a neural network model; And it may include calculating a reward for the neural network model based on the difference identification result.

Description

Digital human modeling method using a neural network learning model {METHOD FOR MODELING A DIGITAL HUMAN BY USING THE NEURAL NETWORK TRIANING MODEL}

This disclosure relates to a method of using a neural network learning model for digital human modeling, and more specifically, to a method of learning a neural network model to model a desired person as a digital human.

We use the digital human creation function provided by realtime 3D engines such as Unreal, Unity, Blender, Maya, iCloud, etc. to create the human being we want to create. To create a virtual human, you must use a method to create a digital human by modifying its face. Therefore, starting from a template, designers must make detailed adjustments to create the face of the person they want, such as adjusting the height of the nose and the size of the eyes.

In addition, detailed adjustment of each part for desired modeling in a given template also has a high level of complexity. Because artificially detailed adjustment of the placement and size of each face texture takes a lot of time, research is needed on modeling methods that can reduce complexity.

The present disclosure aims to solve the problem of providing a learning method of a neural network model for modeling digital humans.

A method performed by a computing device according to an embodiment of the present disclosure for realizing the above-described problem is disclosed. The method includes transforming a digital human using a neural network model; Comparing information extracted from the modified digital human and information about the modeling object; and determining a reward for the neural network model based on the comparison result.

Alternatively, the information about the modeling object may include a two-dimensional (2D) image of the modeling object, and the information extracted from the modified digital human may include a 2D image extracted from the shape of the 3D digital human. It may include, and the comparing step may include comparing a 2D image of the modeling object and a 2D image extracted from the 3D digital human shape.

Alternatively, the 2D image extracted from the shape of the 3D digital human may include a 2D image obtained by rendering the 3D digital human.

Alternatively, the information about the modeling object may include at least one of a 2D image for the front or a 2D image for the side of the modeling object, and the information extracted from the modified digital human is the 3D digital human. It may include at least one of a 2D image extracted in the frontal direction of the human or a 2D image extracted in the side direction, and the step of comparing includes a 2D image of the front of the modeling object and a 2D image of the front of the 3D digital human. It may include at least one of comparing extracted 2D images or comparing a 2D image for a side of the modeling object with a 2D image extracted in a side direction of the 3D digital human.

Alternatively, the information on the digital human may include at least one of frontal image information, side image information, or characteristic information of the digital human.

Alternatively, the information about the modeling object may include feature information about the appearance of the modeling object, and the information extracted from the modified digital human includes feature information about the appearance of the modified digital human. It may include, and the comparing step may include comparing feature information about the appearance of the modeling object and feature information about the appearance of the modified digital human.

Alternatively, the characteristic information about the appearance may include eye width, eye width, eye height, face shape, nose height, nose width, nose width, skin color, saturation of skin color, brightness of skin color, size ratio and arrangement of eyes, nose and mouth. , may include information about at least one of the degree of protrusion of the cheekbones, hair color, hair color saturation, or hair color brightness.

Alternatively, the step of comparing feature information about the appearance of the modeling object and feature information about the appearance of the modified digital human may include the size of the 2D image of the modeling object or the 2D image extracted from the 3D digital human shape. After adjusting the size of , it may include performing a comparison.

Alternatively, the compensation for the neural network model may include a first compensation based on a comparison between frontal images, a second compensation based on a comparison between side images, and a comparison between appearance features. It may be based on an ensemble of third rewards.

Alternatively, the neural network model may be learned through reinforcement learning based on a state containing information about the digital human, an action that transforms the digital human, and a reward for the action.

Alternatively, the comparing step may include calculating a degree of similarity between information extracted from the modified digital human and information about the modeling object, and the step of determining the compensation may include calculating the similarity between the information extracted from the modified digital human and the information about the modeling object. It may include determining the compensation based on similarity.

Alternatively, the neural network model calculates similarity between information extracted from the modified digital human and information about the modeling object, and if the calculated similarity is higher than a predetermined level, information about the reinforcement learning path is collected. can be terminated.

According to an embodiment of the present disclosure for realizing the above-described object, a computer program stored in a computer-readable storage medium is disclosed. When the computer program is executed on one or more processors, it causes the one or more processors to perform operations for digital human modeling, the operations including: transforming a digital human using a neural network model; An operation of comparing information extracted from a modified digital human and information about a modeling object; and determining compensation for the neural network model based on the comparison result.

A computing device according to an embodiment of the present disclosure for realizing the above-described problem is disclosed. The device includes at least one processor; and a memory, wherein the processor transforms the digital human using a neural network model; Compare information extracted from the modified digital human and information about the modeling target; And it may be configured to determine compensation for the neural network model based on the comparison result.

The present disclosure can provide a method of using a neural network learning model for digital human modeling, and through this, can provide an optimized digital human modeling technology using a neural network model.

1 is a block diagram of a computing device for setting a reinforcement learning reward of a neural network model according to an embodiment of the present disclosure.
Figure 2 is a schematic diagram showing a network function according to an embodiment of the present disclosure.
Figure 3 is a conceptual diagram for explaining the reinforcement learning process of a neural network model according to an embodiment of the present disclosure.
Figure 4 is a flowchart showing a neural network model learning method for digital human modeling according to an embodiment of the present disclosure.
Figure 5 is a schematic diagram showing a method of comparing a 2D image of a modeling object and a 2D image extracted from the shape of a 3D digital human according to an embodiment of the present disclosure.
Figure 6 is a schematic diagram showing a method for calculating similarity between information about a modeling object and information extracted from a modified digital human according to an embodiment of the present disclosure.
Figure 7 is an algorithm flowchart showing the steps of granting compensation to the neural network model and transforming a digital human using the neural network model.
Figure 8 is a brief, general schematic diagram of an example computing environment in which embodiments of the present disclosure may be implemented.

Various embodiments are now described with reference to the drawings. In this specification, various descriptions are presented to provide an understanding of the disclosure. However, it is clear that these embodiments may be practiced without these specific descriptions.

As used herein, the terms “component,” “module,” “system,” and the like refer to a computer-related entity, hardware, firmware, software, a combination of software and hardware, or an implementation of software. For example, a component may be, but is not limited to, a process running on a processor, a processor, an object, a thread of execution, a program, and/or a computer. For example, both an application running on a computing device and the computing device can be a component. One or more components may reside within a processor and/or thread of execution. A component may be localized within one computer. A component may be distributed between two or more computers. Additionally, these components can execute from various computer-readable media having various data structures stored thereon. Components can transmit signals, for example, with one or more data packets (e.g., data and/or signals from one component interacting with other components in a local system, a distributed system, to other systems and over a network such as the Internet). Depending on the data being transmitted, they may communicate through local and/or remote processes.

Additionally, the term “or” is intended to mean an inclusive “or” and not an exclusive “or.” That is, unless otherwise specified or clear from context, “X utilizes A or B” is intended to mean one of the natural implicit substitutions. That is, either X uses A; X uses B; Or, if X uses both A and B, “X uses A or B” can apply to either of these cases. Additionally, the term “and/or” as used herein should be understood to refer to and include all possible combinations of one or more of the related listed items.

Additionally, the terms “comprise” and/or “comprising” should be understood to mean that the corresponding feature and/or element is present. However, the terms “comprise” and/or “comprising” should be understood as not excluding the presence or addition of one or more other features, elements and/or groups thereof. Additionally, unless otherwise specified or the context is clear to indicate a singular form, the singular terms herein and in the claims should generally be construed to mean “one or more.”

And, the term “at least one of A or B” should be interpreted to mean “a case containing only A,” “a case containing only B,” and “a case of combining A and B.”

Those skilled in the art will additionally recognize that the various illustrative logical blocks, components, modules, circuits, means, logic, and algorithm steps described in connection with the embodiments disclosed herein may be implemented using electronic hardware, computer software, or a combination of both. It must be recognized that it can be implemented with To clearly illustrate the interchangeability of hardware and software, various illustrative components, blocks, configurations, means, logics, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented in hardware or software will depend on the specific application and design constraints imposed on the overall system. A skilled technician can implement the described functionality in a variety of ways for each specific application. However, such implementation decisions should not be construed as causing a departure from the scope of the present disclosure.

The description of the presented embodiments is provided to enable anyone skilled in the art to use or practice the present invention. Various modifications to these embodiments will be apparent to those skilled in the art. The general principles defined herein may be applied to other embodiments without departing from the scope of the disclosure. Therefore, the present invention is not limited to the embodiments presented herein. The present invention is to be interpreted in the broadest scope consistent with the principles and novel features presented herein.

In this disclosure, network function, artificial neural network, and neural network may be used interchangeably.

1 is a block diagram of a computing device for using a neural network learning model for digital human modeling according to an embodiment of the present disclosure.

The configuration of the computing device 100 shown in FIG. 1 is only a simplified example. In one embodiment of the present disclosure, the computing device 100 may include different components for performing the computing environment of the computing device 100, and only some of the disclosed components may configure the computing device 100.

The computing device 100 may include a processor 110, a memory 130, and a network unit 150.

The processor 110 may be composed of one or more cores, and may include a central processing unit (CPU), a general purpose graphics processing unit (GPGPU), and a tensor processing unit (TPU) of a computing device. unit) may include a processor for data analysis and deep learning. The processor 110 may read a computer program stored in the memory 130 and perform data processing for machine learning according to an embodiment of the present disclosure. According to an embodiment of the present disclosure, the processor 110 may perform an operation for learning a neural network. The processor 110 is used for learning neural networks, such as processing input data for learning in deep learning (DL), extracting features from input data, calculating errors, and updating the weights of the neural network using backpropagation. Calculations can be performed. At least one of the CPU, GPGPU, and TPU of the processor 110 may process learning of the network function. For example, CPU and GPGPU can work together to process learning of network functions and data classification using network functions. Additionally, in one embodiment of the present disclosure, the processors of a plurality of computing devices can be used together to process learning of network functions and data classification using network functions. Additionally, a computer program executed in a computing device according to an embodiment of the present disclosure may be a CPU, GPGPU, or TPU executable program.

The processor 110 according to an embodiment of the present disclosure recognizes information about a modeling object for digital human modeling, transforms a digital human using a neural network model, and uses the information extracted from the transformed digital human and the modeling object. After comparing the information, operations to determine a reward for the neural network model can be performed based on the comparison result. “Digital human” as used in this disclosure may be differently named as virtual human, meta human, etc., and may be referred to as Unreal, Unity, Blender, Maya, etc. , may include digital human assets provided by real-time 3D engines including iCloud, etc. For example, the processor 110 may use a neural network model to transform a digital human and compare information extracted from the transformed digital human with information about the modeling object. At this time, the information about the modeling object is 2D image information about the front of the modeling object, 2D image information about the side, or the appearance of the modeling object. It may be at least one of the characteristic information about. In addition, the information extracted from the modified digital human is at least one of 2D image information extracted in the frontal direction of the 3D digital human, 2D image information extracted in the side direction, or feature information about the appearance of the modified digital human. It can be. Additionally, according to another embodiment, rendering may be used when extracting a 2D image from the 3D digital human. For example, the 3D digital human may be rendered to obtain a 2D image in the frontal or side direction. Additionally, the characteristic information about the appearance includes eye width, eye width, eye height, face shape, nose height, nose width, nose width, skin color, skin color saturation, skin color brightness, size ratio and arrangement of eyes, nose, and mouth, and cheekbones. It may include information about at least one of the degree of protrusion, hair color, hair color saturation, or hair color brightness.

According to an embodiment of the present disclosure, the processor 110 uses reinforcement learning based on a state containing information about a digital human, an action to transform the digital human, and a reward for the action, A neural network model can be trained.

In addition, the processor 110 uses a neural network model to calculate similarity with information extracted from the transformed digital human based on information about the modeling object, and uses the neural network model based on the similarity calculation result. The reward can be determined and returned with the status. Through this, reinforcement learning on the neural network model can be performed by allowing the neural network model to perform actions according to the next cycle.

According to an embodiment of the present disclosure, the memory 130 may store any type of information generated or determined by the processor 110 and any type of information received by the network unit 150.

According to an embodiment of the present disclosure, the memory 130 is a flash memory type, hard disk type, multimedia card micro type, or card type memory (e.g. (e.g. SD or -Only Memory), and may include at least one type of storage medium among magnetic memory, magnetic disk, and optical disk. The computing device 100 may operate in connection with web storage that performs a storage function of the memory 130 on the Internet. The description of the memory described above is merely an example, and the present disclosure is not limited thereto.

The network unit 150 according to an embodiment of the present disclosure may use any type of known wired or wireless communication system.

For example, the network unit 150 may receive information about a modeling target from an external system. At this time, the information received from the database may be training data or inference data for a neural network model. The information about the modeling object may include the information of the above-described example, but is not limited to the above-described example and may be configured in various ways within a range that can be understood by those skilled in the art.

Additionally, the network unit 150 can transmit and receive information processed by the processor 110, a user interface, etc. through communication with other terminals. For example, the network unit 150 may provide a user interface generated by the processor 110 to a client (e.g. user terminal). Additionally, the network unit 150 may receive external input from a user authorized as a client and transmit it to the processor 110. At this time, the processor 110 may process operations such as output, modification, change, and addition of information provided through the user interface based on the user's external input received from the network unit 150.

Meanwhile, the computing device 100 according to an embodiment of the present disclosure is a computing system that transmits and receives information through communication with a client and may include a server. At this time, the client may be any type of terminal that can access the server. For example, the computing device 100, which is a server, may receive information for digital human modeling from an external database, generate modeling results, and provide a user interface regarding the modeling results to a user terminal. At this time, the user terminal outputs the user interface received from the computing device 100, which is a server, and can input or process information through interaction with the user.

In an additional embodiment, the computing device 100 may include any type of terminal that receives data resources generated by an arbitrary server and performs additional information processing.

Figure 2 is a schematic diagram showing a network function according to an embodiment of the present disclosure.

Throughout this specification, computational model, neural network, network function, and neural network may be used interchangeably. A neural network can generally consist of a set of interconnected computational units, which can be referred to as nodes. These nodes may also be referred to as neurons. A neural network consists of at least one node. Nodes (or neurons) that make up neural networks may be interconnected by one or more links.

Within a neural network, one or more nodes connected through a link may form a relative input node and output node relationship. The concepts of input node and output node are relative, and any node in an output node relationship with one node may be in an input node relationship with another node, and vice versa. As described above, input node to output node relationships can be created around links. One or more output nodes can be connected to one input node through a link, and vice versa.

In a relationship between an input node and an output node connected through one link, the value of the data of the output node may be determined based on the data input to the input node. Here, the link connecting the input node and the output node may have a weight. Weights may be variable and may be varied by the user or algorithm in order for the neural network to perform the desired function. For example, when one or more input nodes are connected to one output node by respective links, the output node is set to the values input to the input nodes connected to the output node and the links corresponding to each input node. The output node value can be determined based on the weight.

As described above, in a neural network, one or more nodes are interconnected through one or more links to form an input node and output node relationship within the neural network. The characteristics of the neural network can be determined according to the number of nodes and links within the neural network, the correlation between the nodes and links, and the value of the weight assigned to each link. For example, if the same number of nodes and links exist and two neural networks with different weight values of the links exist, the two neural networks may be recognized as different from each other.

A neural network may consist of a set of one or more nodes. A subset of nodes that make up a neural network can form a layer. Some of the nodes constituting the neural network may form one layer based on the distances from the first input node. For example, a set of nodes with a distance n from the initial input node may constitute n layers. The distance from the initial input node can be defined by the minimum number of links that must be passed to reach the node from the initial input node. However, this definition of a layer is arbitrary for explanation purposes, and the order of a layer within a neural network may be defined in a different way than described above. For example, a layer of nodes may be defined by distance from the final output node.

The initial input node may refer to one or more nodes in the neural network through which data is directly input without going through links in relationships with other nodes. Alternatively, in a neural network network, in the relationship between nodes based on links, it may mean nodes that do not have other input nodes connected by links. Similarly, the final output node may refer to one or more nodes that do not have an output node in their relationship with other nodes among the nodes in the neural network. Additionally, hidden nodes may refer to nodes constituting a neural network other than the first input node and the last output node.

The neural network according to an embodiment of the present disclosure is a neural network in which the number of nodes in the input layer may be the same as the number of nodes in the output layer, and the number of nodes decreases and then increases again as it progresses from the input layer to the hidden layer. You can. In addition, the neural network according to another embodiment of the present disclosure may be a neural network in which the number of nodes in the input layer may be less than the number of nodes in the output layer, and the number of nodes decreases as it progresses from the input layer to the hidden layer. there is. In addition, the neural network according to another embodiment of the present disclosure may be a neural network in which the number of nodes in the input layer may be greater than the number of nodes in the output layer, and the number of nodes increases as it progresses from the input layer to the hidden layer. You can. A neural network according to another embodiment of the present disclosure may be a neural network that is a combination of the above-described neural networks.

A deep neural network (DNN) may refer to a neural network that includes multiple hidden layers in addition to the input layer and output layer. Deep neural networks allow you to identify latent structures in data. In other words, it is possible to identify the potential structure of a photo, text, video, voice, or music (e.g., what object is in the photo, what the content and emotion of the text are, what the content and emotion of the voice are, etc.) . Deep neural networks include convolutional neural networks (CNN), recurrent neural networks (RNN), auto encoders, generative adversarial networks (GAN), and restricted Boltzmann machines (RBM). machine), deep belief network (DBN), Q network, U network, Siamese network, Generative Adversarial Network (GAN), etc. The description of the deep neural network described above is only an example and the present disclosure is not limited thereto.

In one embodiment of the present disclosure, the network function may include an autoencoder. An autoencoder may be a type of artificial neural network to output output data similar to input data. The autoencoder may include at least one hidden layer, and an odd number of hidden layers may be placed between input and output layers. The number of nodes in each layer may be reduced from the number of nodes in the input layer to an intermediate layer called the bottleneck layer (encoding), and then expanded symmetrically and reduced from the bottleneck layer to the output layer (symmetrical to the input layer). Autoencoders can perform nonlinear dimensionality reduction. The number of input layers and output layers can be corresponded to the dimension after preprocessing of the input data. In an auto-encoder structure, the number of nodes in the hidden layer included in the encoder may have a structure that decreases as the distance from the input layer increases. If the number of nodes in the bottleneck layer (the layer with the fewest nodes located between the encoder and decoder) is too small, not enough information may be conveyed, so if it is higher than a certain number (e.g., more than half of the input layers, etc.) ) may be maintained.

A neural network may be trained in at least one of supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning. Learning of a neural network may be a process of applying knowledge for the neural network to perform a specific operation to the neural network.

Neural networks can be trained to minimize output errors. In neural network learning, learning data is repeatedly input into the neural network, the output of the neural network and the error of the target for the learning data are calculated, and the error of the neural network is transferred from the output layer of the neural network to the input layer in the direction of reducing the error. This is the process of updating the weight of each node in the neural network through backpropagation. In the case of teacher learning, learning data in which the correct answer is labeled in each learning data is used (i.e., labeled learning data), and in the case of non-teacher learning, the correct answer may not be labeled in each learning data. That is, for example, in the case of teacher learning regarding data classification, the learning data may be data in which each learning data is labeled with a category. Labeled training data is input to the neural network, and the error can be calculated by comparing the output (category) of the neural network with the label of the training data. As another example, in the case of non-teachable learning for data classification, the error can be calculated by comparing the input training data with the neural network output. The calculated error is backpropagated in the reverse direction (i.e., from the output layer to the input layer) in the neural network, and the connection weight of each node in each layer of the neural network can be updated according to backpropagation. The amount of change in the connection weight of each updated node may be determined according to the learning rate. The neural network's calculation of input data and backpropagation of errors can constitute a learning cycle (epoch). The learning rate may be applied differently depending on the number of repetitions of the learning cycle of the neural network. For example, in the early stages of neural network training, a high learning rate can be used to increase efficiency by allowing the neural network to quickly achieve a certain level of performance, and in the later stages of training, a low learning rate can be used to increase accuracy.

In the learning of neural networks, the training data can generally be a subset of real data (i.e., the data to be processed using the learned neural network), and thus the error for the training data is reduced, but the error for the real data is reduced. There may be an incremental learning cycle. Overfitting is a phenomenon in which errors in actual data increase due to excessive learning on training data. For example, a phenomenon in which a neural network that learned a cat by showing a yellow cat fails to recognize that it is a cat when it sees a non-yellow cat may be a type of overfitting. Overfitting can cause errors in machine learning algorithms to increase. To prevent such overfitting, various optimization methods can be used. To prevent overfitting, methods such as increasing the learning data, regularization, dropout to disable some of the network nodes during the learning process, and use of a batch normalization layer can be applied. You can.

Figure 3 is a conceptual diagram for explaining the reinforcement learning process of a neural network model according to an embodiment of the present disclosure.

Reinforcement learning is a learning method that trains a neural network model based on the reward calculated for the action selected by the neural network model so that the neural network model can determine a better action based on the state. A state is a set of values that indicate what the situation is at the current point in time, and can be understood as an input to a neural network model. Action refers to a decision based on the options that a neural network model can take, and can be understood as the output of a neural network model. Reward refers to the benefit that follows when a neural network model performs an action, and represents the value evaluated for the current state and action. Reinforcement learning can be understood as learning through trial and error in that rewards are given for actions. The reward given to the neural network model during the reinforcement learning process may be the cumulative reward of the results of multiple actions. Through reinforcement learning, it is possible to create a neural network model that maximizes the return, such as the reward itself or the total sum of the rewards, by considering rewards according to various states and actions.

Referring to FIG. 3, in reinforcement learning, there is a neural network model 210 and a result 220 of the model's behavior. The action result 220 can be understood to mean information necessary for reinforcement learning of the neural network model 210. When the neural network model 210 takes an action, the state of the result changes as a result of the action 220, and the model 210 may receive compensation for the action. The goal of reinforcement learning is to train the neural network model (210) to receive as many rewards as possible from the results of the action (220).

According to an embodiment of the present disclosure, the processor 110 uses reinforcement learning based on a state containing information about a digital human, an action to transform the digital human, and a reward for the action, A neural network model can be trained.

The processor 110 uses a neural network model to calculate similarity with information extracted from the transformed digital human based on information about the modeling object, and calculates the similarity of the neural network model based on the similarity calculation result. The reward can be determined and returned along with the status. Through this, reinforcement learning on the neural network model can be performed by allowing the neural network model to perform actions according to the next cycle.

For example, the processor 110 may perform a specific n-th action to transform a digital human through a neural network model. The processor 110 may estimate the reward Rn for the nth action in a specific order, and return the state Sn of the result of the action and the estimated reward Rn to the neural network model. The processor 110 may input the resulting state and reward for the nth action in a specific sequence into a neural network model and perform the n+1th action at the next time. The processor 110 may repeat this cycle to perform reinforcement learning on the neural network model so that the object to be modeled is modeled as a digital human.

Figure 4 is a flowchart showing a neural network model learning method for digital human modeling according to an embodiment of the present disclosure.

Referring to FIG. 4, the computing device 100 according to an embodiment of the present disclosure may receive information about a modeling target from an external system (S110). The external system may be a server, database, etc. that stores and manages information for modeling digital humans. The computing device 100 may use information received from an external system as input data for learning a neural network model for digital human modeling. The computing device 100 may use information received from an external system as input data for the operation (inference) of a neural network model for modeling digital humans. The mode of use of such information may vary depending on the purpose of learning or operation (inference) of the neural network model.

The computing device 100 may transform the digital human based on the received information about the modeling object (S120).

Additionally, the computing device 100 may learn a neural network model by calculating the similarity between the two pieces of information based on the information extracted from the modified digital human in step S120 and the information about the modeling object (S130). At this time, learning of the neural network model may be performed based on reinforcement learning. For example, the computing device 100 inputs information about the modeling target into a neural network model to perform an action to transform a digital human, and returns a reward according to the action to the neural network model to perform reinforcement learning on the neural network model. You can.

The computing device 100 uses a neural network model learned in step S130 to determine compensation based on the calculated similarity between the two pieces of information based on information about the modeling object and information extracted from the modified digital human. can be given (S140). The computing device 100 can effectively model a digital human similar to a modeling object by learning a neural network model through the neural network model reward granting step in step S140. The computing device 100 can use a neural network model learned through reinforcement learning to reduce modeling time, cost, and deviation in modeling quality, which are problems faced by existing modeling methods.

According to an embodiment of the present disclosure, the state to be input to the neural network model may include information about the modeling target. The information about the modeling object may be at least one of 2D image information about the front of the modeling object, 2D image information about the side, or characteristic information about the appearance of the modeling object. Additionally, the characteristic information about the appearance includes eye width, eye width, eye height, face shape, nose height, nose width, nose width, skin color, It may include information such as saturation of skin color, brightness of skin color, size ratio and arrangement of eyes, nose, and mouth, degree of protrusion of cheekbones, hair color, hair color saturation, or hair color brightness, etc. The information in this example can be understood as information that allows the neural network model to calculate the similarity between information about the appearance of the object that is the object of modeling and information extracted from the transformed digital human.

In addition, the information extracted from the modified digital human may include 2D image information extracted in the frontal direction of the 3D digital human, 2D image information extracted in the side direction, or feature information about the appearance of the modified digital human. You can. Characteristic information about the appearance of the modified digital human includes the digital human's eye width, eye width, eye height and face shape, nose height, nose width, nose width, skin color, skin color saturation, skin color brightness, and size of the eyes, nose, and mouth. It may include information such as proportion and placement, degree of protrusion of cheekbones, hair color, hair color saturation, hair color brightness, etc. Compensation may be given to the neural network model based on the results of calculating the similarity between information extracted from the modified digital human and information about the modeling target .

According to an embodiment of the present disclosure, the processor 110 may perform an action to transform a digital human by inputting a state including information about the modeling target into a neural network model. At this time, the act of modifying the digital human is an act of calculating the degree of similarity between the information based on information extracted from the modified digital human and information about the modeling object, and modifying the part of the digital human in the area where there are differences. may include. Specifically, referring to FIG. 5, when performing an action to transform a digital human based on a state including information about the modeling object, the processor 110 extracts information about the appearance of the modeling object and the transformed digital human. The similarity of the extracted information can be calculated. between two pieces of information The step of calculating the similarity may include a step 41 of comparing a 2D image 21 of the front of the modeling object with a 2D image 31 extracted in the front direction of the 3D digital human. When the digital human is deformed, the processor 110 may acquire a 2D image extracted from the shape of the deformed 3D digital human. Additionally, according to another embodiment, the 2D image extracted from the shape of the 3D digital human may include a 2D image obtained by rendering the 3D digital human. The neural network model may be given compensation determined based on a comparison between the 2D image of the modeling object and the 2D image extracted from the shape of the deformed 3D digital human. Specifically, in order to determine compensation based on the comparison between the 2D images of the two objects, a case may be included in which 2D images corresponding to the same direction of the two objects are compared (41). For example, if the 2D image of the modeling target is the side image 22, the 2D image of the digital human being compared is the 2D image 32 extracted in the side direction of the 3D digital human. You can. Additionally, the compensation for the neural network model is a first compensation based on a comparison between images in the frontal direction, a second compensation based on a comparison between images in the lateral direction, and a comparison between features for appearance. It may be determined based on the ensemble of third rewards. At this time, the ensemble method of the first reward, second reward, and third reward can be one of voting, bagging, or boosting. Specifically, voting is hard voting. Voting, soft voting, bagging can use the Random Forest algorithm, and boosting methods include AdaBoost, GBM (Gradient Boosting Machine), May include XGBoost (eXtra Gradient Boost) and LightGBM (Light Gradient Boost) algorithms. However, the ensemble method is not limited to specific embodiments and can be freely selected within the range understandable by those skilled in the art. Additionally, in order to compare the images of the two objects, the process of adjusting the size of the 2D images of the two objects to a 1:1 ratio is performed. It can be included. The neural network model of the processor 110 may perform an action to transform the digital human based on the calculated similarity. Through this transformation of the digital human, the neural network model can perform the action of efficiently and accurately modeling the digital human as a desired target.

Additionally, referring to FIG. 6, the step of the processor 110 identifying the similarity between the information about the appearance of the modeling object and the information about the appearance of the transformed digital human includes the feature information 51 about the appearance of the modeling object and the digital It may include a step (71) of calculating similarity with characteristic information (61) about the human's appearance. At this time, in order to compare information about the appearance of the two objects and calculate the similarity, a process of adjusting the size of the 2D images of the two objects to correspond to a 1:1 ratio may be included. For example, if the eye width of the 2D image of the modeling object adjusted to a 1:1 ratio is 2 cm, and the eye width of the digital human is 1.8 cm, the similarity is 90% based on the characteristic information about the appearance of the modeling object. It can be measured as Additionally, in the step of calculating the similarity between feature information about the appearance of two objects, the nose height information of the modeling target can be calculated in correspondence with the nose height information of the adjusted digital human. Accordingly, modeling efficiency can be increased by transforming the characteristic information about the appearance of the modeling object and the corresponding characteristic information about the appearance of the digital human in a direction similar to the characteristic information about the appearance of the modeling object. When a digital human is transformed according to information about the appearance of the modeling object, the size of similarity compared to the information about the appearance of the modeling object varies depending on the degree to which the digital human was transformed in the previous sequence. At this time, a case may occur in which the magnitude of similarity of the feature information about the appearance of the digital human transformed in the previous sequence is reduced compared to the feature information about the appearance of the modeling target. If this happens, the process of transforming the digital human will be repeated unnecessarily, thereby improving modeling efficiency. To do this, a neural network model must be trained to exclude the case of modifying the digital human to reduce the similarity between the information of the two objects.

According to an embodiment of the present disclosure, the processor 110 may grant compensation based on the behavior of a neural network model based on a state including information about the modeling target and information extracted from the transformed digital human.

At this time, the step of calculating and providing compensation to the neural network model includes, but is not limited to, the step corresponding to FIG. 7.

Referring to FIG. 7, FIG. 7 is an algorithm flowchart showing the steps of granting compensation to the neural network model and transforming a digital human through the neural network model.

Specifically, the processor 110 calculates similarity with information extracted from the transformed digital human based on information about the modeling object, and calculates a reward for the neural network model based on the calculated similarity to state In the return step with , the order of the transformed digital human that is the target of similarity calculation is given as 0. (311) The similarity between the information extracted from the 0th modified digital human and the information about the modeling target is calculated (312). At this time, the neural network model determines whether the similarity calculation result between the information of the two objects is higher than a predetermined level. (313) Specifically, according to one embodiment of the present invention, the similarity calculation result between two objects may be the result of measuring the similarity between feature information about the appearance of a modified digital human and feature information about the appearance of the modeling object. For example, if the eye width of the 2D image of the modeling target is 2 cm and the eye width of the digital human is 1.8 cm, the similarity can be calculated as 90% based on the characteristic information of the modeling target. At this time, in order to calculate the similarity of the two objects, a process of adjusting the size of the 2D images of the two objects to be compared so that they correspond to a 1:1 ratio may be included. In addition, the similarity calculation result is predetermined The process of determining whether the level or higher may include determining whether the similarity of the characteristic information of the two objects is 99% or higher. The expressed processes are only examples, and the process of calculating similarity and determining whether the calculation result is above a predetermined level is not limited to this. After determining whether the similarity calculation result is above a predetermined level, compensation is determined based on the calculated similarity, and compensation is given to the neural network model. (314)

For example, the compensation for the neural network model is the nth compensation determined based on the similarity calculation result between the information extracted from the nth modified digital human and the information about the modeling target and the nth modified digital human. It may include information extracted from the n+1th modified digital human, which will be modified according to the similarity calculation result after the human, and the n+1th compensation determined based on the similarity calculation result of the information on the modeling target.

For example, the reward determined according to the result of calculating the similarity between the information extracted from the modified digital human and the information about the modeling object is a negative reward calculated as one of the following equations: ), including the case. The expressed mathematical equations are only an example and the compensation is not limited to this.

[Equation 1]

[Equation 2]

The neural network model then transforms the digital human (315). After transforming the digital human, the order of the transformed digital human is assigned 1 (316). This process is repeated until the similarity calculation result is judged to be above a predetermined level. If the similarity calculation result is determined to be higher than a predetermined level, a step of terminating information collection on the reinforcement learning path of the neural network model may be included. (317) Digital human modeling efficiency can be increased by training the neural network model in a way that increases the size of similarity by comparing it with information about the modeling target every time a digital human in a specific order is modified.

According to an embodiment of the present disclosure, a computer-readable medium storing a data structure is disclosed.

Data structure can refer to the organization, management, and storage of data to enable efficient access and modification of data. Data structure can refer to the organization of data to solve a specific problem (e.g., retrieving data, storing data, or modifying data in the shortest possible time). A data structure may be defined as a physical or logical relationship between data elements designed to support a specific data processing function. Logical relationships between data elements may include connection relationships between user-defined data elements. Physical relationships between data elements may include actual relationships between data elements that are physically stored in a computer-readable storage medium (e.g., a persistent storage device). A data structure may specifically include a set of data, relationships between data, and functions or instructions applicable to the data. Effectively designed data structures allow computing devices to perform computations while minimizing the use of the computing device's resources. Specifically, computing devices can increase the efficiency of operations, reading, insertion, deletion, comparison, exchange, and search through effectively designed data structures.

Data structures can be divided into linear data structures and non-linear data structures depending on the type of data structure. A linear data structure may be a structure in which only one piece of data is connected to another piece of data. Linear data structures may include List, Stack, Queue, and Deque. A list can refer to a set of data that has an internal order. The list may include a linked list. A linked list may be a data structure in which data is connected in such a way that each data is connected in a single line with a pointer. In a linked list, a pointer may contain connection information to the next or previous data. Depending on its form, a linked list can be expressed as a singly linked list, a doubly linked list, or a circularly linked list. A stack may be a data listing structure that allows limited access to data. A stack can be a linear data structure in which data can be processed (for example, inserted or deleted) at only one end of the data structure. Data stored in the stack may have a data structure (LIFO-Last in First Out) where the later it enters, the sooner it comes out. A queue is a data listing structure that allows limited access to data. Unlike the stack, it can be a data structure (FIFO-First in First Out) where data stored later is released later. A deck can be a data structure that can process data at both ends of the data structure.

A non-linear data structure may be a structure in which multiple pieces of data are connected behind one piece of data. Nonlinear data structures may include graph data structures. A graph data structure can be defined by vertices and edges, and an edge can include a line connecting two different vertices. Graph data structure may include a tree data structure. A tree data structure may be a data structure in which there is only one path connecting two different vertices among a plurality of vertices included in the tree. In other words, it may be a data structure that does not form a loop in the graph data structure.

Throughout this specification, computational model, neural network, network function, and neural network may be used interchangeably. Below, it is described in a unified manner as a neural network. Data structures may include neural networks. And the data structure including the neural network may be stored in a computer-readable medium. Data structures including neural networks also include data preprocessed for processing by a neural network, data input to the neural network, weights of the neural network, hyperparameters of the neural network, data acquired from the neural network, activation functions associated with each node or layer of the neural network, neural network It may include a loss function for learning. A data structure containing a neural network may include any of the components disclosed above. In other words, the data structure including the neural network includes preprocessed data for processing by the neural network, data input to the neural network, weights of the neural network, hyperparameters of the neural network, data acquired from the neural network, activation functions associated with each node or layer of the neural network, neural network It may be configured to include all or any combination of the loss function for learning. In addition to the configurations described above, a data structure containing a neural network may include any other information that determines the characteristics of the neural network. Additionally, the data structure may include all types of data used or generated in the computational process of a neural network and is not limited to the above. Computer-readable media may include computer-readable recording media and/or computer-readable transmission media. A neural network can generally consist of a set of interconnected computational units, which can be referred to as nodes. These nodes may also be referred to as neurons. A neural network consists of at least one node.

The data structure may include data input to the neural network. A data structure containing data input to a neural network may be stored in a computer-readable medium. Data input to the neural network may include learning data input during the neural network learning process and/or input data input to the neural network on which training has been completed. Data input to the neural network may include data that has undergone pre-processing and/or data subject to pre-processing. Preprocessing may include a data processing process to input data into a neural network. Therefore, the data structure may include data subject to preprocessing and data generated by preprocessing. The above-described data structure is only an example and the present disclosure is not limited thereto.

The data structure may include the weights of the neural network. (In this specification, weights and parameters may be used with the same meaning.) And the data structure including the weights of the neural network may be stored in a computer-readable medium. A neural network may include multiple weights. Weights may be variable and may be varied by the user or algorithm in order for the neural network to perform the desired function. For example, when one or more input nodes are connected to one output node by respective links, the output node is set to the values input to the input nodes connected to the output node and the links corresponding to each input node. Based on the weight, the data value output from the output node can be determined. The above-described data structure is only an example and the present disclosure is not limited thereto.

As an example and not a limitation, the weights may include weights that are changed during the neural network learning process and/or weights for which neural network learning has been completed. Weights that change during the neural network learning process may include weights that change at the start of the learning cycle and/or weights that change during the learning cycle. Weights for which neural network training has been completed may include weights for which a learning cycle has been completed. Therefore, the data structure including the weights of the neural network may include weights that are changed during the neural network learning process and/or the data structure including the weights for which neural network learning has been completed. Therefore, the above-mentioned weights and/or combinations of each weight are included in the data structure including the weights of the neural network. The above-described data structure is only an example and the present disclosure is not limited thereto.

The data structure including the weights of the neural network may be stored in a computer-readable storage medium (e.g., memory, hard disk) after going through a serialization process. Serialization can be the process of converting a data structure into a form that can be stored on the same or a different computing device and later reorganized and used. Computing devices can transmit and receive data over a network by serializing data structures. Data structures containing the weights of a serialized neural network can be reconstructed on the same computing device or on a different computing device through deserialization. The data structure including the weights of the neural network is not limited to serialization. Furthermore, the data structure including the weights of the neural network is a data structure to increase computational efficiency while minimizing the use of computing device resources (e.g., in non-linear data structures, B-Tree, Trie, m-way search tree, AVL tree, Red-Black Tree) may be included. The foregoing is merely an example and the present disclosure is not limited thereto.

The data structure may include hyper-parameters of a neural network. And the data structure including the hyperparameters of the neural network can be stored in a computer-readable medium. A hyperparameter may be a variable that can be changed by the user. Hyperparameters include, for example, learning rate, cost function, number of learning cycle repetitions, weight initialization (e.g., setting the range of weight values subject to weight initialization), Hidden Unit. It may include a number (e.g., number of hidden layers, number of nodes in hidden layers). The above-described data structure is only an example and the present disclosure is not limited thereto.

Figure 8 is a brief, general schematic diagram of an example computing environment in which embodiments of the present disclosure may be implemented.

Although the present disclosure has generally been described above as being capable of being implemented by a computing device, those skilled in the art will understand that the present disclosure can be implemented in combination with computer-executable instructions and/or other program modules that can be executed on one or more computers and/or in hardware and software. It will be well known that it can be implemented as a combination.

Typically, program modules include routines, programs, components, data structures, etc. that perform specific tasks or implement specific abstract data types. Additionally, those skilled in the art will understand that the methods of the present disclosure are applicable to single-processor or multiprocessor computer systems, minicomputers, mainframe computers, as well as personal computers, handheld computing devices, microprocessor-based or programmable consumer electronics, etc. It will be appreciated that each of these may be implemented in other computer system configurations, including those capable of operating in conjunction with one or more associated devices.

The described embodiments of the disclosure can also be practiced in distributed computing environments where certain tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote memory storage devices.

Computers typically include a variety of computer-readable media. Computer-readable media can be any medium that can be accessed by a computer, and such computer-readable media includes volatile and non-volatile media, transitory and non-transitory media, removable and non-transitory media. Includes removable media. By way of example, and not limitation, computer-readable media may include computer-readable storage media and computer-readable transmission media. Computer-readable storage media refers to volatile and non-volatile media, transient and non-transitory media, removable and non-removable, implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Includes media. Computer readable storage media may include RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital video disk (DVD) or other optical disk storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage. This includes, but is not limited to, a device, or any other medium that can be accessed by a computer and used to store desired information.

A computer-readable transmission medium typically implements computer-readable instructions, data structures, program modules, or other data on a modulated data signal, such as a carrier wave or other transport mechanism. Includes all information delivery media. The term modulated data signal refers to a signal in which one or more of the characteristics of the signal have been set or changed to encode information within the signal. By way of example, and not limitation, computer-readable transmission media includes wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, RF, infrared, and other wireless media. Combinations of any of the above are also intended to be included within the scope of computer-readable transmission media.

An example environment 1100 is shown that implements various aspects of the present disclosure, including a computer 1102, which includes a processing unit 1104, a system memory 1106, and a system bus 1108. do. System bus 1108 couples system components, including but not limited to system memory 1106, to processing unit 1104. Processing unit 1104 may be any of a variety of commercially available processors. Dual processors and other multiprocessor architectures may also be used as processing unit 1104.

System bus 1108 may be any of several types of bus structures that may further be interconnected to a memory bus, peripheral bus, and local bus using any of a variety of commercial bus architectures. System memory 1106 includes read only memory (ROM) 1110 and random access memory (RAM) 1112. The basic input/output system (BIOS) is stored in non-volatile memory 1110, such as ROM, EPROM, and EEPROM, and is a basic input/output system that helps transfer information between components within the computer 1102, such as during startup. Contains routines. RAM 1112 may also include high-speed RAM, such as static RAM, for caching data.

Computer 1102 may also include an internal hard disk drive (HDD) 1114 (e.g., EIDE, SATA)—the internal hard disk drive 1114 may also be configured for external use within a suitable chassis (not shown). Yes - a magnetic floppy disk drive (FDD) 1116 (e.g., for reading from or writing to a removable diskette 1118), and an optical disk drive 1120 (e.g., a CD-ROM for reading the disk 1122 or reading from or writing to other high-capacity optical media such as DVDs). Hard disk drive 1114, magnetic disk drive 1116, and optical disk drive 1120 are connected to system bus 1108 by hard disk drive interface 1124, magnetic disk drive interface 1126, and optical drive interface 1128, respectively. ) can be connected to. The interface 1124 for implementing an external drive includes at least one or both of Universal Serial Bus (USB) and IEEE 1394 interface technologies.

These drives and their associated computer-readable media provide non-volatile storage of data, data structures, computer-executable instructions, and the like. For computer 1102, drive and media correspond to storing any data in a suitable digital format. Although the description of computer-readable media above refers to removable optical media such as HDDs, removable magnetic disks, and CDs or DVDs, those skilled in the art will also recognize removable optical media such as zip drives, magnetic cassettes, flash memory cards, cartridges, etc. It will be appreciated that other types of computer-readable media, such as the like, may also be used in the example operating environment and that any such media may contain computer-executable instructions for performing the methods of the present disclosure.

A number of program modules may be stored in drives and RAM 1112, including an operating system 1130, one or more application programs 1132, other program modules 1134, and program data 1136. All or portions of the operating system, applications, modules and/or data may also be cached in RAM 1112. It will be appreciated that the present disclosure may be implemented on various commercially available operating systems or combinations of operating systems.

A user may enter commands and information into computer 1102 through one or more wired/wireless input devices, such as a keyboard 1138 and a pointing device such as mouse 1140. Other input devices (not shown) may include microphones, IR remote controls, joysticks, game pads, stylus pens, touch screens, etc. These and other input devices are connected to the processing unit 1104 through an input device interface 1142, which is often connected to the system bus 1108, but may also include a parallel port, an IEEE 1394 serial port, a game port, a USB port, an IR interface, It can be connected by other interfaces, etc.

A monitor 1144 or other type of display device is also connected to system bus 1108 through an interface, such as a video adapter 1146. In addition to monitor 1144, computers typically include other peripheral output devices (not shown) such as speakers, printers, etc.

Computer 1102 may operate in a networked environment using logical connections to one or more remote computers, such as remote computer(s) 1148, via wired and/or wireless communications. Remote computer(s) 1148 may be a workstation, computing device computer, router, personal computer, portable computer, microprocessor-based entertainment device, peer device, or other conventional network node, and is generally connected to computer 1102. For simplicity, only memory storage device 1150 is shown, although it includes many or all of the components described. The logical connections depicted include wired/wireless connections to a local area network (LAN) 1152 and/or a larger network, such as a wide area network (WAN) 1154. These LAN and WAN networking environments are common in offices and companies and facilitate enterprise-wide computer networks, such as intranets, all of which can be connected to a worldwide computer network, such as the Internet.

When used in a LAN networking environment, computer 1102 is connected to local network 1152 through wired and/or wireless communication network interfaces or adapters 1156. Adapter 1156 may facilitate wired or wireless communication to LAN 1152, which also includes a wireless access point installed thereon for communicating with wireless adapter 1156. When used in a WAN networking environment, the computer 1102 may include a modem 1158 or be connected to a communicating computing device on the WAN 1154 or to establish communications over the WAN 1154, such as via the Internet. Have other means. Modem 1158, which may be internal or external and a wired or wireless device, is coupled to system bus 1108 via serial port interface 1142. In a networked environment, program modules described for computer 1102, or portions thereof, may be stored in remote memory/storage device 1150. It will be appreciated that the network connections shown are exemplary and that other means of establishing a communications link between computers may be used.

Computer 1102 may be associated with any wireless device or object deployed and operating in wireless communications, such as a printer, scanner, desktop and/or portable computer, portable data assistant (PDA), communications satellite, wirelessly detectable tag. Performs actions to communicate with any device or location and telephone. This includes at least Wi-Fi and Bluetooth wireless technologies. Accordingly, communication may be a predefined structure as in a conventional network or may simply be ad hoc communication between at least two devices.

Wi-Fi (Wireless Fidelity) allows connection to the Internet, etc. without wires. Wi-Fi is a wireless technology, like cell phones, that allows these devices, such as computers, to send and receive data indoors and outdoors, anywhere within the coverage area of a base station. Wi-Fi networks use wireless technology called IEEE 802.11 (a, b, g, etc.) to provide secure, reliable, and high-speed wireless connections. Wi-Fi can be used to connect computers to each other, the Internet, and wired networks (using IEEE 802.3 or Ethernet). Wi-Fi networks can operate in the unlicensed 2.4 and 5 GHz wireless bands, for example, at data rates of 11 Mbps (802.11a) or 54 Mbps (802.11b), or in products that include both bands (dual band). .

Those skilled in the art will understand that information and signals may be represented using any of a variety of different technologies and techniques. For example, data, instructions, commands, information, signals, bits, symbols and chips that may be referenced in the above description include voltages, currents, electromagnetic waves, magnetic fields or particles, optical fields. It can be expressed by particles or particles, or any combination thereof.

Those skilled in the art will understand that the various illustrative logical blocks, modules, processors, means, circuits and algorithm steps described in connection with the embodiments disclosed herein may be used in electronic hardware, (for convenience) It will be understood that it may be implemented by various forms of program or design code (referred to herein as software) or a combination of both. To clearly illustrate this interoperability of hardware and software, various illustrative components, blocks, modules, circuits and steps have been described above generally with respect to their functionality. Whether this functionality is implemented as hardware or software depends on the specific application and design constraints imposed on the overall system. A person skilled in the art of this disclosure may implement the described functionality in various ways for each specific application, but such implementation decisions should not be construed as departing from the scope of this disclosure.

The various embodiments presented herein may be implemented as a method, apparatus, or article of manufacture using standard programming and/or engineering techniques. The term article of manufacture includes a computer program, carrier, or media accessible from any computer-readable storage device. For example, computer-readable storage media include magnetic storage devices (e.g., hard disks, floppy disks, magnetic strips, etc.), optical disks (e.g., CDs, DVDs, etc.), smart cards, and flash. Includes, but is not limited to, memory devices (e.g., EEPROM, cards, sticks, key drives, etc.). Additionally, various storage media presented herein include one or more devices and/or other machine-readable media for storing information.

It is to be understood that the specific order or hierarchy of steps in the processes presented is an example of illustrative approaches. It is to be understood that the specific order or hierarchy of steps in processes may be rearranged within the scope of the present disclosure, based on design priorities. The appended method claims present elements of the various steps in a sample order but are not meant to be limited to the particular order or hierarchy presented.

The description of the presented embodiments is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be applied to other embodiments without departing from the scope of the disclosure. Thus, the present disclosure is not limited to the embodiments presented herein but is to be interpreted in the broadest scope consistent with the principles and novel features presented herein.

Claims (13)

1. A method for digital human modeling performed by one or more processors of a computing device, comprising:
Transforming a digital human provided by a real-time 3D engine using a neural network model;
Comparing information extracted from the modified digital human and information about the modeling object; and
determining a reward for the neural network model based on the comparison result;
Including,
The information about the modeling object includes at least one of a 2D image of the front or a 2D image of the side of the modeling object,
The information extracted from the modified digital human includes at least one of a 2D image extracted in a frontal direction or a 2D image extracted in a side direction of the digital human,
Comparing the information extracted from the modified digital human and the information about the modeling object may include comparing a 2D image of the front of the modeling object with a 2D image extracted in the front direction of the digital human, or the modeling Comprising at least one step of comparing a 2D image of the side of the object and a 2D image extracted in the side direction of the digital human,
The information about the modeling object includes characteristic information about the appearance of the modeling object,
The information extracted from the modified digital human includes characteristic information about the appearance of the modified digital human,
Comparing the information extracted from the modified digital human and the information about the modeling object further includes comparing feature information about the appearance of the modeling object with feature information about the appearance of the modified digital human. do,
The compensation for the neural network model is,
based on an ensemble of a first compensation based on a comparison between frontal images, a second compensation based on a comparison between side images, and a third compensation based on a comparison between features for appearance,
method.
According to claim 1,
The information about the modeling object includes a two-dimensional (2D) image of the modeling object,
The information extracted from the modified digital human includes a 2D image extracted from the shape of the 3D digital human,
The comparing step includes comparing a 2D image of the modeling object and a 2D image extracted from the shape of the 3D digital human,
method.
According to claim 2,
The 2D image extracted from the shape of the 3D digital human is,
Containing a 2D image obtained by rendering the 3D digital human,
method.
delete delete According to claim 1,
The characteristic information about the appearance includes eye width, eye width, eye height, face shape, nose height, nose width, nose width, skin color, skin color saturation, skin color brightness, size ratio and arrangement of eyes, nose, and mouth, and cheekbone protrusion. Containing information about at least one of the degree, hair color, hair color saturation, or hair color brightness,
method.
According to claim 2,
The step of comparing feature information about the appearance of the modeling object with feature information about the appearance of the modified digital human,
Comprising the step of performing comparison after adjusting the size of the 2D image of the modeling object or the size of the 2D image extracted from the shape of the 3D digital human,
method.
delete According to claim 1,
The neural network model is,
Learned through reinforcement learning based on a state containing information about the digital human, an action to transform the digital human, and a reward for the action,
method.
According to claim 1,
The comparing step includes calculating a degree of similarity between information extracted from the modified digital human and information about the modeling object,
Determining the compensation includes determining the compensation based on the calculated similarity,
method.
According to claim 1,
The neural network model is,
Calculate similarity between information extracted from the modified digital human and information about the modeling object,
If the calculated similarity is higher than a predetermined level, collecting information about the reinforcement learning path is terminated.
method.

A computer program stored in a computer-readable storage medium, wherein when executed by one or more processors, the computer program causes the one or more processors to perform operations for digital human modeling, the operations comprising:
Actions that transform digital humans provided by a real-time 3D engine utilizing neural network models;
An operation of comparing information extracted from a modified digital human and information about a modeling object; and
determining compensation for the neural network model based on the comparison result;
Including,
The information about the modeling object includes at least one of a 2D image of the front or a 2D image of the side of the modeling object,
The information extracted from the modified digital human includes at least one of a 2D image extracted in a frontal direction or a 2D image extracted in a side direction of the digital human,
The operation of comparing the information extracted from the modified digital human and the information about the modeling object may include comparing a 2D image of the front of the modeling object with a 2D image extracted in the front direction of the digital human, or the modeling Comprising at least one operation of comparing a 2D image of the side of the object and a 2D image extracted in the side direction of the digital human,
The information about the modeling object includes characteristic information about the appearance of the modeling object,
The information extracted from the modified digital human includes characteristic information about the appearance of the modified digital human,
The operation of comparing the information extracted from the modified digital human and the information about the modeling object further includes comparing feature information about the appearance of the modeling object with feature information about the appearance of the modified digital human. do,
The compensation for the neural network model is,
based on an ensemble of a first compensation based on a comparison between frontal images, a second compensation based on a comparison between side images, and a third compensation based on a comparison between features for appearance,
A computer program stored on a computer-readable storage medium.

As a computing device,
at least one processor; and
Memory
Including,
The at least one processor,
Transform digital humans provided by a real-time 3D engine using neural network models;
Compare information extracted from the modified digital human and information about the modeling target; and
configured to determine compensation for the neural network model based on the comparison result,
The information about the modeling object includes at least one of a 2D image of the front or a 2D image of the side of the modeling object,
The information extracted from the modified digital human includes at least one of a 2D image extracted in a frontal direction or a 2D image extracted in a side direction of the digital human,
The process of comparing the information extracted from the modified digital human with the information about the modeling object is a process of comparing a 2D image of the front of the modeling object with a 2D image extracted in the front direction of the digital human, or the modeling Comprising at least one comparison process of comparing a 2D image for the side of the object and a 2D image extracted in the side direction of the digital human,
The information about the modeling object includes characteristic information about the appearance of the modeling object,
The information extracted from the modified digital human includes characteristic information about the appearance of the modified digital human,
The process of comparing the information extracted from the modified digital human with the information about the modeling object further includes comparing feature information about the appearance of the modeling object with feature information about the appearance of the modified digital human. do,
The compensation for the neural network model is,
based on an ensemble of a first compensation based on a comparison between frontal images, a second compensation based on a comparison between side images, and a third compensation based on a comparison between features for appearance,
Computing device.