KR102390615B1 - Method and system for generating and sharing realistic 3d character model - Google Patents

Abstract

A system for generating and sharing a realistic 3D character model comprises: a 3D scanner configured to generate a realistic 3D character model from a subject of a specific person; a production terminal configured to produce a virtual character by editing or modifying the character model and produce 3D content using the virtual character; and a server configured to share at least one of the virtual character or the 3D content with a user terminal.

Description

A system and method for creating and sharing a three-dimensional photorealistic character model

It relates to a system and method for creating and sharing a 3D live-action character model, and more specifically, by using 3D live-action character modeling to create a 3D live-action character model that realistically implements the subject of a specific person, based on this It relates to a system and method for producing and sharing 3D content.

Most of the conventional general photobooks support a two-dimensional publication in the form of a booklet or a digitalized digital photobook as an application. Meanwhile, with the spread of smartphones, digital photobooks of celebrities such as actors and models, as well as content of creators or influencers shared through social networking services (SNS), are increasing in popularity.

In general, an influencer is a person who has a great influence on society or the public, and in particular, refers to a person who has a fandom or a large number of followers while working on social media such as YouTube, Instagram, and Facebook. Influencers also generate financial profits by creating, sharing, and selling various contents such as videos, based on their popularity or popular influence on the SNS platform.

However, the content shared based on the popularity of the influencer may be limited to images or videos directly produced by the influencer. In addition, although influencers are not related to themselves on SNS platforms, they also sell products produced for commercial purposes in the form of online shopping simply to generate monetary profit. On the other hand, data related to celebrities can be easily searched for by using a photo book in the form of a booklet or an Internet search. However, since the amount of information shared about the influencer is relatively small, it is inconvenient for users or followers to find information about the influencer they want. In addition, in the case of a conventional two-dimensional publication or digitized digital photo book, there is an advantage that the production process and production period from shooting a specific person to editing and sharing is short, but the use of the produced content is limited. there is.

The present disclosure is to solve the problems of the prior art described above, and through 3D live-action character scanning and modeling, a subject of a specific person, such as an influencer, is converted into a 3D live-action character model and produced, A system and method for creating and sharing a 3D live-action character model capable of producing and sharing 3D content using a 3D character model are provided.

According to an embodiment of the present disclosure, in a system for generating and sharing a three-dimensional live-action character model, a 3D scanner for generating a three-dimensional live-action character model from a subject of a specific person, a virtual character is produced through editing or modification of the character model and a production terminal configured to produce 3D content using a virtual character and a server configured to share at least one of a virtual character or 3D content with a user terminal.

According to an embodiment, the server includes an artificial intelligence-based model that is trained to generate motion data based on a three-dimensional live-action character model, or is trained to extract one or more other similar virtual characters based on characteristic information of the virtual character. It includes a data learning module.

According to an embodiment, the characteristic information includes at least one of keyword information or image information about the appearance or behavior pattern of the virtual character.

According to an embodiment, the server includes a digital twin generator configured to learn information about a behavioral pattern of a specific person based on a three-dimensional live-action character model, and predict the behavior of a virtual character based on the learned information.

According to an embodiment, the server includes a database configured to store and modify a virtual character or 3D content produced through a production terminal.

According to an embodiment, in the system for generating and sharing a three-dimensional live-action character, it further includes an online store configured to allow a user to view and order a virtual character or three-dimensional content through a user terminal.

According to an embodiment, the store is configured to sell goods or services corresponding to the hairstyle or clothing worn by the virtual character through the user terminal when the user reads the virtual character or 3D content.

According to an embodiment, in the system for generating and sharing a three-dimensional real-life character, the system further includes a 3D printer configured to generate a three-dimensional output of the virtual character.

According to another embodiment of the present disclosure, in a method for generating and sharing a three-dimensional live-action character model, by a 3D scanner, generating a three-dimensional live-action character model from a subject of a specific person, by a production terminal, a character model producing a virtual character or 3D content through editing or modification of, by a database, storing the virtual character or 3D content produced through a production terminal, and by a server, at least one of the virtual character or 3D content and sharing one with the user terminal.

According to an embodiment of the present disclosure, by creating and distributing content by creating a three-dimensional live-action character model of a celebrity such as a celebrity or an influencer, users can use the three-dimensional live-action model in a three-dimensional virtual environment or augmented reality environment. This can increase the sense of presence you feel about the celebrity.

According to an embodiment of the present disclosure, content produced based on a three-dimensional real-life character model generated through three-dimensional real-life modeling of a specific person is provided in various fields (eg, entertainment, photo book, game, digital twin, etc.) may be available in For example, a virtual concert in a digital space may be planned using a three-dimensional live-action character model generated based on a specific celebrity.

According to an embodiment of the present disclosure, by sharing content (eg, a photobook, etc.) produced based on a 3D live-action character model generated through 3-D live-action modeling of a specific person, it is executed on a portable mobile device. An environment that can be easily used in any place can be provided by using a separate program such as an application that can be used.

The effects of the present disclosure are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description of the claims.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Embodiments of the present disclosure will be described with reference to the accompanying drawings described below, in which like reference numerals denote like elements, but are not limited thereto.
1 is a schematic diagram of a system for generating and sharing a three-dimensional live-action character model according to an embodiment of the present disclosure.
2 is a diagram illustrating a process of outputting a 3D output of a virtual character through a 3D printer, based on a sharing system of a 3D live-action character model according to an embodiment of the present disclosure.
3 is a block diagram illustrating internal configurations of a user terminal and a server according to an embodiment of the present disclosure.
4 is a block diagram illustrating a configuration of a server according to an embodiment of the present disclosure.
5 is a diagram illustrating a process in which a virtual character produced through 3D scanning and stored in a server is shared with a user terminal through a network according to an embodiment of the present disclosure.
6 is a diagram illustrating a configuration of a data learning module using an artificial neural network model trained to extract a virtual character having similar characteristics based on model information according to an embodiment of the present disclosure.
7 is a diagram illustrating a configuration of a data learning module using an artificial neural network model trained to generate motion data or behavior patterns of a virtual character based on an image or image of a virtual character according to an embodiment of the present disclosure.
8 is a diagram illustrating an example of a photobook application of a virtual character according to an embodiment of the present disclosure.
9 is a diagram illustrating an example of manipulation when viewing a pictorial of a virtual character according to an embodiment of the present disclosure.
10 is a diagram illustrating another example of manipulation when viewing a pictorial of a virtual character according to an embodiment of the present disclosure.
11 is a diagram illustrating an example connected to a store when viewing a pictorial of a virtual character according to an embodiment of the present disclosure.
12 is a flowchart of a method for generating and sharing a three-dimensional live-action character model according to an embodiment of the present disclosure.

Hereinafter, specific contents for carrying out the present disclosure will be described in detail with reference to the accompanying drawings. However, in the following description, if there is a risk of unnecessarily obscuring the gist of the present disclosure, detailed descriptions of well-known functions or configurations will be omitted.

In the accompanying drawings, the same or corresponding components are assigned the same reference numerals. In addition, in the description of the embodiments below, overlapping description of the same or corresponding components may be omitted. However, even if descriptions regarding components are omitted, it is not intended that such components are not included in any embodiment.

Advantages and features of the disclosed embodiments, and methods of achieving them, will become apparent with reference to the embodiments described below in conjunction with the accompanying drawings. However, the present disclosure is not limited to the embodiments disclosed below, but may be implemented in various different forms, and only the present embodiments allow the present disclosure to be complete, and those of ordinary skill in the art to which the present disclosure pertains. It is only provided to fully inform the person of the scope of the invention.

Terms used in the present disclosure will be briefly described, and the disclosed embodiments will be described in detail.

The terms used in the present disclosure are selected as currently widely used general terms as possible while considering the functions in the present disclosure, but these may vary depending on the intention or precedent of a person skilled in the art, the emergence of new technology, and the like. In addition, in a specific case, there is a term arbitrarily selected by the applicant, and in this case, the meaning will be described in detail in the description of the corresponding invention. Therefore, the terms used in the present disclosure should be defined based on the meaning of the term and the contents of the present disclosure, rather than the simple name of the term.

Expressions in the singular in this disclosure include plural expressions unless the context clearly dictates the singular. Also, the plural expression includes the singular expression unless the context clearly dictates the plural.

In the entirety of the present disclosure, when a part 'includes' a certain component, it means that other components may be further included, rather than excluding other components, unless otherwise stated.

In addition, the term 'module' or 'unit' used in the specification means a software or hardware component, and 'module' or 'unit' performs certain roles. However, 'module' or 'unit' is not meant to be limited to software or hardware. A 'module' or 'unit' may be configured to reside on an addressable storage medium or configured to play one or more processors. Thus, as an example, 'module' or 'unit' refers to components such as software components, object-oriented software components, class components and task components, processes, functions, and properties. , procedures, subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, database, data structures, tables, arrays or at least one of variables. Components and 'modules' or 'units' are the functions provided therein that are combined into a smaller number of components and 'modules' or 'units' or additional components and 'modules' or 'units' can be further separated.

According to an embodiment of the present disclosure, a 'module' or a 'unit' may be implemented with a processor and a memory. 'Processor' should be construed broadly to include general purpose processors, central processing units (CPUs), microprocessors, digital signal processors (DSPs), controllers, microcontrollers, state machines, and the like. In some contexts, a 'processor' may refer to an application specific semiconductor (ASIC), a programmable logic device (PLD), a field programmable gate array (FPGA), or the like. 'Processor' refers to a combination of processing devices, such as, for example, a combination of a DSP and a microprocessor, a combination of a plurality of microprocessors, a combination of one or more microprocessors in combination with a DSP core, or any other such configuration. You may. Also, 'memory' should be construed broadly to include any electronic component capable of storing electronic information. 'Memory' means random access memory (RAM), read-only memory (ROM), non-volatile random access memory (NVRAM), programmable read-only memory (PROM), erase-programmable read only memory (EPROM); It may also refer to various types of processor-readable media, such as electrically erasable PROM (EEPROM), flash memory, magnetic or optical data storage, registers, and the like. A memory is said to be in electronic communication with the processor if the processor is capable of reading information from and/or writing information to the memory. A memory integrated in the processor is in electronic communication with the processor.

Reference to "A and/or B" in this specification means A, or B, or A and B.

In the present disclosure, 'three-dimensional data' is a point, line (or edge), plane, curved surface necessary to three-dimensionally simulate the shape of a specific person or an article related thereto, such as a three-dimensional live-action character model and a virtual character. It may refer to data including equations, vectors, and the like defining the like.

In the present disclosure, 'model information (or feature information) may include not only a three-dimensional live-action character model of a specific person (or a virtual character having characteristics similar to a specific person), but also keyword information and image information associated with the model. there is. The keyword information may include one or more keywords indicating characteristics of the 3D real-life character model, such as the virtual character's personality, hobbies, occupations, preferences, and personal information. Also, the image information may include visual characteristics such as hairstyle, body type, and fashion information of the virtual character.

In the present disclosure, a 'digital twin' may refer to a twin model of a specific person who has similar or identical characteristics to a specific person existing in the real world and is active in a virtual digital environment. In addition, the digital twin may refer to a technology capable of predicting a result in advance by simulating a situation that may occur in reality in relation to a specific person in a virtual digital environment.

In the present disclosure, a 'virtual character' may refer to a virtual person in the virtual world expressed through a 3D live-action character model generated by 3D scanning a subject such as a specific person existing in the real world. Such a virtual character may be expressed using 3D data or model information generated based on a specific person.

1 is a schematic diagram of a system 100 for generating and sharing a three-dimensional photorealistic character model according to an embodiment of the present disclosure. As shown, the 3D live-action character model creation and sharing system 100 may include a 3D scanner 160 , a production terminal 162 , a server 130 , and a network 120 . The system 100 may further include user terminals 110_1 , 110_2 , and 110_3 connected to the server 130 through the network 120 . The 3D scanner 160 may generate 3D data from a subject of a specific person. As an embodiment, the 3D scanner 160 may generate 3D data corresponding to the person by photographing the subject of a specific person in various directions using a plurality of image sensors. That is, the 3D scanner 610 may generate a 3D live-action character model including 3D data corresponding to a specific person.

The production terminal 162 may receive the character model generated through the 3D scanner 160 , and may create a virtual character through editing or correction of the character model. Also, the production terminal 162 may be configured to produce 3D content based on a virtual character. For example, three-dimensional content is a three-dimensional digital form that can be used in entertainment fields (eg, games, dramas, movies, music videos, photo books, virtual concerts, etc.) and industrial fields (eg, digital twins, etc.). Content may be included.

The server 130 includes a database 132 , and the database 132 may be configured to store or modify virtual characters or 3D content produced through the production terminal 162 . The server 130 may share the virtual character or 3D content stored in the database 132 with the user terminal 110 through the network 120 .

The server 130 is one or more server devices and/or databases that can store, provide and execute programs (eg, downloadable applications) and data related to the creation and sharing service of the three-dimensional live-action character model, or a cloud It may include one or more distributed computing devices and/or distributed databases based on computing services. The creation and sharing service of the three-dimensional live-action character model provided by the server 130 may be provided to the user through an application or a web browser application installed in each of the plurality of user terminals (110_1, 110_2, 110_3). As an example, the system 100 for generating and sharing a three-dimensional live-action character model provides a list of virtual characters or three-dimensional content stored in the server 130 to the user through a user terminal, or a list of virtual characters or three-dimensional It is possible to provide a service for selecting and viewing content. For example, the user terminals 110_1 , 110_2 , and 110_3 may view a 3D photo book created based on a virtual character stored in the server 130 through the network 120 .

The plurality of user terminals 110_1 , 110_2 , and 110_3 may communicate with the server 130 through the network 120 . The network 120 may be configured to enable communication between the plurality of user terminals 110_1 , 110_2 , and 110_3 and the server 130 . Network 120 according to the installation environment, for example, Ethernet (Ethernet), wired home network (Power Line Communication), telephone line communication device and wired networks such as RS-serial communication, mobile communication network, WLAN (Wireless LAN), It may consist of a wireless network such as Wi-Fi, Bluetooth and ZigBee, or a combination thereof. The communication method is not limited, and the user terminals 110_1, 110_2, 110_3 as well as a communication method using a communication network (eg, a mobile communication network, a wired Internet, a wireless Internet, a broadcasting network, a satellite network, etc.) that the network 120 may include. ) may also include short-range wireless communication between

In FIG. 1 , the user terminals 110_1, 110_2, and 110_3 include the mobile phone terminal 110_1, the tablet terminal 110_2, and the PC terminal 110_3 as examples, but the present invention is not limited thereto. may be any computing device capable of wired and/or wireless communication and in which an application or a web browser application may be installed and executed. For example, the user terminals 110_1, 110_2, and 110_3 are a smartphone, a mobile phone, a navigation system, a computer, a notebook computer, a digital broadcasting terminal, a PDA (Personal Digital Assistants), a PMP (Portable Multimedia Player), a tablet PC, a game console ( game console), a wearable device, an Internet of things (IoT) device, a virtual reality (VR) device, an augmented reality (AR) device, and the like. Also, in FIG. 1, three user terminals 110_1, 110_2, 110_3 are illustrated as communicating with the server 130 through the network 120, but the present invention is not limited thereto, and a different number of user terminals 110_1, 110_2, 110_3 may be configured to communicate with the server 130 via the network 120 .

According to an embodiment, the server 130 may provide a 3D photobook through an application operating in the user terminals 110_1 , 110_2 , 110_3 , a web browser application, or the like. The 3D photobook may provide a virtual character selected based on keyword information and/or image information input by the user. In one example, the user may use keyword information (eg, the model's personality, hobbies, occupation, preferences, personal information, etc.) and/or image information (eg, the model's hairstyle information) through the setting of the 3D photobook. , fashion information, body type, etc.) may be input, and a virtual character may be searched and browsed based on the input characteristic information. Additionally or alternatively, the server 130 may be configured to extract one or more other virtual characters having similar characteristics based on the characteristic information set by the user.

2 is a diagram illustrating a method 200 of outputting a virtual character as a three-dimensional output 152 through a 3D printer based on a sharing system of a three-dimensional live-action character model according to an embodiment of the present disclosure. A method 200 for outputting a virtual character as a three-dimensional output 152 using a 3D printer based on a sharing system of a three-dimensional live-action character model includes a server 130, an online store 140, and a 3D printer 150. and a series of steps executed by the network 120 . Also, the method 200 may further include steps executed by the user terminals 110_1 , 110_2 , and 110_3 connected to the server 130 through the network 120 .

In an embodiment, the online store 140 may be configured to provide a service for viewing and ordering virtual characters or 3D content to the user terminals 110_1 , 110_2 , and 110_3 through the network 120 . In addition, the online store 140, when the user reads the virtual character or 3D content, through the user terminals 110_1, 110_2, 110_3, the virtual character's hairstyle or a product corresponding to the clothing worn by the virtual character or It may be configured to be linked with another online store that provides at least one of the services.

As an embodiment, the user may request a 3D output of the virtual character being viewed through the user terminals 110_1, 110_2, and 110_3. For example, the user may select a preferred virtual character from among the virtual characters provided by the online store 140 through the user terminals 110_1, 110_2, and 110_3, and request a three-dimensional output 152 of the selected virtual character. there is. The server 130 may extract 3D data of the virtual character corresponding to the user's request from the database 132 and transmit it to the 3D printer 150 connected to the online store 140 . The 3D printer 150 may output a 3D output 152 based on 3D data received from the database 132 .

3 is a block diagram illustrating internal configurations of the user terminal 110 and the server 130 according to an embodiment of the present disclosure. As shown, the user terminal 110 may include a memory 312 , a processor 314 , a communication unit 316 , and an input/output interface 318 . Similarly, the server 130 may include a memory 322 , a processor 324 , a communication unit 326 , and an input/output interface 328 . As shown in FIG. 3 , the user terminal 110 and the server 130 may be configured to communicate information and/or data through the network 120 using respective communication units 316 and 326 . . In addition, the input/output device 320 may be configured to input information and/or data to the user terminal 110 or output information and/or data generated from the user terminal 110 through the input/output interface 318 .

The memories 312 and 322 may include any non-transitory computer-readable recording medium. According to an embodiment, the memories 312 and 322 are non-volatile mass storage devices such as random access memory (RAM), read only memory (ROM), disk drive, solid state drive (SSD), flash memory, and the like. (permanent mass storage device) may be included. As another example, a non-volatile mass storage device such as a ROM, an SSD, a flash memory, a disk drive, etc. may be included in the user terminal 110 and the server 130 as a separate permanent storage device distinct from the memory. In addition, the memories 312 and 322 include an operating system and at least one program (eg, a code for an application that provides a 3D live-action character model creation and sharing service installed and driven in the user terminal 110 ) can be saved.

These software components may be loaded from a computer-readable recording medium separate from the memories 312 and 322 . The separate computer-readable recording medium may include a recording medium directly connectable to the user terminal 110 and the server 130, for example, a floppy drive, a disk, a tape, a DVD/CD-ROM drive. , and a computer-readable recording medium such as a memory card. As another example, the software components may be loaded into the memories 312 and 322 through the communication units 316 and 326 instead of a computer-readable recording medium. For example, at least one program is a computer program (eg, a sharing system of a three-dimensional live-action character model) that is installed by the files that the distribution system provides through the network 120 with the installation files of the developers or applications It may be loaded into the memories 312 and 322 based on a web browser or an application that provides a virtual character list, a 3D content list, etc.

The processors 314 and 324 may be configured to process instructions of a computer program by performing basic arithmetic, logic, and input/output operations. Instructions may be provided to the processor 314 , 324 by the memory 312 , 322 or the communication unit 316 , 326 . For example, the processors 314 and 324 may be configured to execute received instructions according to program code stored in a recording device, such as the memories 312 and 322 .

The communication units 316 and 326 may provide a configuration or function for the user terminal 110 and the server to communicate with each other through the network 120 , and the user terminal 110 and/or the server 130 may have different user terminals. 110 or may provide a configuration or function for communicating with another system (eg, a separate cloud system, etc.). For example, a request or data generated by the processor 314 of the user terminal 110 according to a program code stored in a recording device such as the memory 312 (eg, a virtual character generated based on a three-dimensional live-action character model) list, a request for a 3D content list, etc.) may be transmitted to the server 130 through the network 120 under the control of the communication units 316 and 326 . Conversely, a control signal or command provided under the control of the processor 324 of the server 130 is transmitted through the communication unit 326 and the network 120 to the user terminal 110 through the communication unit 316 of the user terminal 110 . ) can be received. For example, the user terminal 110 may receive a virtual character list or a 3D content list from the server 130 through the communication unit 316 .

The input/output interface 318 may be a means for interfacing with the input/output device 320 . As an example, an input device may include a device such as a camera, keyboard, microphone, mouse, etc., including an audio sensor and/or an image sensor, and an output device may include a device such as a display, speaker, haptic feedback device, etc. can As another example, the input/output interface 318 may be a means for an interface with a device in which a configuration or function for performing input and output, such as a touch screen, is integrated into one. For example, when the processor 314 of the user terminal 110 processes a command of a computer program loaded in the memory 312, the server 130 or other user terminal configures using information and/or data provided. A service screen, a list of virtual characters, or 3D content may be displayed on the display through the input/output interface 318 . In FIG. 3 , the input/output device 320 is illustrated not to be included in the user terminal 110 , but the present invention is not limited thereto, and may be configured as a single device with the user terminal 110 . In addition, the input/output interface 328 of the server 130 may be a means for an interface with a device (not shown) for input or output that is connected to the server 130 or that the server 130 may include. In FIG. 3, the input/output interfaces 318 and 328 are illustrated as elements configured separately from the processors 314 and 324, but the present invention is not limited thereto, and the input/output interfaces 318 and 328 may be configured to be included in the processors 314 and 324. there is.

The user terminal 110 and the server 130 may include more components than those of FIG. 3 . However, there is no need to clearly show most of the prior art components. According to an embodiment, the user terminal 110 may be implemented to include at least a portion of the above-described input/output device 320 . In addition, the user terminal 110 may further include other components such as a transceiver, a global positioning system (GPS) module, a camera, various sensors, and a database. For example, when the user terminal 110 is a smartphone, it may include components generally included in the smartphone, for example, an acceleration sensor, a gyro sensor, a camera module, various physical buttons, and touch Various components such as a button using a panel, an input/output port, and a vibrator for vibration may be implemented to be further included in the user terminal 110 .

According to an embodiment, the processor 314 of the user terminal 110 may be configured to operate an application or a web browser application that provides a sharing service of a three-dimensional live-action character model. In this case, the program code associated with the corresponding application may be loaded into the memory 312 of the user terminal 110 . While the application is being operated, the processor 314 of the user terminal 110 receives information and/or data provided from the input/output device 320 through the input/output interface 318 or from the server 130 through the communication unit 316 . Information and/or data may be received, and the received information and/or data may be processed and stored in memory 312 . Also, such information and/or data may be provided to the server 130 through the communication unit 316 .

While the application or web browser application is being operated, the processor 314 may display text input or selected through an input device such as a camera, a microphone, etc., including a touch screen, a keyboard, an audio sensor and/or an image sensor connected to the input/output interface 318, An image, an image, etc. may be received, and the received text, image, and/or image may be stored in the memory 312 or provided to the server 130 through the communication unit 316 and the network 120 . Additionally, the processor 314 transmits a request for a virtual character list or a three-dimensional content list input by the user, a purchase request for a virtual character or three-dimensional content through an online store, a three-dimensional output request, etc. to the network 120 and It may be provided to the server 130 through the communication unit 316 .

The processor 324 of the server 130 may be configured to manage, process, and/or store information and/or data received from a plurality of user terminals and/or a plurality of external systems. According to an embodiment, the processor 324 may receive information about a virtual character or 3D content from a database (not shown). Then, the processor 324 may extract one or more virtual characters or 3D content based on the feature information set by the user. Alternatively, the processor 324 may classify information about a plurality of virtual characters or 3D content according to characteristic information set by the user. Then, the processor 324 may extract information on one or more virtual characters or three-dimensional content related to feature information set by the user from among the classified and stored information on a plurality of virtual characters or three-dimensional content.

The processor 324 may extract one or more virtual characters or three-dimensional content having characteristics similar to the characteristic information set by the user. According to an embodiment, the processor 324 may extract a list of virtual characters or 3D contents viewed by the user and feature information on the virtual characters or 3D contents included in the list. In addition, the processor 324 may calculate the utilization rate of the virtual character or 3D content searched or read by the user. Accordingly, the processor 324 may calculate a utilization rate for searching or viewing a virtual character or 3D content corresponding to the characteristic information set by the user. The calculated feature information and information on the usage rate of the virtual character or 3D content is each virtual character displayed on the display of the user terminal when the user terminal reads a plurality of virtual characters or 3D content through the online store. It can be used to determine the order or rank of characters, their arrangement position, highlighting, etc.

4 is a block diagram illustrating a configuration of a server according to an embodiment of the present disclosure. As shown, the server 130 may include a database 132 , a digital twin generator 134 , and a data learning module 136 . The database 132 may be configured to store virtual characters or 3D content produced through a production terminal (not shown). In addition, the database 132 may store data about a three-dimensional live-action character model generated by a 3D scanner from a subject of a specific person.

The data learning module 136 is trained to generate motion data of the virtual character based on the three-dimensional real-life character model or model information (or feature information) of the virtual character, or based on the model information (or feature information) of the virtual character Thus, it may include an AI-based model trained to extract one or more other virtual characters with similar characteristics. The data learning module 136 may be configured to extract one or more virtual characters having an appearance or behavior pattern similar to the virtual character based on the model information, wherein the model information is based on the appearance or behavior pattern of the virtual character. It may include at least one of keyword information and image information for the .

In one embodiment, the data learning module 136 calculates a degree of similarity between the corresponding virtual character and a plurality of other virtual characters based on the model information set by the user to extract another virtual character corresponding to the corresponding virtual character. can For example, if the hairstyle among the image information of a specific virtual character is set to 'short hair', the data learning module 136 selects a virtual character with high similarity among other virtual characters whose image information is 'short hair' among the model information. can be classified. Meanwhile, in the above example, only the case where the data learning module 136 extracts a virtual character having a similar hairstyle from the image information is described, but the present invention is not limited thereto, and fashion information (eg, clothing, accessories, etc.) of the image information. , a virtual character having similar visual characteristics, such as body shape, may be extracted. In addition, in the above-described example, although the data learning module 136 has been described as learning image information among model information, the present invention is not limited thereto, and information including keyword characteristics such as keyword information may be learned.

In one embodiment, the data learning module 136 learns the motion data (or behavior pattern) of the first character model based on the image and/or the image of the first character model, and stores the learning result in the database 132 . and may be configured to apply the motion data of the first character model stored in the database 132 as the motion data of the second character model. For example, the data learning module 136 may learn walking motion data from an image for a first model for learning motion data, and apply it as walking motion data among motion data of a virtual character of a second model. . In this way, the data learning module 136 learns data about various postures or motions of the first model included in the image or image for the first model and stores it in the database 132, and then in the database 132. It may be configured to apply the stored various posture information of the first model as motion data of the second model.

The digital twin generator 134 learns information about the behavior pattern of a specific person based on the three-dimensional live-action character model extracted from the database 132, and predicts the behavior of the virtual character based on the learned information. can be configured. The database 132 may store information on a behavior pattern learned through the digital twin generator 134 and information on a behavior prediction of a virtual character.

As an embodiment, the digital twin generator 134 may learn pre-stored model information and behavior patterns of the virtual character, and store the learned information in the database 132 . After that, based on the learned information stored in the database 132 , the digital twin generator 134 may predict the behavior pattern of the virtual character according to a specific situation.

In another embodiment, the digital twin generator 134 may generate a prediction scenario based on the model information and behavior pattern of at least one specific person stored by the database 132 . The predicted scenario generated in this way may be applied to realizing at least one of a game, animation, and virtual concert in which a virtual character is active. For example, the virtual character may implement various motions by applying the behavior pattern learned by the digital twin generator 134 as the behavior pattern of the virtual character in the game. In the above-described embodiment, the digital twin generator 134 uses the learned model information and behavior patterns to implement at least one of a game, an animation, or a virtual concert in which a virtual character is active, but is not limited thereto. , model information and behavior patterns learned in various fields such as movies and dramas through virtual characters can be applied.

5 is a diagram illustrating a process in which a virtual character produced through 3D scanning and stored in a server is shared with a user terminal through a network according to an embodiment of the present disclosure. In one embodiment, the 3D scanner may be composed of a plurality of sensors (eg, image sensors) 510, and a three-dimensional live-action character model from the subject of a specific person M through the plurality of sensors 510 can create The plurality of sensors 510 may generate a three-dimensional live-action character model by photographing all directions of the subject. In this case, the three-dimensional live-action character model may include information or 3D model data about a polygon, a curved surface, an edge, a vector, an equation, etc. representing the three-dimensional shape of the subject. As shown in FIG. 5 , the plurality of sensors 510 are shown in the form of an image sensor or a camera, but are not limited thereto, and a probe device, a time of flight (TOF) sensor, a laser sensor, a lidar sensor, etc. It may include sensors capable of generating a three-dimensional live-action character model in various ways.

The production terminal 162 may generate the virtual character DT based on the 3D live-action character model generated through the 3D scanner. In an embodiment, the production terminal 162 may set model information of a 3D live-action character model generated through a 3D scanner, and the model information may include information of a specific person transmitted from the server 130 . .

Also, the production terminal 162 may produce 3D content based on the generated virtual character DT. The 3D content may be a character such as a game, animation, drama, or movie using the virtual character DT, but is not limited thereto. Also, the 3D content may be a virtual concert in which the virtual character DT acts as a singer. In this case, the 3D content may be produced in the form of a metaverse, which means a 3D virtual world in which social, economic, and cultural activities like the real world are performed.

The server 130 may store the 3D live-action character model generated through the 3D scanner and the virtual character DT and 3D content produced through the production terminal 162, and the virtual character DT and 3D content may be configured to share with the user terminal 110 through the network 120 . As an embodiment, the user may set the preferred model information 520 through the user terminal 110 . For example, when a user searches for a virtual character (DT) or 3D content, the user sets the model information 520 including the preferred keyword information 522 and/or the image information 524, and the corresponding model information A virtual character corresponding to 520 may be searched. The keyword information 522 may include personality, hobbies, occupations, preferences, personal information, and the like of the virtual character DT. The image information 524 may include visual features such as hairstyle, fashion information, and body shape of the virtual character DT. The user terminal 110 may transmit a search request to the server 130 based on the model information 520 set through the network 120 . The network 120 transmits the search-requested model information 520 to the server 130, and the server 130, based on the received model information 520, has one or more virtual characters (DT) having similar characteristics. may be extracted and transmitted to the user terminal 110 through the network 120 . The user terminal 110 may be configured to receive a search result, and to allow the user to view the corresponding virtual character DT or 3D content through the display of the user terminal 110 .

6 is a diagram illustrating the configuration of a data learning module 136 using an artificial neural network model 612 trained to extract a virtual character having similar characteristics based on model information 520 according to an embodiment of the present disclosure. . The data learning module 136 may include an artificial neural network model 612 trained to extract one or more virtual characters having similar characteristics based on the model information 520 set by the user. The data learning module 136 or the artificial neural network model 612 used by the data learning module 136 may be generated, stored, or updated by an external computing device and executed by the processor 324 shown in FIG. 3 . The model information 520 may include keyword information 522 and image information 524 .

As shown, the data learning module 136 calculates a similarity 613 of pre-stored virtual characters in the database 132 of the server (eg, 130 in FIG. 4 ) by inputting the model information 520 as an input. An artificial neural network model 612 may be included.

As an embodiment, the degree of similarity 613 may include a degree of similarity 613 of model information of one or more virtual characters with respect to keyword information 522 and image information 524 among model information 520 set by the user. there is. For example, among the virtual characters stored in the server, the similarity 613 of the first virtual character may be calculated as 0.8, and the similarity 613 of the second virtual character may be calculated as 0.4. When the similarity 613 calculated by the artificial neural network model 612 exceeds a threshold (eg, 0.6), the data learning module 136 extracts the model information of the corresponding virtual character from the database and outputs it. can Meanwhile, although two degrees of similarity 613 calculated by the data learning module 136 are illustrated in FIG. 6 , the present invention is not limited thereto, and different numbers of degrees of similarity 613 may be output.

7 is a data learning module 136 using an artificial neural network model 612 trained to generate motion data or behavior patterns of a virtual character based on an image or image 710 of the virtual character according to an embodiment of the present disclosure. A diagram showing the configuration of The data learning module 136 may include, for example, an artificial neural network model 612 trained to extract motion data of the virtual character based on the image or video information of the virtual character stored in the server. The data learning module 136 or the artificial neural network model 612 used by the data learning module may be generated, stored, or updated by an external computing device and executed by the processor 324 shown in FIG. 3 . As shown, the data learning module 136 extracts motion data 614 and 615 based on pre-stored information in the database 132 of the server (eg, 130 in FIG. 4 ), or It may include an artificial neural network model 612 that learns a behavior pattern. The artificial neural network model 612 may extract at least one motion data 614 and 615 by inputting an image or an image (hereinafter, referred to as an image) of a virtual character.

In one embodiment, when an image of a virtual character is input, the artificial neural network model 612 recognizes an expression or posture of a virtual character included in the image of the virtual character, and implements the recognized expression or posture in the virtual character. Possible motion data can be extracted. For example, the artificial neural network model 612 may learn to extract and classify the facial expression of the virtual character as the first motion data 614 and the posture of the virtual character as the second motion data 615 . The first motion data 614 and the second motion data 615 classified by the data learning module 136 may be classified into facial expression data and posture data, respectively, and stored in the server. In another embodiment, the first motion data 614 and the second motion data 615 of the virtual character stored in the server may be configured to be applied as motions of other virtual characters.

In an embodiment, when an image of a virtual character is input, the artificial neural network model 612 may extract a behavior pattern such as an expression, posture, or movement of the virtual character included in the image of the virtual character. For example, the artificial neural network model 612 may learn to extract and classify the action of moving the shoulder as the first motion data 614 and the action of moving the leg as the second motion data 615 among the actions of the virtual character. can The first motion data 614 and the second motion data 615 classified by the data learning module 136 may be stored in the server. In another embodiment, the first motion data 614 and the second motion data 615 of the virtual character stored in the server may be applied as behavior patterns of other virtual characters. Meanwhile, although two motion data 614 and 615 are illustrated in FIG. 7 , the present invention is not limited thereto, and the artificial neural network model 612 may learn to extract and classify different numbers of motion data 614 and 615 .

8 is a diagram illustrating an example of a photobook application 800 of a virtual character according to an embodiment of the present disclosure. As shown, a plurality of shortcut buttons may be located on the user interface of the virtual character photobook application 800 executed by the user terminal. For example, a 'home' button, a 'my library' button, a 'store' button, and a 'my page' button may be displayed at the bottom of the user interface of the photobook application 800 .

In one embodiment, when the home button displayed on the user interface of the photobook application 800 is selected, a search for a virtual character, a list of photos for each virtual character (810_1, 810_2, 812_1, 812_1), a list of recommended virtual characters, etc. will be displayed. can As illustrated, the pictorial lists 810_1 and 810_2 of the model A among the pictorial lists for each virtual character may be disposed on the upper part of the user interface of the pictorial application 800 . In this case, the user may browse the pictorial of the model A through a touch input for the pictorial 810_1. In addition, when the 'My Library' button displayed at the bottom of the user interface of the photobook application 800 is selected, a list of interests including a photobook that the user has previously viewed, a previously purchased photobook, or a photobook to be purchased or read is displayed. can be When the 'store' (or 'online store') button displayed at the bottom of the user interface of the photobook application 800 is selected, an online store in which the user can view and order virtual characters or 3D content may be displayed. On the store, a user may search for or purchase a product or service corresponding to a hairstyle or clothing worn by a specific virtual character while viewing a plurality of virtual characters or 3D content. In addition, the store is an online shopping mall associated with a virtual character's three-dimensional output (eg, the three-dimensional output 152 shown in FIG. 2 ), clothes, shoes, accessories, etc., mounted on the virtual character in the photo book or the virtual character's hair. It can be linked to a hair salon related to a style. When the 'My Page' button at the bottom of the user interface of the photobook application 800 is selected, personal information such as a user's profile, preferences regarding a virtual character set by the user, etc. may be displayed. Meanwhile, although two lists of model A and model B of a virtual character are illustrated on the user interface of the photobook application 800 in FIG. 8 , the number of virtual characters and the number of photos may be different without being limited thereto.

9 is a diagram illustrating an example 900 of a manipulation operation when viewing a pictorial of a virtual character according to an embodiment of the present disclosure. As shown, the picture book of the virtual character displayed on the user terminal may be configured to enable three-dimensional viewing of the virtual character DT according to the selection of the direction key 910 by the user. In one embodiment, when the user touches (H) one of the plurality of direction keys 910, the three-dimensional model of the virtual character DT displayed on the display of the user terminal while the direction key 910 is touched (H) It can be rotated in the direction of the direction key 910 . For example, assuming that the virtual character DT displayed on the display of the user terminal is facing the front, the right side, the rear side, the left side, and the front side of the virtual character DT when the right direction key 910_4 is touched (H) The three-dimensional model of the virtual character DT may be rotated in the horizontal direction to be viewed in order. Conversely, when the left direction key 910_2 of the direction keys 910 displayed on the display through the user terminal is touched (H), the virtual character DT is displayed in order of the left side, the rear side, the right side, and the front side of the virtual character DT. ) can be rotated horizontally. As another example, when the upper direction key 910_1 of the direction keys 910 displayed on the display of the user terminal is touched (H), the virtual character DT is displayed in the order of the upper surface, the rear surface, the lower surface, and the front surface of the virtual character DT. The three-dimensional model may be rotated vertically. Conversely, when the lower direction key 910_3 displayed on the display of the user terminal is touched (H), the three-dimensional model of the virtual character DT is vertically displayed so that the lower surface, the rear surface, the upper surface, and the front surface of the virtual character DT are shown in this order. direction can be rotated. Through the rotation of the virtual character DT according to the selection of the above-described direction key, the user can view various aspects of the 3D model of the virtual character DT in various directions. Although the above-described embodiment has been described as touching (H) the direction keys 910 displayed on the display of the user terminal one by one, the present invention is not limited thereto, and the virtual character DT may be rotated by simultaneously touching (H) a plurality of direction keys. there is. For example, when the upper direction key 910_1 and the left direction key 910_2 are simultaneously pressed, the virtual character DT may be rotated in the upper left diagonal direction.

10 is a diagram illustrating another example 1000 of a manipulation operation when viewing a pictorial of a virtual character according to an embodiment of the present disclosure. As shown, the 3D model of the virtual character DT can be rotated and viewed through gestures such as the user's touch and drag operation H on the virtual character DT displayed on the display of the user terminal. For example, when viewing the right side of the virtual character DT, the user may touch the left side of the display of the user terminal and then drag and drop it in the right direction. Conversely, when viewing the left side of the virtual character DT, the user may touch the right side of the display of the user terminal and then drag and drop it in the left direction. As another example, when viewing the upper surface of the virtual character DT, the user may touch the upper side of the display of the user terminal and then drag and drop it downward. Meanwhile, when viewing the lower surface of the virtual character DT, the user may rotate the virtual character DT by touching the lower side of the display of the user terminal and then dragging and dropping in the upper direction. In addition, reading of the virtual character DT through drag and drop may be executed in a diagonal direction, and rotation of the virtual character DT may be performed through two or more touches and drag and drop.

11 is a diagram illustrating an example 1100 connected to a store when viewing 1110 of a pictorial of a virtual character according to an embodiment of the present disclosure. As illustrated, a store (or an online store) configured to allow a user to order a product or service related thereto when viewing a virtual character or 3D content through the user terminal may be displayed on the display of the user terminal. When a user reads a virtual character or three-dimensional content, the store provides a product or service corresponding to the virtual character's hairstyle or clothing (eg, clothes, shoes, accessories, etc.) worn by the virtual character through the user terminal. may be configured to be sold. In addition, the store may be configured to provide products or services corresponding to the virtual character's hairstyle or clothing worn by the virtual character in the form of a list, so as to be connected to another online store corresponding to information selected by the user on the list. In one embodiment, when selecting or touching at least one of the virtual character's head or body part when viewing the pictorial 1120 or 3D content of the virtual character, it is connected to a store related thereto or related store information is displayed on the display. may be configured to be displayed. For example, when the user touches or selects a part of the head of the virtual character displayed on the pictorial 1120, the store 1130 information related to the corresponding hairstyle may be checked and connected. In addition, when the user touches or selects a part of the body of the virtual character displayed on the pictorial 1120 , it may be configured to check and connect information about the store 1140 related to clothing worn on the corresponding body part.

In the above-described example, an example of a store for viewing and purchasing information on goods or services corresponding to clothes or hairstyles worn by the virtual character has been described, but the present invention is not limited thereto. For example, a store for viewing and purchasing information on background pictures and props around the virtual character displayed on the virtual character pictorial 1120 may be further linked.

12 is a flowchart of a method for generating and sharing a three-dimensional live-action character model according to an embodiment of the present disclosure. As shown, the method 1200 for generating and sharing a three-dimensional live-action character model may begin with the step (S1210) of generating a three-dimensional live-action character model from a subject of a specific person by a 3D scanner. In one embodiment, the 3D live-action character model is generated by a 3D scanner, and includes 3D model data including information about polygons, curved surfaces, edges, points, etc., vectors, equations, etc. that can express the appearance of the subject. can do.

Next, a virtual character or three-dimensional content may be produced (S1230) by editing or correcting the generated three-dimensional live-action character by the production terminal. Here, the virtual character may be a virtual reality character expressed by a three-dimensional live-action character model and model information. Alternatively, the virtual character may be a virtual character generated based on information learned by a data learning module or a digital twin generator of a server. Also, the 3D content may be content such as games, movies, dramas, animations, and virtual concerts produced using virtual characters.

The database may store (S1250) virtual characters or 3D content produced through the production terminal. Here, the database may include a three-dimensional live-action character model representing a virtual character, a virtual character, and three-dimensional content. In addition, the database may further include model information, motion data, and behavior patterns of virtual characters and 3D contents generated through a data learning module and a digital twin generator of the server.

Finally, by the server, at least one of a virtual character or 3D content may be shared with the user terminal ( S1270 ). In an embodiment, the user may request the virtual character or the 3D content from the server through the network through an input such as a touch on the list of virtual characters or 3D contents displayed on the display using the user terminal. The server may transmit a virtual character or 3D content searched or selected by the user according to the received request to the user terminal. In another embodiment, the user terminal may receive one or more virtual characters or three-dimensional content having similar characteristics from the server according to characteristic information such as keyword information or image information set by the user. In this case, on the display of the user terminal, the received virtual characters or 3D contents may be arranged according to the order of similarity with the feature information or highlighted (eg, 'recommendation', 'best', etc.) may be output. there is.

In general, the system for creating and sharing a three-dimensional photorealistic character model described herein includes a wireless telephone, a cellular telephone, a laptop computer, a wireless multimedia device, a wireless communication personal computer (PC) card, a PDA, an external or internal modem, It may refer to various types of devices, such as a device that communicates over a wireless channel, and the like. A device may include an access terminal (AT), an access unit, a subscriber unit, a mobile station, a mobile device, a mobile unit, a mobile phone, a mobile, a remote station, a remote terminal, a remote unit, a user device, user equipment, It may have various names, such as a handheld device and the like. Any device described herein may have memory for storing instructions and data, as well as hardware, software, firmware, or combinations thereof.

The techniques described herein may be implemented by various means. For example, these techniques may be implemented in hardware, firmware, software, or a combination thereof. Those skilled in the art will further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the disclosure herein may be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.

In a hardware implementation, the processing units used to perform the techniques include one or more ASICs, DSPs, digital signal processing devices (DSPDs), programmable logic devices (PLDs). ), field programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, electronic devices, other electronic units designed to perform the functions described herein. , a computer, or a combination thereof.

Accordingly, the various illustrative logic blocks, modules, and circuits described in connection with the disclosure herein may include general purpose processors, DSPs, ASICs, FPGAs or other programmable logic devices, discrete gate or transistor logic, discrete hardware components, or may be implemented or performed in any combination of those designed to perform the functions described herein. A general purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, eg, a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration.

For firmware and/or software implementations, the techniques may include random access memory (RAM), read-only memory (ROM), non-volatile random access memory (NVRAM), PROM ( on computer-readable media such as programmable read-only memory), erasable programmable read-only memory (EPROM), electrically erasable PROM (EEPROM), flash memory, compact disc (CD), magnetic or optical data storage devices, etc. It may be implemented as stored instructions. The instructions may be executable by one or more processors and may cause the processor(s) to perform certain aspects of the functionality described herein.

If implemented in software, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. Storage media may be any available media that can be accessed by a computer. By way of non-limiting example, such computer readable medium may contain RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or desired program code in the form of instructions or data structures. may include any other medium that can be used for transport or storage to a computer and can be accessed by a computer. Also, any connection is properly termed a computer-readable medium.

For example, if the software is transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, wireless, and microwave, the coaxial cable , fiber optic cable, twisted pair, digital subscriber line, or wireless technologies such as infrared, radio, and microwave are included within the definition of medium. As used herein, disk and disk include CD, laser disk, optical disk, digital versatile disc (DVD), floppy disk, and Blu-ray disk, where disks are usually Data is reproduced magnetically, whereas discs reproduce data optically using a laser. Combinations of the above should also be included within the scope of computer-readable media.

A software module may reside in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium may be coupled to the processor such that the process can read information from, or write information to, the storage medium. Alternatively, the storage medium may be integrated into the processor. The processor and storage medium may reside within the ASIC. The ASIC may exist in the user terminal. Alternatively, the processor and the storage medium may exist as separate components in the user terminal.

The previous description of the disclosure is provided to enable any person skilled in the art to make or use the disclosure. Various modifications to the disclosure will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to various modifications without departing from the spirit or scope of the disclosure. Accordingly, this disclosure is not intended to be limited to the examples set forth herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Although example implementations may refer to utilizing aspects of the presently disclosed subject matter in the context of one or more standalone computer systems, the subject matter is not so limited, but rather in connection with any computing environment, such as a network or distributed computing environment. may be implemented. Still further, aspects of the presently disclosed subject matter may be implemented in or across a plurality of processing chips or devices, and storage may be similarly affected across the plurality of devices. Such devices may include PCs, network servers, and handheld devices.

Although subject matter has been described in language specific to structural features and/or methodological acts, it will be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts set forth above. Rather, the specific features and acts described above are set forth as example forms of implementing the claims.

Although the method mentioned in this specification has been described through specific embodiments, it is possible to implement it as computer-readable code on a computer-readable recording medium. The computer-readable recording medium includes all types of recording devices in which data readable by a computer system is stored. Examples of the computer-readable recording medium include ROM, RAM, CD-ROM, magnetic tape, floppy disk, and optical data storage device. In addition, the computer-readable recording medium is distributed in a computer system connected to a network, so that the computer-readable code can be stored and executed in a distributed manner. In addition, functional programs, codes, and code segments for implementing the embodiments can be easily inferred by programmers in the art to which the present invention pertains.

Although the present disclosure has been described with reference to some embodiments herein, it should be understood that various modifications and changes can be made without departing from the scope of the present disclosure as understood by those skilled in the art to which the present invention pertains. something to do. Further, such modifications and variations are intended to fall within the scope of the claims appended hereto.

110: user terminal 120: network
130: server 132: database
134: digital twin generation unit 136: data learning module
150: 3D printer 152: printout
160: 3D scanner 162: production terminal
312: memory 314: processor
316: communication unit 318: input/output interface
320: input/output device 510: image sensor unit
520: model information 522: keyword information
524: image information 612: machine learning
613: similarity 614: first motion data
615: second motion data 710: training data (image/video)
810: first model pictorial 812: second model pictorial
1110: pictorial view 1120: pictorial
1130: model hair information 1140_1: model clothing information
1140_2: Model shoe information M: Actual model
DT: 3D virtual model H: User operation

Claims (10)

In the 3D live-action character model creation and sharing system,
A 3D scanner for generating a three-dimensional live-action character model from the subject of a specific person;
a production terminal configured to produce a virtual character by editing or modifying the character model, and to produce 3D content using the virtual character; and
A server configured to share at least one of the virtual character or the 3D content with a user terminal
including,
The server is
A data learning module comprising an artificial intelligence-based model trained to generate motion data based on the three-dimensional live-action character model, or to extract one or more other virtual characters having similar characteristics based on the characteristic information of the virtual character ; and
A digital twin generator configured to learn information about the behavioral pattern of the specific person based on the three-dimensional live-action character model, and predict the behavior of the virtual character based on the learned information
including,
The characteristic information, which can be set by a user of the user terminal, includes at least one of keyword information or image information about the appearance or behavior pattern of the virtual character,
The data learning module is configured to calculate a degree of similarity between the virtual character and a plurality of other virtual characters based on the characteristic information set by the user, and based on the similarity, one having an appearance or behavior pattern similar to that of the virtual character. configured to extract more than one virtual character,
system.
delete delete delete delete According to claim 1,
The server is a database configured to store and modify the virtual character or the three-dimensional content produced through the production terminal.
A system comprising
According to claim 1,
An online store configured to allow the user to view and order the virtual character or the 3D content through the user terminal
Further comprising, the system.
8. The method of claim 7,
The store is configured to sell goods or services corresponding to the hairstyle or clothing worn by the virtual character through the user terminal when the user reads the virtual character or the three-dimensional content.
8. The method of claim 7,
a 3D printer configured to generate a three-dimensional output of the virtual character
Further comprising, the system.
In the method of generating and sharing a three-dimensional live-action character model,
Generating a three-dimensional live-action character model from the subject of a specific person by the 3D scanner;
producing, by a production terminal, a virtual character or 3D content through editing or modification of the character model;
Storing the virtual character or 3D content produced through the production terminal by a database;
By the data learning module of the server, learning to generate motion data based on the three-dimensional live-action character model through an artificial intelligence-based model, or learning to extract one or more other similar virtual characters based on the characteristic information of the virtual character a step of - wherein the characteristic information is settable by a user of a user terminal and includes at least one of keyword information or image information about an appearance or behavior pattern of the virtual character;
By the data learning module of the server, based on the characteristic information set by the user, the degree of similarity between the virtual character and a plurality of other virtual characters is calculated, and at least one having an appearance or behavior pattern similar to the virtual character extracting a virtual character;
learning, by the digital twin generator of the server, information on the behavior pattern of the specific person based on the three-dimensional live-action character model, and predicting the behavior of the virtual character based on the learned information; and
Sharing, by the server, at least one of the virtual character or 3D content with a user terminal
A method comprising

Images