KR20240025320A - Method, computer device, and computer program to create 3d avatar based on multi-angle image - Google Patents

Abstract

A method, computer device, and computer program for generating a multi-angle image-based 3D avatar are disclosed. The 3D avatar creation method includes generating a plurality of 2D target images by combining an input image of a target person with a plurality of 2D standard images obtained by scanning a 3D standard avatar model; and generating a 3D avatar for the target person by reconstructing the plurality of 2D target images into 3D.

Description

Method, computer device, and computer program for creating a multi-angle image-based 3D avatar {METHOD, COMPUTER DEVICE, AND COMPUTER PROGRAM TO CREATE 3D AVATAR BASED ON MULTI-ANGLE IMAGE}

The explanation below is about image synthesis technology using deep learning.

Face conversion technology using artificial intelligence is developing to a level where converted faces can be created with high resolution.

Face transformation technology can be provided to users in a variety of ways. For example, a specific face can be composited with a user-desired background, thereby allowing the user or another person's face to appear in the user-desired background. You can also change the face of a famous person in a video to your own or someone else's face.

For example, Korea Patent Publication No. 10-1871662 (registration date June 21, 2018) discloses an image synthesis technology based on face detection.

Provides a method and device for acquiring the 2D images necessary to create a 3D avatar by photographing a 3D standard avatar model in virtual space.

In a 3D avatar generating method executed on a computer device, the computer device includes at least one processor configured to execute computer readable instructions included in a memory, and the 3D avatar generating method is performed by the at least one processor. , generating a plurality of 2D target images by combining an input image of a target person with a plurality of 2D standard images obtained by scanning a 3D standard avatar model; and generating a 3D avatar for the target person by reconstructing the plurality of 2D target images into 3D, using the at least one processor.

According to one aspect, the 3D standard avatar model may correspond to a 3D face model with normal facial features.

According to another aspect, the 3D standard avatar model may correspond to a 3D face model created by creating a 3D model of the average value of the facial features of the learning target through an artificial intelligence deep learning model.

According to another aspect, the plurality of 2D standard images may be stored as snapshots scanned at different angles or heights by placing the 3D standard avatar model in a virtual space implemented with a 3D tool.

According to another aspect, the step of generating the plurality of 2D target images includes the facial area of the 2D standard image being the target target through deep learning synthesis using the input image as a source image and each 2D standard image as a target image. A 2D target image transformed into a person's face can be created.

According to another aspect, generating a 3D avatar for the target person may include reconstructing the plurality of 2D target images into 3D based on triangulation using geometric relationships between images. there is.

According to another aspect, the step of creating a 3D avatar for the target person may include customizing the 3D avatar of the target person by modifying resources related to the avatar.

According to another aspect, the input image may be an original image for a specific person or a composite image obtained by combining faces between people.

In a 3D avatar generating method executed on a computer device, the computer device includes at least one processor configured to execute computer readable instructions included in a memory, and the 3D avatar generating method is performed by the at least one processor. , creating a 3D standard avatar model with a 3D face model with average facial features through an artificial intelligence deep learning model; and generating, by the at least one processor, a plurality of 2D standard images by scanning the 3D standard avatar model, wherein an image combining the 2D standard image with the face of the target person is applied to the target person. Provides a 3D avatar creation method characterized in that it is used as a 2D target image required to create a 3D avatar.

A computer program stored in a computer-readable recording medium is provided to execute the 3D avatar creation method on the computer device.

A computer device, comprising: at least one processor configured to execute computer readable instructions included in a memory, wherein the at least one processor selects a target person in a plurality of 2D standard images obtained by scanning a 3D standard avatar model. A process of generating a plurality of 2D target images by synthesizing input images for; and a computer device that processes a process of reconstructing the plurality of 2D target images into 3D to create a 3D avatar for the target person.

According to embodiments of the present invention, by shooting a 3D standard avatar model in a virtual space and acquiring the 2D images necessary to create a 3D avatar, more 2D images can be acquired in an environment where sophisticated settings are possible, and through this, high-quality You can create a 3D avatar.

1 is a diagram illustrating an example of a network environment according to an embodiment of the present invention.
Figure 2 is a block diagram showing an example of a computer device according to an embodiment of the present invention.
Figure 3 is a flowchart showing an example of a 3D avatar creation method that can be performed by a computer device according to an embodiment of the present invention.
Figure 4 shows an example of a 3D standard avatar model for use in creating an avatar in an embodiment of the present invention.
Figures 5 and 6 are example diagrams for explaining the process of acquiring a 2D standard image in one embodiment of the present invention.
Figures 7 and 8 are exemplary diagrams for explaining the process of acquiring a 2D target image in one embodiment of the present invention.
9 to 10 are example diagrams for explaining the process of creating a 3D avatar according to an embodiment of the present invention.
Figure 11 shows an example of a face synthesis service screen in one embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings.

Embodiments of the present invention relate to image synthesis technology using deep learning.

Embodiments including those specifically disclosed in this specification can secure sufficient 2D images necessary to create a 3D avatar in an environment that allows elaborate settings using virtual space.

The 3D avatar creation system according to embodiments of the present invention may be implemented by at least one computer device, and the 3D avatar creation method according to embodiments of the present invention may be implemented by at least one computer device included in the 3D avatar creation system. It can be performed through . At this time, the computer program according to an embodiment of the present invention may be installed and driven in the computer device, and the computer device may perform the 3D avatar creation method according to the embodiment of the present invention under the control of the driven computer program. there is. The above-described computer program can be combined with a computer device and stored in a computer-readable recording medium to execute the 3D avatar creation method on the computer.

1 is a diagram illustrating an example of a network environment according to an embodiment of the present invention. The network environment in FIG. 1 shows an example including a plurality of electronic devices 110, 120, 130, and 140, a plurality of servers 150 and 160, and a network 170. Figure 1 is an example for explaining the invention, and the number of electronic devices or servers is not limited as in Figure 1. In addition, the network environment in FIG. 1 only explains one example of environments applicable to the present embodiments, and the environment applicable to the present embodiments is not limited to the network environment in FIG. 1.

The plurality of electronic devices 110, 120, 130, and 140 may be fixed terminals or mobile terminals implemented as computer devices. Examples of the plurality of electronic devices 110, 120, 130, and 140 include smart phones, mobile phones, navigation devices, computers, laptops, digital broadcasting terminals, Personal Digital Assistants (PDAs), and Portable Multimedia Players (PMPs). ), tablet PC, etc. For example, in FIG. 1, the shape of a smartphone is shown as an example of the electronic device 110. However, in embodiments of the present invention, the electronic device 110 actually communicates with other devices through the network 170 using a wireless or wired communication method. It may refer to one of various physical computer devices capable of communicating with electronic devices 120, 130, 140 and/or servers 150, 160.

The communication method is not limited, and may include not only a communication method utilizing a communication network that the network 170 may include (for example, a mobile communication network, wired Internet, wireless Internet, and a broadcast network), but also short-range wireless communication between devices. For example, the network 170 may include a personal area network (PAN), a local area network (LAN), a campus area network (CAN), a metropolitan area network (MAN), a wide area network (WAN), and a broadband network (BBN). , may include one or more arbitrary networks such as the Internet. Additionally, the network 170 may include any one or more of network topologies including a bus network, star network, ring network, mesh network, star-bus network, tree or hierarchical network, etc. Not limited.

Each of the servers 150 and 160 is a computer device or a plurality of computers that communicate with a plurality of electronic devices 110, 120, 130, 140 and a network 170 to provide commands, codes, files, content, services, etc. It can be implemented with devices. For example, the server 150 may be a system that provides a service (for example, an avatar creation service) to a plurality of electronic devices 110, 120, 130, and 140 connected through the network 170.

Figure 2 is a block diagram showing an example of a computer device according to an embodiment of the present invention. Each of the plurality of electronic devices 110, 120, 130, and 140 described above or each of the servers 150 and 160 may be implemented by the computer device 200 shown in FIG. 2. For example, the 3D avatar creation system according to embodiments of the present invention may be implemented by the computer device 200 shown in FIG. 2.

As shown in FIG. 2, this computer device 200 may include a memory 210, a processor 220, a communication interface 230, and an input/output interface 240. The memory 210 is a computer-readable recording medium and may include a non-permanent mass storage device such as random access memory (RAM), read only memory (ROM), and a disk drive. Here, non-perishable large-capacity recording devices such as ROM and disk drives may be included in the computer device 200 as a separate permanent storage device that is distinct from the memory 210. Additionally, an operating system and at least one program code may be stored in the memory 210. These software components may be loaded into the memory 210 from a computer-readable recording medium separate from the memory 210. Such separate computer-readable recording media may include computer-readable recording media such as floppy drives, disks, tapes, DVD/CD-ROM drives, and memory cards. In another embodiment, software components may be loaded into the memory 210 through the communication interface 230 rather than a computer-readable recording medium. For example, software components may be loaded into memory 210 of computer device 200 based on computer programs installed by files received over network 170.

The processor 220 may be configured to process instructions of a computer program by performing basic arithmetic, logic, and input/output operations. Commands may be provided to the processor 220 by the memory 210 or the communication interface 230. For example, processor 220 may be configured to execute received instructions according to program code stored in a recording device such as memory 210.

The communication interface 230 may provide a function for the computer device 200 to communicate with other devices (eg, the storage devices described above) through the network 170. For example, a request, command, data, file, etc. generated by the processor 220 of the computer device 200 according to a program code stored in a recording device such as memory 210 is transmitted to the network ( 170) and can be transmitted to other devices. Conversely, signals, commands, data, files, etc. from other devices may be received by the computer device 200 through the communication interface 230 of the computer device 200 via the network 170. Signals, commands, data, etc. received through the communication interface 230 may be transmitted to the processor 220 or memory 210, and files, etc. may be stored in a storage medium (as described above) that the computer device 200 may further include. It can be stored as a permanent storage device).

The input/output interface 240 may be a means for interfacing with the input/output device 250. For example, input devices may include devices such as a microphone, keyboard, or mouse, and output devices may include devices such as displays and speakers. As another example, the input/output interface 240 may be a means for interfacing with a device that integrates input and output functions, such as a touch screen. The input/output device 250 may be configured as a single device with the computer device 200.

Additionally, in other embodiments, computer device 200 may include fewer or more components than those of FIG. 2 . However, there is no need to clearly show most prior art components. For example, the computer device 200 may be implemented to include at least some of the input/output devices 250 described above, or may further include other components such as a transceiver, a database, etc.

Hereinafter, specific embodiments of the method and device for generating a multi-angle image-based 3D avatar will be described.

To create a 3D avatar for a person, a 3D avatar is created by installing dozens to 100 or more cameras in an offline space, then filming people located in the space from various angles and heights, and reconstructing the captured images in 3D. can do.

In order to create a 3D avatar of another person, there is the difficulty of having to build a lot of filming equipment every time, and because the shooting environment such as angle and height is manually adjusted, there is a problem that it takes a lot of time and money to match and correct the image.

In addition, in the case of people who are not real people, such as the dead, non-existent synthetic figures, or people living long distances, it is impossible or difficult to participate in the filming required to create a 3D avatar.

In these embodiments, a 3D avatar can be created without restrictions on the target object or shooting environment using a 3D standard avatar model produced through an artificial intelligence-based deep learning model and a virtual space that allows for elaborate settings.

The computer device 200 according to this embodiment can provide an avatar creation service to clients through a dedicated application installed on the client or through access to a web/mobile site related to the computer device 200. The computer device 200 may be configured with a 3D avatar creation system implemented on a computer. For example, the 3D avatar creation system may be implemented in the form of a program that operates independently, or may be implemented in the form of an in-app of a specific application to enable operation on the specific application.

The processor 220 of the computer device 200 may be implemented as a component for performing the following 3D avatar creation method. Depending on the embodiment, components of the processor 220 may be selectively included in or excluded from the processor 220. Additionally, depending on the embodiment, components of the processor 220 may be separated or merged to express the functions of the processor 220.

The processor 220 and its components can control the computer device 200 to perform the steps included in the 3D avatar creation method below. For example, the processor 220 and its components may be implemented to execute instructions according to the code of an operating system included in the memory 210 and the code of at least one program.

Here, the components of the processor 220 may be expressions of different functions performed by the processor 220 according to instructions provided by program codes stored in the computer device 200.

The processor 220 may read necessary instructions from the memory 210 where instructions related to controlling the computer device 200 are loaded. In this case, the read command may include an command for controlling the processor 220 to execute steps that will be described later.

Steps included in the 3D avatar creation method to be described later may be performed in an order different from the order shown, and some of the steps may be omitted or additional processes may be included.

Figure 3 is a flowchart showing an example of a 3D avatar creation method that can be performed by a computer device according to an embodiment of the present invention.

The 3D avatar creation method according to this embodiment can be performed by the computer device 200 described above. In this case, the processor 220 of the computer device 200 may be implemented to execute control instructions according to the code of an operating system or at least one program included in the memory 210. Here, the processor 220 causes the computer device 200 to perform the steps (S310 to S330) included in the 3D avatar creation method of FIG. 3 according to the control command provided by the code stored in the computer device 200. (200) can be controlled.

Referring to FIG. 3, in step S310, the processor 220 may scan a 3D standard avatar model in virtual space to generate a plurality of 2D images (hereinafter referred to as '2D standard images'). The 3D standard avatar model corresponds to a 3D model with normal facial features that can accommodate various facial features, and is created through 3D facial modeling technology based on artificial intelligence deep learning. It may refer to a 3D face model. For example, a 3D standard avatar model may refer to a 3D face model created by creating a 3D model of the average value of the facial features of numerous learning targets based on an artificial intelligence deep learning model that learns the distribution of a data set. The processor 220 can scan a 3D standard avatar model using the virtual space on the 3D tool. Instead of offline space, you can use a virtual space that allows elaborate settings such as shooting angle and height in a 3D tool as a shooting environment, and use this virtual space to snap 3D standard avatar models at different angles or heights within 360 degrees. By saving as a snapshot, dozens to hundreds of standard 2D images can be created.

In step S320, when an input image for a target person for avatar creation is given, the processor 220 synthesizes the input image with each 2D standard image to create a plurality of 2D images (hereinafter referred to as '2D target images'). can be created. The processor 220 can synthesize the face area of a 2D standard image into the face of a target person through facial synthesis technology based on deep learning (eg, DNN, etc.). By applying deep learning face synthesis to scan data (2D standard image) for a 3D standard avatar model, scan data (2D target image) with the face changed to the target person can be obtained. When the input image is called the source image and the 2D standard image is the target image, the weight is set at a ratio of 0:100 = target: source to maintain the facial features of the source image and create a background image (the rest of the style area excluding the face area). can only be changed. In other words, the processor 220 can obtain a composite image in which the facial features of the facial area extracted from the source image are maintained while the remaining areas are transformed into the style of a 2D standard image. As a result, by combining all of the plurality of 2D standard images obtained in step S310 with the face of the target person, it is possible to obtain the same result as if the person was directly photographed from 360 degrees by changing the angle or height. .

In step S330, the processor 220 may reconstruct the plurality of 2D target images obtained in step S320 into 3D to create a 3D avatar for the desired target person. The processor 220 can create a 3D avatar using scan data (2D target image) whose face has been changed to a target person. For example, the processor 220 may reconstruct a 2D target image into 3D based on triangulation using geometric relationships between 2D images. Furthermore, the processor 220 may customize the 3D avatar of the target person using resources related to the avatar. For example, the processor 220 can create a 3D avatar with desired elements or designs by changing or adding the avatar's eye color, facial expression, skin tone or texture, hairstyle, clothing, or other accessories.

In these embodiments, a 3D standard avatar model produced through an artificial intelligence-based deep learning model and a 3D tool are used to use a virtual space that allows for elaborate settings to show a certain person without restrictions on the existence of the target person, conditions, shooting environment, etc. Even so, you can create a 3D avatar of that person.

Figure 4 shows an example of a 3D standard avatar model for use in creating an avatar in an embodiment of the present invention.

Referring to FIG. 4, the 3D standard avatar model 410 is a 3D model with ordinary facial features with good face synthesis performance, and a 3D face model created through deep learning-based 3D face modeling can be used.

Through an artificial intelligence deep learning model that learns the distribution of a data set, a 3D face model created by averaging the facial features of numerous learning targets as a 3D model can be used as a 3D standard avatar model (410).

Figures 5 and 6 are example diagrams for explaining the process of acquiring a 2D standard image in one embodiment of the present invention.

Referring to FIG. 5, the processor 220 uses the virtual space 50 implemented with a 3D tool to place the 3D standard avatar model 410 in the virtual space 50 and then displays it at different angles or heights within 360 degrees. A snapshot can be created by scanning the 3D standard avatar model 410. In this embodiment, instead of offline space, which consumes a lot of cost and time, a virtual space that allows elaborate settings such as shooting angle and height in a 3D tool can be used as a shooting environment.

Referring to FIG. 6, the processor 220 can obtain tens to hundreds of 2D standard images 620 by storing 3D standard avatar models 410 at different angles or heights as snapshots using virtual space. there is.

Figures 7 and 8 are exemplary diagrams for explaining the process of acquiring a 2D target image in one embodiment of the present invention.

Referring to FIG. 7, when an input image 730 for a target person for avatar creation is given, the processor 220 synthesizes the input image 730 with a 2D standard image 620 to create a 2D target required for 3D avatar creation. An image 740 can be created.

When the input image 730 is the source image and the 2D standard image 620 is the target image, the weight is set at a ratio of 0:100=target:source to use the face area of the 2D standard image 620 as the target person. By changing the face to , a 2D target image 740 with the face of the target person can be obtained.

Referring to FIG. 8, the processor 220 performs face synthesis with the target person for all of the plurality of 2D standard images 620 acquired through the 3D standard avatar model 410, thereby creating a plurality of 2D target images 740. ) can be obtained. N 2D target images 740 can be created by combining the N 2D standard images 620 with the face of the target person. At this time, the N number of 2D target images 740 are 2D images substantially necessary for creating a 3D avatar for the target person.

9 to 10 are example diagrams for explaining the process of creating a 3D avatar according to an embodiment of the present invention.

Referring to FIG. 9 , the processor 220 may reconstruct a plurality of 2D target images 740 into 3D to generate a 3D avatar 950 for the target person. A 3D avatar 950 can be created using the 2D target image 740, which is scan data containing the target person's face.

For example, the processor 220 can create a 3D avatar 950 with a desired face by reconstructing the 2D target image 740 into 3D using a triangulation method based on geometric relationships between images.

The processor 220 is also capable of customizing the 3D avatar 950 of the target person using resources related to the avatar.

For example, as shown in FIG. 10, the 3D avatar 950 can be customized in a desired direction by changing the existing outfit 1001 of the 3D avatar 950 to another desired outfit 1002.

In addition to the costume, you can change or add the eye color, facial expression, skin tone or texture, hairstyle, and other accessories of the 3D avatar (950).

The input image 730 used to create the 3D avatar 950 may be an original image or, depending on the embodiment, a synthetic image.

The avatar creation service according to the present invention may be provided as part of a face synthesis service that synthesizes the faces of two people and provides a composite result. Through the face synthesis service, two people can be combined, and a service that creates a 3D avatar for a synthetic person, not a real person, can be provided.

Figure 11 shows an example of a face synthesis service screen in one embodiment of the present invention.

Referring to FIG. 11, the face synthesis service screen 1100 includes a source selection interface 1110 for selecting a source image, a synthesis result interface 1120 for providing a synthesis result image, and a synthesis result interface 1120 for adjusting the synthesis ratio of the source image. It may include a ratio adjustment interface 1130, a reset interface 1140 for resetting the composite ratio of the source image, and a style selection interface 1150 for selecting a style source (target image). Here, the style source refers to the targeting style to be reflected in the resulting image, and the background (appearance) area excluding the face area of the image set as the style source is applied as the style appearance of the resulting image.

The user can upload the A image and B image of the target for compositing through the source selection interface 1110.

The user can use the ratio adjustment interface 1130 to adjust the composite ratio between the A image and the B image as desired. When the reset interface 1140 is input, the composite ratio on the ratio adjustment interface 1130 is automatically adjusted to the initial value (for example, 50:50).

The processor 220 can combine the A image and B image input as the source image at a ratio desired by the user. In this case, the source image selected as the A image can be applied as the style source. Through the style selection interface 1150, one of image A and image B or another separate image can be selected and applied as a style source.

When the composite image of image A and image B is called the source image and the style image is the target image, the style can be changed while maintaining the facial features of the source image by setting the weight at a ratio of 0:100=target:source.

The processor 220 may display a composite result image using the A image and the B image through the composite result interface 1120. At this time, when image A is applied as a style source, the style of image A is reflected in the resulting composite image.

Furthermore, the face synthesis service screen 1000 may further include an avatar creation interface 1160 for creating a 3D avatar using the synthesis result image.

When the avatar creation interface 1160 is selected, the processor 220 uses the synthesis result image displayed through the synthesis result interface 1120 as the target person to generate and provide a 3D avatar with a composite face of the A image and the B image. You can. In other words, the processor 220 uses the composite result of the A image and the B image as an input image for the target person, creates a 2D target image by combining it with a pre-prepared 2D standard image, and reconstructs it in 3D to create a composite person. You can create a 3D avatar for.

Accordingly, the present embodiments can create a 3D avatar using not only the original image of the target person but also a synthetic image, making it possible to create a 3D avatar not only for an existing real person but also for a virtual person.

As such, according to embodiments of the present invention, a 3D avatar can be created without restrictions on the target object or shooting environment by capturing a 3D standard avatar model in a virtual space and obtaining the 2D image necessary to create a 3D avatar. Moreover, according to embodiments of the present invention, more 2D images can be acquired in an environment where sophisticated settings are possible, thereby creating a high-quality 3D avatar.

The device described above may be implemented with hardware components, software components, and/or a combination of hardware components and software components. For example, the devices and components described in the embodiments include a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), and a programmable logic unit (PLU). It may be implemented using one or more general-purpose or special-purpose computers, such as a logic unit, microprocessor, or any other device capable of executing and responding to instructions. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. Additionally, a processing device may access, store, manipulate, process, and generate data in response to the execution of software. For ease of understanding, a single processing device may be described as being used; however, those skilled in the art will understand that a processing device includes multiple processing elements and/or multiple types of processing elements. It can be seen that it may include. For example, a processing device may include a plurality of processors or one processor and one controller. Additionally, other processing configurations, such as parallel processors, are possible.

Software may include a computer program, code, instructions, or a combination of one or more of these, which may configure a processing unit to operate as desired, or may be processed independently or collectively. You can command the device. The software and/or data may be embodied in any type of machine, component, physical device, computer storage medium or device for the purpose of being interpreted by or providing instructions or data to the processing device. there is. Software may be distributed over networked computer systems and stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. At this time, the medium may continuously store a computer-executable program, or temporarily store it for execution or download. In addition, the medium may be a variety of recording or storage means in the form of a single or several pieces of hardware combined. It is not limited to a medium directly connected to a computer system and may be distributed over a network. Examples of media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, And there may be something configured to store program instructions, including ROM, RAM, flash memory, etc. Additionally, examples of other media include recording or storage media managed by app stores that distribute applications, sites or servers that supply or distribute various other software, etc.

As described above, although the embodiments have been described with limited examples and drawings, various modifications and variations can be made by those skilled in the art from the above description. For example, the described techniques are performed in a different order than the described method, and/or components of the described system, structure, device, circuit, etc. are combined or combined in a different form than the described method, or other components are used. Alternatively, appropriate results may be achieved even if substituted or substituted by an equivalent.

Therefore, other implementations, other embodiments, and equivalents of the claims also fall within the scope of the claims described below.

Claims (20)

In a 3D avatar creation method executed on a computer device,
The computer device includes at least one processor configured to execute computer readable instructions contained in a memory,
The 3D avatar creation method is:
generating, by the at least one processor, a plurality of 2D target images by combining an input image of a target person with a plurality of 2D standard images obtained by scanning a 3D standard avatar model; and
Generating a 3D avatar for the target person by reconstructing the plurality of 2D target images into 3D by the at least one processor
A 3D avatar creation method including. According to paragraph 1,
The 3D standard avatar model corresponds to a 3D face model with normal facial features.
A 3D avatar creation method featuring: According to paragraph 1,
The 3D standard avatar model corresponds to a 3D face model created by creating a 3D model of the average value of the facial features of the learning target through an artificial intelligence deep learning model.
A 3D avatar creation method featuring: According to paragraph 1,
The plurality of 2D standard images are stored as snapshots scanned at different angles or heights by placing the 3D standard avatar model in a virtual space implemented with a 3D tool.
A 3D avatar creation method featuring: According to paragraph 1,
The step of generating the plurality of 2D target images includes:
Generating a 2D target image in which the face area of the 2D standard image is transformed into the face of the target person through deep learning synthesis using the input image as a source image and each 2D standard image as a target image.
A 3D avatar creation method featuring: According to paragraph 1,
The step of creating a 3D avatar for the target person is,
Reconstructing the plurality of 2D target images into 3D based on triangulation using geometric relationships between images
A 3D avatar creation method including. According to paragraph 1,
The step of creating a 3D avatar for the target person is,
Customizing the 3D avatar of the target person by modifying resources related to the avatar.
A 3D avatar creation method including. According to paragraph 1,
The input image is an original image for a specific person or a composite image created by combining faces between people.
A 3D avatar creation method featuring: In a 3D avatar creation method executed on a computer device,
The computer device includes at least one processor configured to execute computer readable instructions contained in a memory,
The 3D avatar creation method is:
Creating a 3D standard avatar model using a 3D face model with average facial features using an artificial intelligence deep learning model using the at least one processor; and
Generating, by the at least one processor, a plurality of 2D standard images by scanning the 3D standard avatar model
Including,
An image that combines the 2D standard image with the face of the target person is used as the 2D target image needed to create a 3D avatar for the target person.
A 3D avatar creation method featuring: According to clause 9,
The step of producing the 3D standard avatar model is,
Creating a 3D face model with the average value of the facial features of the learning target through the artificial intelligence deep learning model.
A 3D avatar creation method featuring: According to clause 9,
The step of generating a plurality of 2D standard images includes:
A step of placing the 3D standard avatar model in a virtual space implemented with a 3D tool, scanning it at different angles or heights, and saving it as a snapshot.
A 3D avatar creation method including. A computer program stored in a computer-readable recording medium to cause the computer device to execute the 3D avatar creation method of any one of claims 1 to 11. In computer devices,
At least one processor configured to execute computer readable instructions contained in memory
Including,
The at least one processor,
A process of generating a plurality of 2D target images by combining an input image of a target person with a plurality of 2D standard images obtained by scanning a 3D standard avatar model; and
A process of reconstructing the plurality of 2D target images into 3D to create a 3D avatar for the target person.
A computer device that processes According to clause 13,
The 3D standard avatar model corresponds to a 3D face model with average facial features.
A computer device characterized by a. According to clause 13,
The 3D standard avatar model corresponds to a 3D face model created by creating a 3D model of the average value of the facial features of the learning target through an artificial intelligence deep learning model.
A computer device characterized by a. According to clause 13,
The plurality of 2D standard images are stored as snapshots scanned at different angles or heights by placing the 3D standard avatar model in a virtual space implemented with a 3D tool.
A computer device characterized by a. According to clause 13,
The at least one processor,
Generating a 2D target image in which the face area of the 2D standard image is transformed into the face of the target person through deep learning synthesis using the input image as a source image and each 2D standard image as a target image.
A computer device characterized by a. According to clause 13,
The at least one processor,
Reconstructing the plurality of 2D target images into 3D based on triangulation using geometric relationships between images
A computer device characterized by a. According to clause 13,
The at least one processor,
Customizing a 3D avatar of the target person by modifying resources associated with the avatar
A computer device characterized by a. According to clause 13,
The input image is an original image for a specific person or a composite image created by combining faces between people.
A computer device characterized by a.

Images