WO2023224212A1

WO2023224212A1 - Image processing method and image processing device for facilitating three-dimensional object editing by user

Info

Publication number: WO2023224212A1
Application number: PCT/KR2023/001639
Authority: WO
Inventors: 진재혁
Original assignee: 주식회사 원유니버스
Priority date: 2022-05-20
Filing date: 2023-02-06
Publication date: 2023-11-23
Also published as: KR102641060B1; KR20230162184A

Abstract

Disclosed is an image processing method for facilitating three-dimensional (3D) object editing by a user, the image processing method comprising: a step of acquiring an original image of a 3D object; an object editing step; an edited image acquisition step of acquiring a UV map image and a 2D image of an edited object; a step of generating an original texture map for the original image, which is performed in parallel with the edited image acquisition step; a step of collecting pixel information from the 2D image and the UV map image; a step of modeling a corrected texture map to be applied to an actual 3D model, by using the pixel information of the 2D image, the pixel information of the UV map image, and information of the texture map; and a step of performing UV mapping using the corrected texture map.

Description

Image processing method and image processing device that facilitates editing of 3D objects by users

The present invention relates to an image processing method and an image processing device that facilitate editing of three-dimensional (3D) objects by a user. Specifically, the present invention relates to an image processing method and an image processing device that facilitates editing of 3D avatar makeup by a user. It's about.

There are two main ways for users to directly modify the makeup of the 3D avatar object that represents them in the metaverse.

First, the direct painting method has the advantage of being intuitive because painting is performed on an actual 3D model, but it has the disadvantage of being awkward and difficult to depict in detail because it is painting in a 3D space that is generally unfamiliar to users.

Second, it is a texture real-time editing method, which has the advantage of enabling convenient and detailed depiction because it draws on a generally familiar 2D plane. However, it is not intuitive because it must be drawn on the texture rather than the image directly visible to the user. The downside is that it's awkward.

As such, there is a need for an image processing method and image processing device for 3D object makeup that complements the shortcomings of conventional methods, enables intuitive and detailed description, and improves user convenience.

The present invention was developed to solve the above-described conventional problems, and its purpose is to provide an image processing method and image processing device for 3D object makeup that enables intuitive and detailed description and improves user convenience. there is.

An image processing method that facilitates editing of a three-dimensional (3D) object by a user according to an embodiment of the present invention includes obtaining an original image of a 3D object; object editing step; An editing image acquisition step of acquiring a 2D image and a UV map image for the edited object; Performed in parallel with the edited image acquisition step, generating an original texture map for the original image; collecting pixel information from the 2D image and the UV map image; Modeling a corrected texture map to be applied to an actual 3D model using the 2D image pixel information, the UV map image pixel information, and the texture map information; and performing UV mapping using the corrected texture map.

In one embodiment, the object editing step is performed according to a user editing command input through an editing interface, and the user is preferably able to set a predetermined location where the edited image is obtained using the editing interface. do.

In one embodiment, the image processing method preferably models the corrected texture map and outputs a mapped 3D model in real time through the output unit.

In one embodiment, the step of collecting pixel information from the 2D image and the UV map image includes collecting pixel color information at a predetermined coordinate from the 2D image, and pixel color information at the same coordinate as the predetermined coordinate from the UV map image. It is desirable to collect UV information and output pixel color information with UV coordinates corresponding to the pixel UV information from the original texture map.

In one embodiment, the pixel color information collected from the 2D image is compared with the pixel color information collected from the original texture map, and if the two are different, the pixel color information collected from the 2D image is mapped to an actual 3D model. It is desirable to output the information to be used for decision making.

According to another embodiment of the present invention, an image processing device that facilitates editing of three-dimensional (3D) objects by a user, the user interface including an input unit and an output unit including an editing interface that supports the user's editing of 3D objects. wealth; an image acquisition unit that acquires a 2D image and a UV map image for the original 3D object image displayed on the output unit; a texture generator that generates an original texture map by expanding the original 3D object image in a two-dimensional UV space; a pixel information extraction unit that extracts pixel information of predetermined coordinates from the image acquired by the image acquisition unit; a modeling unit that models a corrected texture map to be applied to an actual 3D model using the 2D image, the UV map image, and the original texture map; and a UV mapping unit that maps the corrected texture map to a 3D model.

In one embodiment, the editing interface preferably supports the user to set a predetermined position where the edited image acquired by the image acquisition unit is acquired when editing an object.

In one embodiment, the output unit preferably models the corrected texture map and outputs a mapped 3D model in real time.

In one embodiment, the pixel information extraction unit collects pixel color information of a predetermined coordinate from the 2D image, collects pixel UV information of the same coordinate as the predetermined coordinate from the UV map image, and collects pixel UV information of the same coordinate as the predetermined coordinate from the UV map image. , it is desirable to collect pixel color information with UV coordinates corresponding to the pixel UV information.

In one embodiment, the modeling unit compares the pixel color information collected from the 2D image with the pixel color information collected from the original texture map, and if the two are different, the pixel color information collected from the 2D image is compared to the actual pixel color information collected from the 2D image. It is desirable to model the corrected texture map by determining it as information to be mapped to the 3D model.

Therefore, according to the present invention, a user can edit 3D avatar makeup intuitively and easily.

Additionally, according to the present invention, there is an effect that detailed description is possible when editing an object.

Additionally, according to the present invention, there is an effect of improving user convenience in editing 3D objects.

1 is a configuration diagram of an image processing device according to an embodiment of the present invention.

Figure 2 is a diagram for explaining UV mapping.

Figure 3 is a flowchart of an image processing method according to an embodiment of the present invention.

Figure 4 is a diagram for explaining an image processing method according to an embodiment of the present invention.

Figure 5 is a diagram for explaining an image processing method according to another embodiment of the present invention.

Hereinafter, preferred embodiments will be described with reference to the attached drawings. In this process, the thickness of lines or sizes of components shown in the drawing may be exaggerated for clarity and convenience of explanation. In addition, the terms described below are terms defined in consideration of functions in the present invention, and may vary depending on the intention or custom of the user or operator. Therefore, definitions of these terms should be made based on the content throughout this specification.

In this specification, a module may mean a functional and structural combination of hardware for carrying out the technical idea of the present invention and software for driving the hardware. For example, the module may mean a logical unit of a predetermined code and hardware resources for executing the predetermined code, and does not necessarily mean a physically connected code or one type of hardware. It can be easily inferred by an average expert in the technical field.

Additionally, when a component is referred to as being “connected” or “connected” to another component, it may be directly connected or connected to the other component, but other components may also exist in between. It must be understood that there is. On the other hand, when it is mentioned that a component is “directly connected” or “directly connected” to another component, it should be understood that there are no other components in between.

Singular expressions include plural expressions unless the context clearly dictates otherwise.

In addition, throughout the specification of the present application, when a part "includes" a certain element, this means that it may further include other elements rather than excluding other elements, unless specifically stated to the contrary.

It is obvious to those skilled in the art that the present invention can be embodied in other specific forms without departing from the essential features of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. In the drawings, like symbols refer to like elements.

In addition, the following examples do not limit the scope of the present invention, but are provided merely as examples, and there may be various embodiments implemented through the technical idea of the present invention.

In the following description, a 3D (three-dimensional) model refers to 3D content expressed in a virtual 3D space. For example, a 3D model may be 3D content that represents an object in the 3D real world in a virtual 3D space. In the following description, 3D means three dimensions and 2D means two dimensions.

영상처리장치image processing device

Figure 1 is a configuration diagram of an image processing device 100 according to an embodiment of the present invention.

Referring to the drawing, the image processing device 100 includes a user interface unit 110, an image acquisition unit 120, a texture creation unit 130, a pixel information extraction unit 140, a modeling unit 150, and a UV mapping unit. It may be configured to include (160), a storage unit (170), and a control unit (180).

The above configurations are illustrative, and some of the listed configurations may be omitted, and configurations not listed may be further included in the image processing apparatus 100.

The user interface unit 110 is for communication between the image processing device 100 and the user and includes an input unit 112 and an output unit 114.

The input unit 112 may receive information including a processing command from the user. This input unit 112 may include at least one of a voice input unit, a gesture input unit, a touch input unit, and a mechanical input unit.

Additionally, the input unit 112 includes an editing interface (not shown) that supports user editing of objects. The editing interface allows users to edit object images using input including keyboard input and touch screen-based gestures. For example, a user can change the color, size, or any other visual property of the original object through an editing interface.

Additionally, the editing interface may support the user to arbitrarily determine a predetermined location where the object image is obtained when the user edits an object. For example, if the object is a 3D avatar face, the editing interface can display the 3D object by rotating it to various angles desired by the user, and allow the user to select the object image observed at a certain location designated by the user as the image to be edited. .

Meanwhile, the output unit 114 is intended to generate output related to vision, hearing, tactile sensation, etc., and may include at least one of a display unit and a speaker.

Additionally, the output unit 114 may further include a preview interface (not shown). Users can preview and review the edited 3D object through the preview interface before creating the edited 3D object model. Additionally, the preview interface may support a user to, for example, change the scale, orientation or placement of a 3D object on the display screen.

The input unit 112 and the output unit 114 may be provided as separate components, or may be provided integrally, such as a touch input display unit.

Additionally, the user interface unit 110 may further include a processor (not shown) that controls the overall operation of each component of the user interface unit 110.

The image acquisition unit 120 acquires an object image displayed on the output unit 114.

For example, the image acquisition unit 120 may capture and acquire the original image of the object model before editing by the user.

Additionally, the image acquisition unit 120 may acquire a 2D image for an object model edited by the user that is observed at a location designated by the user.

Additionally, the image acquisition unit 120 may acquire a UV map image for the object model observed at a location designated by the user. Specifically, the image acquisition unit 120 may generate a UV map image and UV mapping coordinate information for a 3D object model using preset 3D model information.

Here, the 2D image of the object and the UV map image are 1:1 matching images in which the information contained in each pixel is different, but the location is the same.

The texture map generator 130 generates a texture map representing the texture of the object model.

Here, the texture map is a two-dimensional UV map for a 3D object image obtained by unwrapping the 3D object image in a two-dimensional UV space. The texture map includes polygons that make up the object model and includes UV mapping coordinate information that ensures that the polygon of the model and the expanded polygon have the same shape. At this time, the UV map is obtained by expanding the 3D object image into a 2-dimensional UV space based on the 3-dimensional coordinates of the 3D object model.

Here, the UV map applies spherical unwrap to convert the three-dimensional coordinates (x, y, z) of each vertex in the 3D model of the mesh structure into the coordinates (u, v) of the UV coordinate system according to Equation 1 below. It can be obtained by converting to .

(Here, r is the radius of the sphere when spherically expanded,

lim.)

In the present invention, the texture map generator 130 generates a texture map for the original image before the object is edited by the user.

The pixel information extraction unit 140 extracts pixel color information of predetermined coordinates (x, y) from the 2D image acquired by the image acquisition unit 120, and extracts the same pixel color information from the UV map image acquired by the image acquisition unit 120. Extract pixel UV information at coordinates (x,y).

Here, the pixel color information obtained by the pixel information extractor 140 from the 2D image includes RGB information, and the pixel information obtained by the pixel information extractor 140 from the UV map image includes UV coordinate information.

The modeling unit 150 uses the 2D image information acquired by the image acquisition unit 120, the UV map image information, and the texture map information generated by the texture map generator 130 to create a corrected texture to be applied to the actual 3D model. Model the map.

Specifically, the modeling unit 150 uses pixel UV information for a predetermined coordinate in the UV map image extracted by the pixel information extraction unit 150 to create an original texture map with UV coordinates corresponding to the pixel UV information. By collecting pixel color information for a pixel and comparing it with pixel color information for pixels with the same coordinates in the 2D image, pixel color information to be mapped to the actual 3D model is determined.

Here, if the pixel color information for the pixel of the original texture map at the corresponding location is different from the pixel color information of the 2D image at the corresponding location, the pixel color information of the 2D image is determined as information to be mapped to the actual 3D model, so that the user Can reflect object editing by .

In the same manner as described above, the modeling unit 150 generates a corrected texture to be applied to the actual 3D model using 2D image information, UV map image information, and texture map information of the object edited by the user.

Additionally, the above process is performed for one pixel, and by repeating the process for the remaining pixels, a texture map to be mapped to the actual 3D model is completed.

Once the final texture map to be mapped to the actual model is generated, the UV mapping unit 160 synthesizes a 3D object image by UV mapping it to the actual 3D model.

UV mapping is a 3D modeling process that turns a 2D picture into a 3D model. Figure 2 is a diagram to explain the relationship between the mesh 210 of the 3D model, the material 220, and the 2D image 230. am. The mesh 210 may be a data structure that stores a plurality of coordinate data, and may create a 3D mesh based on the shape of a 2D object.

The mesh 210 may include polygon data and UV. Polygon data may be composed of vertices, edges, and faces representing polygons that make up the shape of a 3D model. UV refers to the two-dimensional coordinates of the texture corresponding to the vertex/line/face of the polygon. Referring to the drawing, for example, UV may represent the u and v coordinates of texture 1 corresponding to a face defined by x, y, and z coordinates.

Material 220 may be composed of multiple textures. The drawing shows an example in which the material 220 includes texture 1 and texture 2. The texture included in the material 220 may be created based on a 2D image.

Accordingly, one face defined by the mesh can correspond to one material. For example, a different material may correspond to each face. Additionally, a material may correspond to multiple faces within one mesh or multiple faces within multiple meshes. Accordingly, the texture generated based on the 2D image can be expressed on one side of the 3D model generated by polygon data, and its corresponding relationship can be identified by UV.

In another configuration, the storage unit 170 may store various data related to the image processing method according to the present invention. The storage unit 170 includes flash memory, hard disk, Secure Digital Card (SD card), Random Access Memory (RAM), Read Only Memory (ROM), and web storage. It may be implemented with one or more storage media such as storage).

The control unit 180 controls the overall operation of each part of the image processing apparatus 100 to perform the image processing method according to the present invention. The control unit 180 includes a user interface unit 110, an image acquisition unit 120, a texture map creation unit 130, a pixel information extraction unit 140, a modeling unit 150, a UV mapping unit 160, and a storage unit. Each component of the image processing apparatus 100, including at least one of (170), can be controlled.

The control unit 180 includes application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), processors, and controllers. It may be implemented with at least one of (controllers), micro-controllers, and microprocessors.

영상 처리 방법Image processing method

The image processing method according to the present invention can be implemented through the image processing apparatus 100 described above. Figure 3 is a flowchart of an image processing method according to an embodiment of the present invention.

Referring to Figure 3, first, the original image of the object is acquired (S100). As described above, the original image may be acquired by the image acquisition unit 120 of the image processing device 100.

Here, the acquired image will be the object image before editing by the user.

Next, object editing is performed by the user (S110). As described above, the user can change the color, size, or any other visual attribute of the original object through the editing interface.

When an object is edited by a user on the original image, a 2D image and a UV map image for the original image are acquired (S120). For convenience, this is referred to as the editing image acquisition step (S120). As described above, 2D images and UV map images may also be acquired by the image acquisition unit 120.

Here, the user can determine a predetermined location where the image is acquired. For example, when the object is an avatar face and the user wants to modify the makeup of the avatar's face and wants to modify the makeup based on the front of the face, an image of the front of the face can be obtained.

Meanwhile, when the user wants to edit to add a cheek touch to the right side of the avatar's face (based on the displayed screen), an image of the side of the face viewed from 45 degrees on the right can be obtained, and conversely, a cheek touch to the left side of the avatar's face can be obtained. When you want to edit to add, you can obtain an image of the side of the face viewed from 45 degrees to the left.

To this end, the editing interface can provide a function to display a 3D object by rotating it to an angle desired by the user.

Meanwhile, a texture map is generated (S130) in parallel with the editing image acquisition step (S120). The texture map represents the texture of an object with respect to the original image, and is performed after the original image acquisition step (S100), and can be performed in parallel with the edited image acquisition step (S120) without any separate precedence relationship.

Next, pixel information is collected from the acquired 2D image and UV map image (S140). Specifically, the pixel information extraction unit 140 extracts pixel color information for a pixel at predetermined coordinates (x, y) from the 2D image, and extracts pixel color information for a pixel at the same coordinates (x, y) from the UV map image. Extract pixel UV information.

Here, pixel color information obtained from the 2D image includes RGB information, and pixel information obtained from the UV map image includes UV coordinate information.

In addition, the pixel information extraction unit 140 uses pixel UV information for predetermined coordinates in the UV map image obtained in the edited image acquisition step (S120) to extract the original texture map generated in the texture map generation step (S140). In , pixel color information for a pixel with (u,v) coordinates corresponding to the corresponding pixel UV information is collected.

Next, the corrected texture map to be applied to the actual 3D model is modeled (S150). The corrected texture map is modeled in the modeling unit 150 using 2D image information, UV map image information, and texture map information.

Specifically, the modeling unit 150 collects pixel color information of predetermined coordinates (x, y) extracted from the 2D image collected in the pixel information collection step (S140) and predetermined coordinates (x, y) extracted from the UV map image. The pixel color information on the texture map with the corresponding UV coordinates is compared with the pixel UV information of y), and if the two are different, the pixel color information of the given coordinates (x, y) extracted from the 2D image is added to the actual 3D model. Determine the information to be mapped.

This is a series of operations performed on specific pixels of the object image. By repeating the process for all pixels, the modeling unit 150 can generate a final texture map to be mapped to the actual model.

Once the final texture map to be mapped to the actual model is created, UV mapping is performed using it to synthesize a 3D object image (S160).

Next, with reference to FIG. 4, an embodiment to which the above invention is applied will be described.

In this example, the user adds makeup corresponding to the cheek touch area in the avatar's face image (no cheek touch).

Referring to the drawing, (a) is a 2D image for the object edited by the user, (b) is a UV map image for the object, and (c) is a texture map for the original image before editing by the user. .

First, the image acquisition unit 120 acquires the original image of the object. This is an object image before editing by the user, and in this embodiment, it will be an avatar face image without cheek touch makeup.

Next, the user performs object editing to add cheek touch makeup through the editing interface.

When editing is performed by the user, the image acquisition unit 120 acquires a 2D image and a UV map image for the edited object. At this time, the user can determine a predetermined location where the image is acquired. The embodiment of FIG. 4 explains a case where a user obtains an image of the front of the face.

The images obtained in this way are shown in FIG. 4, where (a) is a 2D image for the edited object and (b) is a UV map image for the object.

In parallel with the image acquisition step, the texture map generator 130 creates a texture map using the original image. In the drawing, (c) shows a texture map created from the original image before user editing. Therefore, there is no cheek touch makeup in (c).

Next, pixel information is collected from the acquired 2D image (a) and UV map image (b). Referring to the drawing, pixel color information is extracted for a pixel at predetermined coordinates (x, y) from the 2D image (a), which corresponds to rgb (214, 177, 208) in this embodiment.

Next, from the UV map image of FIG. 4B, UV information is extracted for a pixel having the same coordinates (x, y) as the pixel from which pixel color information was extracted from the 2D image. In this example, the UV coordinates of the corresponding pixel correspond to (0.2, 0.4).

When pixel UV information is collected from the UV map image, pixel color information for the pixel with the corresponding UV coordinates (0.2, 0.4) is collected on the texture map (c) for the original image.

Next, the pixel color information of the 2D image (a) is compared with the pixel color information of the texture map (c) for the original image, and if the two are different, the pixel at predetermined coordinates (x, y) extracted from the 2D image Color information is determined as information to be mapped to the actual 3D model.

As described above, the corrected texture map to be applied to the actual 3D model is modeled, and the process is repeated for all pixels to generate the final texture map to be mapped to the actual model.

Once the final texture map to be mapped to the actual model is created, UV mapping is performed using it to synthesize a 3D object image.

In the above manner, according to the present invention, editing of a 3D object by a user can be reflected and output in real time.

Meanwhile, Figure 5 is a diagram of an embodiment in which a user adds right cheek touch makeup. The difference from the embodiment of FIG. 4 is that, rather than acquiring an image of the front of the face, an image observed from a 45-degree angle on the right side of the face is acquired. The rest of the process is the same, so redundant explanations will be omitted.

The embodiments described above may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., singly or in combination. Program instructions recorded on the medium may be specially designed and configured for the embodiment or may be known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CDROMs and DVDs, and magneto-optical media such as floptical disks. Includes magneto-optical media, and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, etc. Examples of program instructions include machine language code, such as that produced by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa. 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. Software and/or data may be used on any type of machine, component, physical device, virtual equipment, computer storage medium or device to be interpreted by or to provide instructions or data to a processing device. , or may be permanently or temporarily embodied in a transmitted signal wave. 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.

Although the embodiments have been described with limited drawings as described above, those skilled in the art can apply various technical modifications and variations based on the above. 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 following claims.

Claims

An image processing method that facilitates editing of three-dimensional (3D) objects by a user, comprising:

Obtaining an original image of a 3D object;

object editing step;

An editing image acquisition step of acquiring a 2D image and a UV map image for the edited object;

Performed in parallel with the edited image acquisition step, generating an original texture map for the original image;

collecting pixel information from the 2D image and the UV map image;

Modeling a corrected texture map to be applied to an actual 3D model using the 2D image pixel information, the UV map image pixel information, and the texture map information; and

An image processing method comprising performing UV mapping using the corrected texture map.
According to paragraph 1,

The object editing step is performed according to a user editing command input through an editing interface,

An image processing method wherein the user can set a predetermined location where the edited image is obtained using the editing interface.
The method of claim 1, wherein the image processing method:

An image processing method characterized by modeling the corrected texture map and outputting a mapped 3D model in real time through the output unit.
The method of claim 1, wherein collecting pixel information from the 2D image and the UV map image comprises:

Collecting pixel color information at predetermined coordinates from the 2D image, and collecting pixel UV information at the same coordinates as the predetermined coordinates from the UV map image,

An image processing method comprising collecting pixel color information having UV coordinates corresponding to the pixel UV information from the original texture map.
According to clause 4,

Comparing the pixel color information collected from the 2D image and the pixel color information collected from the original texture map, and if the two are different, determining the pixel color information collected from the 2D image as information to be mapped to the actual 3D model Featured image processing method.
An image processing device that facilitates three-dimensional (3D) object editing by the user,

a user interface unit including an input unit and an output unit including an editing interface that supports the user's editing of 3D objects;

an image acquisition unit that acquires a 2D image and a UV map image for the original 3D object image displayed on the output unit;

a texture map generator that generates an original texture map by expanding the original 3D object image in a two-dimensional UV space;

a pixel information extraction unit that extracts pixel information of predetermined coordinates from the image acquired by the image acquisition unit;

a modeling unit that models a corrected texture map to be applied to an actual 3D model using the 2D image, the UV map image, and the original texture map; and

An image processing device comprising a UV mapping unit that maps the corrected texture map to a 3D model.
The method of claim 6, wherein the editing interface is:

An image processing device characterized in that it supports the user to set a predetermined position where the edited image acquired by the image acquisition unit is obtained when editing an object.
According to clause 6,

The output unit models the corrected texture map and outputs a mapped 3D model in real time.
The method of claim 6, wherein the pixel information extractor,

Collecting pixel color information at predetermined coordinates from the 2D image, collecting pixel UV information at the same coordinates as the predetermined coordinates from the UV map image, and having UV coordinates corresponding to the pixel UV information in the original texture map. An image processing device characterized by collecting pixel color information.
The method of claim 6, wherein the modeling unit,

Compare the pixel color information collected from the 2D image and the pixel color information collected from the original texture map, and if the two are different, correct by determining the pixel color information collected from the 2D image as information to be mapped to the actual 3D model. An image processing device characterized by modeling a texture map.