JP2018148525A - Virtual three-dimensional object generation device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a technique for generating a virtual three-dimensional object for three-dimensionally displaying a subject, which can easily recognize a size of the subject.SOLUTION: A virtual three-dimensional object generation device is a device configured to generate a virtual three-dimensional object for three-dimensionally displaying a subject. The virtual three-dimensional object generation device comprises: an image acquisition part; a size acquisition part; and a subject generation part. The image acquisition part is configured to acquire a plurality of picked-up images obtained by imaging the subject from a plurality of different angles in S110. The size acquisition part is configured to acquire size information for specifying a size of the subject in S130. The subject generation part is configured to generate the virtual three-dimensional object of the subject to which the size of the subject is made to correspond, on the basis of the plurality of picked-up images and the size information in S140 and S170.SELECTED DRAWING: Figure 2

Description

  The present disclosure relates to a technique for generating a virtual three-dimensional object for displaying a subject three-dimensionally.

  Patent Document 1 below proposes a technique for displaying a subject in a three-dimensional manner, such as displaying an object such as an exhibit as if it is rotating.

JP 2014-042655 A

  By the way, as in the technique of Patent Document 1, when a subject is generally displayed as an image, it is difficult to recognize the size of the subject. One aspect of the present disclosure is preferably configured to easily recognize the size of a subject in a technique for generating a virtual three-dimensional object for displaying a subject three-dimensionally.

  The virtual three-dimensional object generation device according to one aspect of the present disclosure is an apparatus configured to generate a virtual three-dimensional object for displaying a subject three-dimensionally. The virtual three-dimensional object generation device includes an image acquisition unit, a size acquisition unit, and a subject generation unit.

  The image acquisition unit is configured to acquire a plurality of captured images obtained by imaging the subject from a plurality of different angles. The size acquisition unit is configured to acquire size information for specifying the size of the subject.

The subject generation unit is configured to generate a virtual three-dimensional object for a subject associated with the size of the subject based on a plurality of captured images and size information.
According to such a virtual three-dimensional object generation device, a virtual three-dimensional object is generated for a subject associated with the size of the subject based on a plurality of captured images and size information, so that the size of the subject is recognized. It can be made easier.

  Moreover, the virtual three-dimensional object generation device according to one aspect of the present disclosure may include a member acquisition unit and a covering generation unit. The member acquisition unit is configured to acquire member information including at least the appearance and dimensions of the covering member that represents a member that can cover at least a part of the subject. The covering generation unit is configured to generate a covering solid object representing a virtual three-dimensional object in which the covering member is arranged along the surface of the subject three-dimensional object based on the member information.

According to such a virtual three-dimensional object generation device, it is possible to represent a state in which at least a part of a subject is covered with a covering member with a virtual three-dimensional object.
Further, in the virtual three-dimensional object generation device according to one aspect of the present disclosure, the member acquisition unit acquires, as member information, expansion / contraction information representing information related to expansion / contraction of the covering member, in addition to the appearance and dimensions of the covering member, The unit may be configured to generate a covered three-dimensional object arranged along the surface of the subject three-dimensional object by expanding and contracting the covering member in consideration of expansion / contraction information.

  According to such a virtual three-dimensional object generation device, the covering member is expanded and contracted to generate the covering three-dimensional object arranged along the surface of the subject three-dimensional object. 3D objects can be generated.

1 is a block diagram showing a configuration of a virtual try-on system 1. FIG. It is a flowchart of a three-dimensional image generation process. It is a top view which shows the method of obtaining the captured image used as the basis of a stereo image. It is the side view and sectional drawing which show a stereo image. It is a flowchart of a clothing image generation process. It is explanatory drawing (the 1) which shows an example of member information. It is explanatory drawing (the 2) which shows an example of member information. It is explanatory drawing (the 1) which shows the process which matches the image of clothes, and a coordinate. It is explanatory drawing (the 2) which shows the process which matches the image of clothes, and a coordinate. It is explanatory drawing (the 1) which shows the position alignment in the process which produces | generates a clothing image. It is explanatory drawing (the 2) which shows the position alignment in the process which produces | generates a clothing image. It is a flowchart of a displacement image generation process. It is explanatory drawing which shows an example of the operation | movement at the time of producing | generating a displacement image. It is a flowchart of a terminal process. It is a flowchart of the clothing image generation process in other embodiment. It is a flowchart of a coordination process.

Hereinafter, embodiments of the present disclosure will be described with reference to the drawings.
[1. Embodiment]
[1-1. Constitution]
The virtual try-on system 1 shown in FIG. 1 generates a three-dimensional mannequin that is a virtual three-dimensional object for a user who is the subject of the system 1, and causes the three-dimensional mannequin to try on a virtual arbitrary garment. Have That is, the virtual try-on system 1 is a system that supports purchase of clothes by a user by giving a specific image when the subject wears clothes.

  The virtual try-on system 1 includes a server 10 and databases 31 and 32. The virtual try-on system 1 may include one or a plurality of terminal devices 40. Although only one terminal device 40 is illustrated in FIG. 1, another terminal device 40 having the same configuration may be provided.

  The server 10 is configured to be able to read and write data in the databases 31 and 32, and with one or a plurality of terminal devices 40 via the Internet network 5, a mobile phone base station 7, a wireless LAN access point 9, and the like. It is configured to be communicable. The hardware configuration of the server 10 is the same as that of a general server.

  The databases 31 and 32 include a product DB 31 and a subject DB 32. The product DB 31 is a database that stores data related to a large number of products. As will be described later, the data related to the product includes information such as the appearance of the product such as clothes, the dimensions of each part of the product, and the expansion and contraction rate of the product.

The subject DB 32 is a database that stores information on a large number of subjects for each subject. Information on the subject will be described later.
Each terminal device 40 is a communication device such as a smartphone or a tablet terminal possessed by a large number of users. The terminal device 40 is configured to be able to communicate with the server 10 by being connected to the base station 7 and the access point 9.

  The server 10 and the terminal device 40 are mainly configured by known microcomputers having CPUs 11 and 41 and semiconductor memories (hereinafter, memories 12 and 42) such as RAM, ROM, and flash memory. Various functions of the server 10 and the terminal device 40 are realized by the CPUs 11 and 41 executing programs stored in a non-transitional physical recording medium. In this example, the memories 12 and 42 correspond to non-transitional tangible recording media storing programs.

  Also, by executing this program, a method corresponding to the program is executed. Note that the non-transitional tangible recording medium means that the electromagnetic waves in the recording medium are excluded. Further, the number of microcomputers constituting the server 10 and the terminal device 40 may be one or plural.

  The server 10 includes a stereoscopic image generation unit 16, a clothing image generation unit 17, and a displacement image generation unit 18 as functional configurations realized by the CPU 11 executing the program. The terminal device 40 includes a display control unit 46 as a function configuration realized by the CPU 41 executing the program.

  The method of realizing these elements constituting the server 10 and the terminal device 40 is not limited to software, and some or all of the elements may be realized using one or a plurality of hardware. For example, when the above function is realized by an electronic circuit that is hardware, the electronic circuit may be realized by a digital circuit including a large number of logic circuits, an analog circuit, or a combination thereof.

  In the server 10, the function as the stereoscopic image generation unit 16 generates user data by performing a stereoscopic image generation process to be described later, and generates a stereoscopic image of the subject based on the user data. The user data represents a subject solid object and a subject solid coordinate group.

  The subject three-dimensional object represents image data for displaying the subject in three dimensions. The subject three-dimensional object may be provided with coordinates of vertices when each part of the subject is represented by a rectangular parallelepiped, a cylinder, or the like, a parameter indicating the shape of a link connecting the coordinates, and the like. Specifically, the subject three-dimensional object may be configured as data equivalent to three-dimensional CAD data.

  The subject three-dimensional coordinate group represents information as a coordinate group in which a large number of parts on the surface of the subject are represented by coordinate values. That is, the subject three-dimensional coordinate group is not limited to the coordinates of the vertices but is data including the coordinates of the parts between them.

  The function as the clothing image generation unit 17 generates a clothing image by performing a clothing image generation process described later. A clothing image represents an image in a state where a user virtually wears clothing.

  The function as the displacement image generation unit 18 generates a displacement image by performing a displacement image generation process described later. A displacement image represents an image when a clothing image is displaced, such as by extending or contracting an arm in accordance with an external command.

The server 10 further includes a communication unit 19. The communication unit 19 is configured as a known communication module for performing communication via the base station 7 or the access point 9.
Next, in the terminal device 40, the function as the display control unit 46 performs terminal processing described later, thereby exchanging data with the server 10 and displaying a display image to be provided to the subject.

  The terminal device 40 further includes an imaging unit 47, a display unit 48, an operation detection unit 49, and a communication unit 50. The imaging unit 47 is configured as a known imaging device that images an object around the terminal device 40. In the present embodiment, the imaging unit 47 is used to obtain an image of a subject.

  The display unit 48 is configured as a known display. For example, a clothing image is displayed on the display unit 48. The motion detection unit 49 is configured as a known motion sensor that detects a force applied to the terminal device 40. The motion detection unit 49 is configured by combining, for example, a gyro, an acceleration sensor, a yaw rate sensor, and the like, and is used to detect how the subject in the state with the terminal device 40 moves.

The communication unit 50 is configured as a known communication module for performing communication via the Internet network 5.
[1-2. processing]
[1-2-1. Stereoscopic image generation processing]
A stereoscopic image generation process executed by the server 10 will be described with reference to the flowchart of FIG. First, in S110, the server 10 acquires image information.

  As shown in FIG. 3, the image information acquired here includes captured images obtained by capturing an image of a subject using the imaging unit 47 of the terminal device 40 from a plurality of directions. The image may be captured by a technique in which the subject rotates once in the horizontal direction while the imaging unit 47 captures a moving image including a plurality of frames.

  Subsequently, in S120, the server 10 detects the angle of the subject for each image. In this process, the angle may be detected from the orientation of the reference portion of the subject in advance. For example, when the subject is a person, the direction of the subject in the horizontal direction is recognized for each image in consideration of the orientation of the face of the subject, the orientation of the toes, the orientation of the shoulders, and the like. For example, the angle at which the subject rotates clockwise with respect to the front of the subject is detected.

  Subsequently, in S130, the server 10 extracts a reference object used when specifying the size of the subject from at least one of the plurality of captured images. The size of the subject represents a dimension at an arbitrary part of the subject. The size of the subject corresponds to, for example, the full length, the full width, the circumference, and the like.

  The reference object represents an object serving as a reference for size. The reference object corresponds to an object whose dimensions are standardized and known, such as a beverage can, a book, and newspaper. In this process, an object existing at a distance similar to the subject is extracted as a reference object.

  However, it is not necessary to obtain information on the reference object from the image. The server 10 may separately acquire information on the dimensions of the subject, such as the height of the subject, the length of the face, and the distance between both eyes, as a reference object.

  Subsequently, in S140, the server 10 associates the length with each part of the subject by comparing the size of the reference object with the size of the subject. Specifically, it calculates how many pixels the reference object having a known length occupies in the vertical and horizontal directions in the image, and calculates the length per pixel for each direction. Then, the size of each part is obtained depending on how many pixels each part of the subject occupies. At this time, when the distance from the imaging unit 47 to the subject and the distance from the imaging unit 47 to the reference object are different, the dimensions of the respective units may be corrected according to the difference in distance.

  Subsequently, in S150, the server 10 generates a stereoscopic image of the subject. A stereoscopic image is obtained by cutting out a portion of a subject from captured images captured at a number of angles and continuously joining the appearance at each angle to obtain a three-dimensional virtual three-dimensional object. This three-dimensional object corresponds to the subject three-dimensional object described above. An image when this three-dimensional object is viewed from an arbitrary angle is defined as a subject image.

  Subsequently, in S170, the server 10 associates coordinates with the subject three-dimensional object. In this process, by associating the coordinates of the surface of the subject three-dimensional object, a coordinate group indicating the subject associated with the coordinates corresponding to the size of the subject is generated.

  This coordinate group corresponds to the subject solid coordinate group described above. Specifically, as shown in FIG. 4, for the subject three-dimensional object 65, for example, a cross-sectional view is obtained for each unit length in the vertical direction (for example, about 1 cm of height), and the object is detected for each cross-sectional view. The coordinates indicating the surrounding positions are associated as the coordinates of the subject three-dimensional object 65.

  In the case of the example shown in FIG. 4, the coordinates of the periphery of the body part and the periphery of the arm and foot parts are extracted. At this time, in the cross-sectional view, a mesh is prepared in which squares each having a side length of 1 cm or the like are arranged vertically and horizontally, and each of the intersections of the sides of these squares and the surroundings in the cross-sectional view is prepared. The coordinate value should be obtained for.

  Subsequently, in S180, the server 10 records the subject three-dimensional object and the subject three-dimensional coordinate group in the subject DB 32 as user data related to the subject, and then ends the three-dimensional image generation process of FIG. In this process, it is preferable to recognize and record the positions of joints such as the neck, limbs and waist. The position of the joint may be specified for each subject from the appearance of the subject, or an average joint position of many subjects may be adopted.

[1-2-2. Clothing image generation processing]
Next, clothing image generation processing executed by the server 10 will be described with reference to the flowchart of FIG.

  First, in S210, the server 10 acquires product designation information. The product designation information represents information for specifying the product selected by the user. For example, a product number corresponds to the product designation information. The product designation information is transmitted to the server 10 by the terminal process described later by the terminal device 40.

  Subsequently, in S220, the server 10 acquires member information. The member information represents data related to the above-described product. The member information is acquired from the product DB 31. For example, when the upper garments 71 and 72 as shown in FIGS. 6 and 7 are selected as products, the member information includes information such as the appearance of the product such as clothes, the dimensions of each part, and the expansion / contraction rate. The appearance of the product includes at least the stomach side and the back side of the clothes.

  As the expansion / contraction rate, a value set in advance for each material of clothing may be used. Further, the actual expansion / contraction rate may be measured for each piece of clothing or for each material of the clothing, and the value may be adopted. In order to measure the expansion / contraction rate of clothes, for example, as shown in FIG. 8, a checkered clothes whose dimensions of one grid are known are prepared, and apexes of a plurality of grids are set as a plurality of reference points. . For example, in the example shown in FIG. 8, P10, P20, P30, P40, etc. are used as reference points.

  Then, how the distance between the plurality of reference points changes when the model actually wears the garment is measured. In the example shown in FIG. 9, the reference points P10, P20, P30, P40, etc. are moved to P11, P21, P31, P41, etc., and the lattice is distorted, so that there is a distortion between the reference points P11, P21, P31, P41. It can be seen that the distance is changing. The change rate at this time may be adopted as the expansion / contraction rate in each direction such as the vertical direction and the horizontal direction.

  Subsequently, in S230, the server 10 acquires user data. Here, the user data represents data about a user who has transmitted the product designation information among a large number of subject solid coordinate groups stored in the subject DB 32.

  Subsequently, in S240, the server 10 combines the coordinate positions. In this process, as shown in FIG. 10, the process of arranging clothes coordinates is performed according to the coordinates indicated by the subject solid coordinate group. In addition, about clothing, for example, one or a plurality of parts which became a ring in the clothing is virtually cut and developed into one cloth shape, and coordinate values are associated with each part.

  However, the virtually cut portions are associated with each other so that the cut portions can be joined later. Also, when associating coordinate values with each part of clothes, as in the process of S170 described above, a mesh is prepared in which squares in which the length of one side of the clothes is set to a unit length such as 1 cm are arranged vertically and horizontally. A coordinate value may be obtained for each of the intersections between the sides of the square and the periphery in the cross-sectional view. Further, when the product includes a pattern or a character, the positional relationship with the pattern or the character is associated with the coordinate value.

  10 and 11, preset user reference positions F10 and F20 among the coordinates of the surface of the subject three-dimensional object 65, and a preset clothing reference position F11 among the coordinate values of clothes. , F21 are aligned so that at least one set of the positions matches. Note that the user reference positions F10 and F20 and the clothes reference positions F11 and F21 are positions that are associated with each other, and the positional relationship between the body part and the clothes part changes even if clothes that do not match the body shape are worn. It is set at a position where it is difficult to do.

  Starting from the clothes reference positions F11 and F21, the coordinate values of the clothes are arranged in order along the surface of the subject solid object 65 indicated by the coordinates of the user data so that the distance between the plurality of coordinates indicating the clothes does not change. A coordinate group is obtained for the clothes in a state that does not consider expansion and contraction. Let this coordinate group be a covering solid coordinate group. In addition, when the circumference | surroundings length of clothes is insufficient in this coating | coated solid coordinate group, it is good to leave the virtually cut | disconnected site | parts not mutually joined.

  Subsequently, in S250, the server 10 corrects the surface position. In this process, when the peripheral length of the clothes remains in the cover solid coordinate group, for example, the clothes may be left in a state where the clothes are not left by moving the clothes coordinates from the coordinates of the user data to the outer peripheral side as a whole. .

  Subsequently, in S260, the server 10 corrects the coordinates based on the expansion / contraction rate. In this process, in the vertical direction in the covering solid coordinate group, that is, the vertical direction, the coordinate value is moved with respect to the clothes reference positions F11 and F21 according to the set expansion / contraction ratio. This is because it is affected by gravity.

  Further, in the horizontal direction in the covering solid coordinate group, that is, in the horizontal direction, it is not necessary to expand and contract when the peripheral length of the clothes remains. In this case, it means that the subject can wear clothes comfortably.

  Further, when the length of the circumference of the clothes is insufficient, the clothes are stretched / contracted so as to conform to the shape of the periphery of the stereoscopic image of the subject, with the lateral expansion / contraction rate as the upper limit. Thus, a covered solid coordinate group corrected in consideration of expansion and contraction is obtained.

  Further, if the perimeter of the garment is insufficient even when the upper limit value of the expansion / contraction rate is adopted, a flag indicating that the clothing cannot be worn is set in the memory 12. In this case, it means that the subject cannot physically wear the selected clothes.

  Subsequently, in S270, the server 10 generates a covered solid object based on the corrected covered solid coordinate group. The covered three-dimensional object represents image data for displaying clothes in three dimensions. Similar to the subject three-dimensional object, the covered three-dimensional object only needs to include coordinates of vertices when each part of the clothes is represented by a rectangular parallelepiped, a cylinder, or the like, a parameter indicating the shape of a link connecting the coordinates, and the like.

  Subsequently, in S280, the server 10 outputs the clothing image and records the clothing image in the product DB 31, and then ends the clothing image generation processing of FIG. The clothing image is an image of a three-dimensional object in which a subject three-dimensional object is partially covered with a covering three-dimensional object when viewed from an arbitrary direction.

  In the process of S280, instead of the clothing image, a cover image representing an image of only the clothing at the time of clothing or the above-described subject image may be output in accordance with a command selected by the user. In addition, when a flag indicating that clothing is not possible is set, for example, in a clothing image, a virtually cut portion may not be joined, or red or flashing display may be displayed in the image. It may be shown that it is not possible to wear clothes.

[1-2-3. Displacement image generation processing]
Next, displacement image generation processing executed by the server 10 will be described with reference to the flowchart of FIG.

  First, in S310, the server 10 determines whether or not operation information has been received. The action information represents information serving as an instruction for displacing the clothing image. The operation information includes, for example, an operation of sliding the hand portion upward on the display unit 48 on which the wearing image is displayed. When such an operation is performed on the terminal device 40, the terminal device 40 determines that an instruction to generate a clothing image with a hand raised is input, and outputs that the hand is raised as operation information.

  Further, the operation information may be obtained from an image obtained by actually capturing a subject. For example, as illustrated in FIG. 13, when a subject with his hand raised is imaged by the imaging unit 47 of the terminal device 40, the fact that the hand has been raised may be output as operation information.

  Further, the motion information may be obtained from the detection result by the motion detection unit 49. For example, the motion detection unit 49 can detect motions such as shaking the terminal device 40, turning the terminal device 40, and moving the terminal device 40 up and down or left and right. May be associated in advance. For example, if an operation of shaking the terminal device 40 is associated with a state where the subject raises his hand, an instruction to generate a clothing image with his hand raised by shaking the terminal device 40 is input. Can do.

  If the server 10 determines in S310 that the motion information has not been received, the displacement image generation process in FIG. 12 ends. On the other hand, if the server 10 determines that the motion information has been received in S310, the server 10 proceeds to S320 and generates a subject three-dimensional object corresponding to the motion. That is, as shown in FIG. 13, if movement information indicating that the hand is raised is received, the movement amount for each part of the body is calculated according to the coordinates of the joints and the content of the movement, and the subject three-dimensional object is A new object three-dimensional object is obtained by deformation.

At this time, the obtained dimensions are maintained for the parts other than the movable part of the joint, and only the joint part is moved around the support point of the joint regardless of the obtained dimensions.
Subsequently, in S330, the server 10 associates coordinates with the subject three-dimensional object. In this process, the same process as that of S150 is performed.

  Subsequently, in S340, the server 10 sequentially performs the processes of S240 to S280 in the clothing image generation process, and then ends the displacement image generation process of FIG. That is, as shown in FIG. 13, a covered three-dimensional object is created according to the subject three-dimensional object 65 displaced according to the motion information, and a clothing image is generated from these three-dimensional objects. Then, this clothing image can be displayed on the display unit 48.

[1-2-4. Terminal processing]
Next, terminal processing executed by the terminal device 40 will be described using the flowchart of FIG. The terminal process is a process performed by the terminal device 40 in response to the above-described stereoscopic image generation process, clothing image generation process, and displacement image generation process.

  First, in S410, the terminal device 40 determines whether an image of the subject has been captured. The image here corresponds to a plurality of images obtained by imaging the subject from a plurality of directions. If the terminal device 40 determines in S410 that an image of the subject has been captured, the terminal device 40 proceeds to S420, and transmits the captured image to the server 10 as image information.

  On the other hand, if the terminal device 40 determines in S410 that an image of the subject has not been captured, the terminal device 40 proceeds to S430 and determines whether or not a product has been selected. If the terminal device 40 determines that the product has been selected in S430, the terminal device 40 proceeds to S440 and transmits the product selection information to the server 10.

  On the other hand, if it is determined in S430 that no product has been selected, the terminal device 40 proceeds to S450 and determines whether a clothing image has been received. If the terminal device 40 determines that the clothing image has been received in S450, the terminal device 40 proceeds to S460, and displays the clothing image on the display unit 48.

  Subsequently, in S470, the terminal device 40 determines whether an operation is detected. If the terminal device 40 determines that the operation is not detected in S470, the terminal device 40 returns to S470. On the other hand, if it is determined that the operation is detected in S470, the terminal device 40 proceeds to S480, transmits the operation information to the server 10, and then returns to S450. The operation information includes information for instructing what operation the user has performed or how to displace the clothing image.

  On the other hand, if it is determined that the clothing image has not been received in S450, the terminal device 40 determines whether or not to end the display of the clothing image in S490. Whether or not to end the display is determined by an instruction from the user.

  If it is determined that the terminal device 40 does not end in S490, the terminal device 40 returns to S410. On the other hand, if the terminal device 40 determines to end in S490, it ends the terminal processing of FIG.

[1-3. effect]
According to the first embodiment described in detail above, the following effects are obtained.
(1a) The virtual try-on system 1 described above is configured to generate a virtual three-dimensional object for displaying a subject three-dimensionally, and includes the function of the three-dimensional image generation unit 16. The function of the stereoscopic image generation unit 16 is configured to acquire a plurality of captured images obtained by imaging the subject from a plurality of different angles. The function of the stereoscopic image generation unit 16 is configured to acquire size information for specifying the size of the subject. In addition, the function of the stereoscopic image generation unit 16 is configured to generate a virtual three-dimensional object for a subject associated with the size of the subject based on a plurality of captured images and size information.

  According to such a virtual try-on system 1, a virtual three-dimensional object is generated for a subject associated with the subject size based on a plurality of captured images and size information, so that the size of the subject can be easily recognized. can do.

  (1b) The virtual try-on system 1 includes the function of the clothing image generation unit 17. The function of the clothing image generation unit 17 is configured to acquire member information including at least the appearance and dimensions of the covering member that represents a member that can cover at least a part of the subject. In addition, the function of the clothing image generation unit 17 is configured to generate a covered three-dimensional object representing a virtual three-dimensional object in which a covering member is disposed along the surface of the subject three-dimensional object based on the member information.

According to such a virtual try-on system 1, it is possible to represent a state when a subject is covered with a covering member as a stereoscopic image.
(1c) In the virtual try-on system 1 described above, in the function of the clothing image generation unit 17, in addition to the appearance and dimensions of the covering member, expansion / contraction information representing information regarding expansion / contraction of the covering member is acquired as member information. In consideration of the above, the covering member is expanded and contracted to generate a covering solid object arranged along the surface of the subject solid object.

  According to such a virtual try-on system 1, the covering member is expanded and contracted to generate a covering three-dimensional object arranged along the surface of the subject three-dimensional object. Therefore, when the covering member expands and contracts, a stereoscopic image considering expansion and contraction is generated. Can be generated.

[2. Other Embodiments]
As mentioned above, although embodiment of this indication was described, this indication is not limited to the above-mentioned embodiment, and can carry out various modifications.

  (2a) In the above embodiment, the clothes selected by the user are virtually tried on each time, but the present invention is not limited to this. For example, when another user who already has a similar body shape tries on similar clothes, the image may be provided.

  Specifically, a modification image generation process executed by the server 10 will be described with reference to the flowchart of FIG. First, the server 10 performs the processes of S210 to S230 described above.

  Subsequently, in S610, the server 10 determines whether a similar clothing image exists. A similar clothing image refers to a clothing image of similar clothing by another user having a body shape similar to the user. The clothing image may be an actually captured image, or an image obtained by performing a clothing image generation process on another user.

  If the server 10 determines in S610 that a similar clothing image does not exist, the server 10 performs the processing of S240 to S260, and then performs the processing of S280, and then ends the clothing image generation processing of FIG.

  On the other hand, if the server 10 determines in S610 that a similar clothing image exists, the server 10 proceeds to S620 and acquires a similar clothing image. Subsequently, in S630, the server 10 performs a correction suitable for the user, and then performs the process of S280, and then ends the clothing image generation process of FIG. The appropriate correction may include, for example, a correction that changes the face of another user to the user's face or makes fine adjustments to the body shape.

According to such a virtual try-on system, the already generated clothing image can be used effectively.
(2b) In the above embodiment, only the clothes selected by the user are virtually tried on, but the present invention is not limited to this. For example, in addition to the clothes selected by the user, clothes recommended by the manager of the server 10 such as a store may be virtually tried on.

  Specifically, the coordination process executed by the server 10 will be described with reference to the flowchart of FIG. First, in S710, the server 10 extracts corresponding products. The corresponding product represents a product set in advance as a product corresponding to the selected product. For example, as shown in FIG. 6 and FIG. 7, corresponding products are set in advance for the products. The upper garments as shown in FIGS. 6 and 7 are associated with clothes that can be worn simultaneously with the selected clothes such as trousers, bags, accessories, and the like as corresponding products.

  Subsequently, in S720, the server 10 performs the processing of S220 to S280 of the clothing image generation processing for the selected product and the corresponding product. Subsequently, in S730, the server 10 outputs the clothing image including the corresponding product, and then ends the coordination process of FIG.

According to such a virtual try-on system, it is possible to provide a clothing image that is tried on not only on the product selected by the user but also on the product recommended by the administrator.
(2c) In the above embodiment, an example in which the subject is a person has been described, but the subject can be arbitrarily applied. For example, a vehicle such as a passenger car may be applied as the subject, and a protective cover that covers the vehicle may be applied as the covering member.

  (2d) In the embodiment described above, the server 10 performs the stereoscopic image generation process, the clothing image generation process, the displacement image generation process, and the coordination process, but these processes may be performed by the terminal device 40. Even if it does in this way, the effect similar to the said embodiment can be enjoyed substantially.

  (2e) A plurality of functions of one constituent element in the above embodiment may be realized by a plurality of constituent elements, or a single function of one constituent element may be realized by a plurality of constituent elements. . Further, a plurality of functions possessed by a plurality of constituent elements may be realized by one constituent element, or one function realized by a plurality of constituent elements may be realized by one constituent element. Moreover, you may abbreviate | omit a part of structure of the said embodiment. Further, at least a part of the configuration of the above embodiment may be added to or replaced with the configuration of the other embodiment. In addition, all the aspects included in the technical idea specified from the wording described in the claims are embodiments of the present disclosure.

  (2f) In addition to the virtual try-on system 1 described above, non-transitional devices, such as a device serving as a component of the virtual try-on system 1, a program for causing a computer to function as the virtual try-on system 1, and a semiconductor memory storing the program The present disclosure can also be realized in various forms such as an actual recording medium, a virtual fitting method, or a virtual three-dimensional object generation method.

[3. Correspondence between Configuration of Embodiment and Configuration of Present Disclosure]
In the embodiment described above, the virtual try-on system 1 corresponds to an example of a virtual three-dimensional object generation device as referred to in the present disclosure. In addition, the process of S110 among the processes executed by the server 10 in the above embodiment corresponds to an example of an image acquisition unit referred to in the present disclosure, and the process of S130 in the above embodiment is an example of a size acquisition unit referred to in the present disclosure. Equivalent to. In the above embodiment, the processes of S140 and S170 correspond to an example of a subject generation unit referred to in the present disclosure, and the process of S220 in the above embodiment corresponds to an example of a member acquisition unit referred to in the present disclosure. Moreover, in the said embodiment, the process of S240, S250, S260 is equivalent to an example of the coating | coated production | generation part said by this indication.

  DESCRIPTION OF SYMBOLS 1 ... Virtual try-on system, 5 ... Internet network, 7 ... Base station, 9 ... Access point, 10 ... Server, 11 ... CPU, 12 ... Memory, 16 ... Three-dimensional image generation part, 17 ... Clothes image generation part, 18 ... Displacement Image generation unit, 19 ... communication unit, 31 ... product DB, 32 ... subject DB, 40 ... terminal device, 41 ... CPU, 42 ... memory, 46 ... display control unit, 47 ... imaging unit, 48 ... display unit, 49 ... Motion detection unit, 50 ... communication unit, 65 ... three-dimensional object, 71 ... upper garment.

Claims (3)

A virtual three-dimensional object generation device configured to generate a virtual three-dimensional object for displaying a subject three-dimensionally,
An image acquisition unit configured to acquire a plurality of captured images obtained by imaging a subject from a plurality of different angles;
A size acquisition unit configured to acquire size information for specifying the size of the subject;
A subject generation unit configured to generate a subject three-dimensional object representing a virtual three-dimensional object for the subject associated with the subject size, based on the plurality of captured images and the size information;
A virtual three-dimensional object generation device comprising: The virtual three-dimensional object generation device according to claim 1,
A member acquisition unit configured to acquire member information including at least the appearance and dimensions of the covering member with respect to the covering member representing a member capable of covering at least a part of the subject;
A covering generation unit configured to generate a covering three-dimensional object representing a virtual three-dimensional object in which the covering member is arranged along the surface of the subject three-dimensional object based on the member information;
A virtual three-dimensional object generation device further comprising: The virtual three-dimensional object generation device according to claim 2,
The member acquisition unit is configured to acquire, as the member information, expansion / contraction information representing information related to expansion / contraction of the covering member, in addition to the appearance and dimensions of the covering member,
The virtual three-dimensional object generation device configured to generate a three-dimensional covered object arranged along a surface of the subject three-dimensional object by expanding and contracting the covering member in consideration of the expansion / contraction information.