Object design assistance device, control method for object design assistance device, and control program for object design assistance device

Abstract

To more easily design an object that can be actually produced.SOLUTION: An object design assistance device includes: a storage unit (real object database) configured to store images of multiple real objects that are actually present in association with three-dimensional information of the real objects; a selection reception unit configured to receive selection of an image as a reference image from the images of the real objects stored in the storage unit; an instruction reception unit configured to receive an instruction for generation of a feature of an object to be generated; a generation unit configured to generate a virtual object image having the feature instructed by the instruction for generation, based on the reference image, using a predetermined generation model; and a comparison unit configured to compare the virtual object image with the images of the multiple real objects stored in the storage unit and determine whether a predetermined condition is satisfied. The generation unit is also configured to repeat generation of the virtual object image until the predetermined condition is satisfied by the comparison unit, and to generate, for the virtual object satisfying the predetermined condition, three-dimensional information of that virtual object.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present invention relates to an object design support device, a control method for the object design support device, and a control program for the object design support device.

Background Art

[0002] Conventionally, there is known a clothing virtual generation system that uses a machine learning model to generate 3D (3-Dimension) clothing model data, pattern data, and / or 3D fabric model data from 2D (2-Dimension) clothing image data (for example, Patent Document 1). In recent years, the development of image generation AI (Artificial Intelligence) that generates an image according to a sentence (so-called prompt) that indicates features or an image has been progressing (for example, Non-Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Non-Patent Documents

[0004]

Non-Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0005] Using the above-described technology, it is considered possible to design an object such as clothing with an image generation AI in a 2D image and then convert it into 3D model data for output. However, further data processing is required until the clothing designed by the image generation AI can be worn. That is, there has been a demand for a method of more easily designing producible objects.

Means for Solving the Problems

[0006] An object design support device according to an embodiment of the present invention includes a storage unit that stores images of a plurality of actual objects that actually exist in association with three-dimensional information of the actual objects, a selection reception unit that receives a selection of at least one or more images as a reference image from the images of the actual objects stored in the storage unit, an instruction reception unit that receives a generation instruction for specifying characteristics of an object to be generated, a generation unit that generates an image of a virtual object having the characteristics specified by the generation instruction based on the reference image using a predetermined generation model, and a comparison unit that determines whether a result of comparing the image of the virtual object with the images of the plurality of actual objects stored in the storage unit satisfies a predetermined condition. The generation unit repeatedly generates an image of the virtual object until it is determined by the comparison unit that the predetermined condition is satisfied, and generates three-dimensional information of the virtual object that satisfies the predetermined condition.

[0007] In the object design support device according to an embodiment of the present invention, the generation instruction may include, as characteristics of the object to be generated, a specification of the shape of each element constituting the object.

[0008] In the object design support device according to an embodiment of the present invention, the generation instruction may include, as characteristics of the object to be generated, a specification of at least any one of color, pattern, and material indicating the aspect of the object.

[0009] In the object design support device according to an embodiment of the present invention, the generation instruction may include, as characteristics of the object to be generated, specification of dimensions of each element constituting the object.

[0010] In the object design support device according to an embodiment of the present invention, the selection reception unit may receive a reference image for each element constituting the object to be generated.

[0011] In the object design support device according to an embodiment of the present invention, the generation unit may generate an image of a virtual object using a generation model created by learning the association of the shape, dimensions, and aspect of the virtual object as three-dimensional information of each real object for each real object among the images of a plurality of real objects stored in the storage unit.

[0012] In the object design support device according to an embodiment of the present invention, the comparison unit may determine that a predetermined condition is satisfied when the difference between the feature amount calculated from the features of the virtual object generated by the generation unit and the feature amount calculated from the features of a plurality of real objects stored in the storage unit is equal to or greater than a predetermined threshold value.

[0013] A control method for an object design support device according to an embodiment of the present invention includes: storing, in a storage unit, images of a plurality of actual objects that actually exist, in association with information on the three-dimensional space of the actual objects; receiving a selection of at least one or more images as a reference image from the images of the actual objects stored in the storage unit; receiving a generation instruction specifying characteristics of an object to be generated; generating an image of a virtual object having the characteristics specified by the generation instruction based on the reference image; determining whether a result of comparing the image of the virtual object with the images of the plurality of actual objects stored in the storage unit satisfies a predetermined condition, and the generating step repeats generating the image of the virtual object until it is determined by the determining step that the predetermined condition is satisfied, and generates information on the three-dimensional space of the virtual object for the virtual object that satisfies the predetermined condition.

[0014] A control program for an object design support device according to an embodiment of the present invention realizes a function of storing, in a storage unit, images of a plurality of actual objects that actually exist, in association with information on the three-dimensional space of the actual objects; a function of receiving a selection of at least one or more images as a reference image from the images of the actual objects stored in the storage unit; a function of receiving a generation instruction specifying characteristics of an object to be generated; a function of generating an image of a virtual object having the characteristics specified by the generation instruction based on the reference image using a predetermined generation model; a function of determining whether a result of comparing the image of the virtual object with the images of the plurality of actual objects stored in the storage unit satisfies a predetermined condition, and the generating function repeats generating the image of the virtual object until it is determined by the determining function that the predetermined condition is satisfied, and generates information on the three-dimensional space of the virtual object for the virtual object that satisfies the predetermined condition.

Advantages of the Invention

[0015] According to an embodiment of the present invention, it is possible to provide an object design support device or the like that can more easily design an object that can be manufactured.

Brief Description of the Drawings

[0016]

Figure 1

Figure 2

Figure 3

Figure 4

Embodiments for Carrying Out the Invention

[0017] Hereinafter, an embodiment of the invention according to the present disclosure (also referred to as the present invention) will be described with reference to the drawings. Note that the drawings are merely examples, and the present invention is not limited to those shown in the drawings. For example, the block diagrams, flowcharts, data tables, etc. of the illustrated object design support apparatus (information processing apparatus) are merely examples, and the present invention is not limited thereto.

[0018] In this specification, an "object" is an object designed by a user, and includes, for example, "clothes", "furniture", "buildings", "tableware", "bags", "watches", "vehicles", "jewelry", "electrical appliances", "handicrafts", "organisms", etc. Note that in this specification, "design" may include not only the creation of a design in two dimensions but also the design for actually manufacturing an object. Hereinafter, clothes will be described as an example of an object, but "clothes" may include suits, kimonos, etc., and may include trousers, skirts, one-piece dresses, all-in-one outfits, shirts, T-shirts, jackets, coats, swimsuits, etc. Further, "clothes" may include accessories such as hats, scarves, gloves, neckties, belts, decorations such as necklaces, earrings, watches, glasses, masks, footwear such as shoes, sandals, clogs, and masks as sanitary supplies.

[0019] <Overview of Object Design Support System> Referring also to FIG. 1, first, an object design support system using an object design support apparatus will be described. The object design support apparatus 100 is connected to an information processing terminal of a user (hereinafter also referred to as a “user terminal”) (not shown), generates an image of a virtual object in response to a prompt input by the user terminal, and outputs the image to the user terminal. Here, the object design support apparatus 100 generates an image of a virtual object using a generation model learned with an image of an actual object that actually exists together with three-dimensional information of the actual object associated with the image. Note that the object design support apparatus 100 may output a three-dimensional model of the virtual object. The three-dimensional model of the virtual object is information necessary to make the virtual object three-dimensional, and may be, for example, a polygon mesh model (mesh model) including a set of vertices, edges, and faces that define the shape of the appearance (polyhedron object) of the virtual object.

[0020] The image of the actual object existing in reality and the three-dimensional information of the actual object are stored in the actual object database (DB) 400. Note that the three-dimensional information of the actual object may be information embedded in the image or information that can be identified from a plurality of images. For example, the image of the actual object may be a plurality of two-dimensional images obtained by photographing the actual object from a plurality of directions, and the three-dimensional shape (stereoscopic shape) of the actual object may be reproducible from these plurality of images. For example, the image of the actual object may be generated by photogrammetry based on a plurality of images obtained by photographing the object from a plurality of directions. Note that "Photogrammetry" is a method of photographing a subject from various angles, analyzing and integrating the digital images, and creating a three-dimensional 3DCG (3 Dimensional Computer Graphics) model. The photographing method from a plurality of directions is not particularly limited, and a large number (for example, 200) of photographing units (cameras) may be regularly installed so as to surround the photographing target to photograph a plurality of images, or a turntable on which the photographing target is placed may be rotated while photographing with a camera to photograph a plurality of images. Alternatively, without moving the photographing target, a plurality of images may be photographed by moving the camera while photographing. Note that an existing method may be used for generating a three-dimensional model from a plurality of images.

[0021] In addition, the image and three-dimensional information of the object may be obtained by photographing the object with a 3D camera capable of photographing depth information.

[0022] Note that the applicant has collected a large number of rare vintage clothes, and in one embodiment of the present invention, the image and three-dimensional information of the actual object stored in the actual object DB 400 may be obtained by photographing these clothes.

[0023] In the real object database 400, information regarding the features of a real object may be associated with and stored in the image of the real object. FIG. 2 is an example of a data table in which information regarding a real object is stored when the real object is "clothing". Note that the figure is an example, and the information to be stored is not limited to that shown in the figure, and the information to be stored may also be less than that shown in the figure. For example, in the figure, the locations indicated by "*" indicate that information is stored, and the locations indicated by "-" indicate that no information is stored. Note that the information described below may be associated manually by annotation or may be associated by machine learning.

[0024] In the data table TB10, information regarding the category, attributes, parts, decorations, age, etc. of a real object may be associated with and stored in an identifier that uniquely identifies the real object. The category is information indicating the type of the real object, and may be, for example, "skirt", "shirt", "jacket", "pullover", etc. Also, the category may be classified into a major category and a minor category. Further, in the real object database 400, information regarding the attributes of a real object may be stored. The attributes of a real object are information indicating the features of the real object, and may be, for example, information such as color, pattern, material, etc.

[0025] Also, in the actual object DB 400, information regarding the shape of each element constituting the actual object may be associated with the image of the actual object. Each element constituting the object is a part that forms the object. For example, in the case of clothing, it may be a pattern or ornament sewn with thread or the like, such as a collar, sleeves, shoulders, length, pockets, buttons, etc. Information regarding the shape of each element constituting the object is information on the shape and type of each element. For example, if the element is a "collar", it may include information regarding shapes such as a regular collar, a roll collar, a shawl collar, a bow tie, an open collar, etc. Also, if the element is a "sleeve", in addition to the length such as short sleeves and long sleeves, it may include information regarding shapes such as a dolman sleeve, a French sleeve, a no sleeve, a puff sleeve, etc.

[0026] Also, although not shown in FIG. 2, in the actual object DB 400, information regarding the dimensions of each element constituting the actual object may be associated with the image of the actual object. For example, when the element is a "sleeve", the sleeve length and the dimensions of the cuff may be associated.

[0027] Also, in the actual object DB 400, information regarding the decoration applied to the actual object and the information regarding the era in which the actual object was manufactured may be further associated with the image of the actual object. The decoration may be, for example, studs, cutouts, piping, double-breasted tailoring, fringe, etc.

[0028] <Hardware Configuration> Next, with reference to FIG. 4, the hardware configuration of the object design support apparatus (information processing apparatus) 100 according to an embodiment of the present invention will be described.

[0029] The object design support device 100 is composed of an information processing device and may typically be a server. The object design support device 100 realizes the functions and methods described in this embodiment through the cooperation of a processor 101, a memory 102, a storage 103, an input / output interface (I / F) 104, and a communication I / F 105. For example, the functions or methods of the present disclosure are realized by the processor 101 executing instructions included in a program read into the memory 102.

[0030] The processor 101 executes functions and / or methods realized by codes or instructions included in a program stored in the storage 103. For example, it includes a central processing unit (CPU), a micro processing unit (MPU), a graphics processing unit (GPU), etc., and realizes each process disclosed in each embodiment by a logic circuit (hardware) formed on an integrated circuit or the like or a dedicated circuit.

[0031] The memory 102 temporarily stores a program loaded from the storage 103 and provides a working area for the processor 101. The memory 102 includes, for example, a random access memory (RAM), a read only memory (ROM), etc.

[0032] The storage 103 stores a program for making the information processing device function as an object design support device. The storage 103 includes, for example, a hard disk drive (HDD), a solid state drive (SSD), a flash memory, etc.

[0033] The communication I / F 105 is implemented as hardware such as a network adapter, communication software, or a combination thereof, and performs transmission and reception of various data with a user's terminal (not shown) via a wireless or wired network.

[0034] The input / output I / F 104 includes an input device for inputting various operations to the object design support device 100 and an output device for outputting the processing results processed by the object design support device 100. The input / output I / F 104 may integrate the input device and the output device, or may separate the input device and the output device.

[0035] <Functional Configuration> Next, with reference to FIG. 1, the functional configuration of the object design support device according to an embodiment of the present invention will be described. As functions realized by the control unit 110, the object design support device 100 includes a reception unit 111, a generation unit 114, a comparison unit 115, an output unit 116, and a learning unit 117. The reception unit 111 includes an instruction reception unit 112 and a selection reception unit 113. In FIG. 1, functional units that are not essential in each embodiment described hereinafter may not be provided. Also, the functions or processes of each functional unit may be realized by machine learning or AI within a realizable range.

[0036] Hereinafter, an embodiment of the present invention will be described together with the processing of each functional unit of the object design support device 100, also using the flowchart of FIG. 3. FIG. 3 is an example of a flowchart showing the processing by the object design support device 100 according to an embodiment of the present invention.

[0037] First, as described above, images of a plurality of actual objects existing in reality are stored in association with the three-dimensional information of the actual objects (step S11). These information are stored in the actual object DB 400. In FIG. 1, the actual object DB 400 is shown separately from the object design support device 100, but the actual object DB 400 may be stored in the storage of the object design support device 100. Also, as described above, information regarding the characteristics of the actual object may be stored in the image of the actual object.

[0038] When the user starts designing an object, the object design support device 100 transmits an image of the actual object to the user terminal in order to allow the user to select an image of the actual object on the user terminal. The user can select an image 12 similar to the object they want to design from among the images of a plurality of actual objects. The selection reception unit 113 receives the selection of at least one or more images as the reference image 12 from the images of the actual objects stored in the actual object DB 400 (step S12). Also, the instruction reception unit 112 receives a generation instruction 11 specifying the characteristics of the object to be generated from the user terminal (step S13). The generation instruction may be a so-called prompt that specifies the characteristics of the object to be generated.

[0039] Based on the reference image 12, the generation unit 114 generates an image of a virtual object having the characteristics specified by the generation instruction 11 using a predetermined generation model (step S14). The generation model may be a learning model that learns the images and characteristics of the actual objects stored in the actual object DB 400 and generates an image of a virtual object based on a prompt. Note that the learning unit 117 may perform machine learning on the association between the shape, dimensions, and aspect of each element constituting the actual object as the three-dimensional information of the actual object for each of the plurality of actual object images stored in the actual object DB 400, and create a generation model.

[0040] Alternatively, the generation unit 114 may generate a virtual object by an algorithm using a deep neural network such as a variational autoencoder or a generative adversarial network (GAN).

[0041] The comparison unit 115 determines whether or not the result of comparing the image of the virtual object with the images of a plurality of actual objects stored in the actual object DB 400 satisfies a predetermined condition (step S15).

[0042] Here, a predetermined condition will be described. In one embodiment of the present invention, the generation unit 114 generates a virtual object using a generation model that has learned an image or the like of an existing real object. However, when the real object is a product with someone else's design, it is not preferable to generate a counterfeit. Therefore, it is desirable to adopt a new design while referring to the excellent design of the real object. According to one embodiment of the present invention, as a predetermined condition, the designability of the virtual object may be determined using a condition that can determine that the virtual object is not similar to the real object and is a new design.

[0043] For example, when the difference between the feature amount calculated from the features of the virtual object generated by the generation unit 114 and the feature amount calculated from the features of a plurality of real objects stored in the real object DB 400 is equal to or greater than a predetermined threshold value, it may be determined that a predetermined condition is satisfied. For example, the feature amount of an object (including a real object and a virtual object) may be a shape, color, pattern, dimension (width, depth), combination of each element, combination of materials, or the like. The comparison unit 115 represents these feature amounts numerically, and if the difference between the numerical value of the feature amount of the real object and the numerical value of the feature amount of the virtual object is equal to or greater than a threshold value such that it can be said that the two objects are not similar, it may be determined that a predetermined condition is satisfied. Note that the comparison may be performed for each feature amount or for the total of the feature amounts. Thereby, it is possible to output a new design that is not similar to the real object.

[0044] When it is determined by the comparison unit 115 that a predetermined condition is not satisfied (NO in step S15), the process returns to step S14, and the generation unit 114 may repeat the generation process of the virtual object based on the prompt. When it is determined by the comparison unit 115 that the predetermined condition is satisfied (YES in step S15), the output unit 116 generates three-dimensional information of the virtual object that satisfies the predetermined condition and outputs an image of the virtual object (step S16). In an embodiment of the present invention, since the generation unit 114 generates a virtual object by using a generation model that has learned three-dimensional information of a real object, it can generate including three-dimensional information. Note that the output unit 116 may output the virtual object in a manner that can be rotated 360° on the user terminal. This may be realized, for example, by using a lightweight JavaScript library such as Three.js for rendering 3D videos in a browser. Also, the file format of the virtual object output by the output unit 116 may be, but is not limited to, the obj format, fdx format, unitypackage format, etc.

[0045] Note that the instruction reception unit 112 may receive, as a generation instruction, a specification of the shape of each element constituting the object, which is a feature of the object to be generated. For example, when the object to be generated is a shirt, the generation instruction may include the shapes of the collar, sleeves, body, etc. constituting the shirt. Thereby, an object with a design along the user's image can be generated.

[0046] Also, the generation instruction may include a specification of at least any one of color, pattern, and material indicating the aspect of the object as a feature of the object to be generated. For example, when the object to be generated is a jacket, the generation instruction may include specifications such as green, tartan check, and wool. Note that it may be the aspect of the entire object, or the aspect may be specifiable for each element constituting the object. For example, the color and material may be specifiable separately for the sleeves and the body. Thereby, an object with a design along the user's image can be generated.

[0047] Furthermore, the generation instruction may include, as characteristics of the object to be generated, the specification of the dimensions of each element constituting the object. For example, as a prompt, numerical values of cuffs and collar openings may be input, or specifications such as "bare hands are long up to the fingertips" and "three-quarter length, which is 〇〇 cm shorter from the wrist" may be made. Thereby, an object that more matches the user's body type and preferences can be generated.

[0048] Note that the selection reception unit 113 may receive a reference image for each element constituting the object to be generated. For example, for each element, a reference image may be selectable, such as "image A" for the "collar", "image B" for the "sleeve", and "image C" for the "pattern".

[0049] The output unit 116 may output information for realizing the virtual object in the real world. For example, the output unit 116 may output design data for a 3D printer, a pattern, a design drawing, etc., according to the object to be produced. Also, when a plurality of virtual objects are generated by the generation unit 114, the output unit 116 may output the plurality of virtual objects to the user terminal. The user can select the virtual object to be produced and cause the output unit 116 to output the information for production.

[0050] Although the present invention has been described based on the drawings and embodiments, it should be noted that those skilled in the art can easily make various modifications and corrections based on the present disclosure. Therefore, it should be noted that these modifications and corrections are included in the scope of the present invention. For example, the functions, etc. included in each component, each step, etc. can be rearranged so as not to be logically contradictory, and a plurality of components and steps, etc. can be combined into one or divided. Also, the configurations shown in the above embodiments may be appropriately combined.

[0051] For example, in FIG. 1, only one object design support device 100 is shown, but it is not limited to this, and there may be a plurality of them. Further, the object design support device 100 is a distributed server that cooperates by communicating via a network, and may include an edge server or may be a so-called cloud server. That is, the object design support device 100 is not limited to a physical server and may also include a virtual server.

[0052] Also, at the time of generating the generation model, for example, the weight and height recommended for a certain piece of clothing may be associated and learned, and by including the height and weight in the prompt by the user, the dimensions of the automatically generated clothing may be determined.

[0053] In the above description, clothing is used as an example of the object. However, as the object, as described above, furniture, buildings, tableware, bags, watches, vehicles, jewelry, electrical appliances, handicrafts, organisms, etc. may also be targets. In the case of furniture, for example, as each element constituting a table, legs, a tabletop, etc. may be specifiable together with the material and color, and as each element constituting a chair, legs, a backrest, a seat part, etc. may be specifiable together with the material and color. Also, in the case of a building, for example, characteristics such as the exterior wall color, the pattern of the exterior wall, the position of the veranda, the number of floors, the door, the window, the roof, etc. may be specifiable. As the actual object data of the building, the appearance, dimensions, etc. of the building may be obtained by image processing from satellite images provided by existing services.

[0054] Also, in the program of the present disclosure, the two-dimensional virtual object image (2D image) temporarily generated by the generation unit 114 may also be obtained as a product in the process of generation. That is, the output unit 116 may be able to output the 2D image of the virtual object generated by the generation unit 114. Further, the output unit 116 may be able to output the virtual object generated by the generation 114 in a state of being superimposed on another object. For example, the output unit 116 may output an image of a clothing model in a state of being worn by a person.

[0055] The program of each embodiment of the present disclosure may be provided in a state stored in a storage medium readable by an information processing apparatus. The storage medium can store the program in a "non-transitory tangible medium". The program includes, for example, a software program or a control program. When each functional part of the object design support apparatus is realized by software, the object design support apparatus functions as a reception part 111, an instruction reception part 112, a selection reception part 113, a generation part 114, a comparison part 115, an output part 116, and a learning part 117 by executing the program loaded on the memory by a processor.

[0056] Also, the program of the present disclosure may be provided to the object design support apparatus via any transmission medium (such as a communication network or a broadcast wave) capable of transmitting the program.

[0057] Also, each embodiment of the present disclosure can also be realized in the form of a data signal embedded in a carrier wave, in which the program is embodied by electronic transmission. Note that the program of the present disclosure may be implemented using, for example, a script language such as JavaScript (registered trademark), Python, a C language, a Go language, Swift, Kotlin, Java (registered trademark), etc.

Description of Signs

[0058] 100 Object design support apparatus (information processing apparatus) 110 Control part 111 Reception part 112 Instruction reception part 113 Selection reception part 114 Generation part 115 Comparison part 116 Output part 117 Learning part 10 User input 11 Generation instruction 12 Reference image 20 Output image

Claims

1. A storage unit that stores images of a plurality of actual objects existing in reality in association with three-dimensional information of the actual objects; A selection reception unit that receives selection of at least one or more images as reference images from the images of the actual objects stored in the storage unit; An instruction reception unit that receives a generation instruction for specifying characteristics of an object to be generated; A generation unit that generates an image of a virtual object having the characteristics specified by the generation instruction using a predetermined generation model based on the reference image; A comparison unit that determines whether or not a result of comparing the image of the virtual object with the images of the plurality of actual objects stored in the storage unit satisfies a predetermined condition; comprising; The generation unit repeatedly generates an image of the virtual object until it is determined by the comparison unit that the predetermined condition is satisfied, and generates three-dimensional information of the virtual object for which the predetermined condition is satisfied. An object design support device.

2. The generation instruction includes specification of the shape of each element constituting the object as a characteristic of the object to be generated. The object design support device according to claim 1.

3. The generation instruction includes specification of at least one of color, pattern, and material indicating the aspect of the object as a characteristic of the object to be generated. The object design support device according to claim 1 or 2.

4. The generation instruction includes specification of the dimensions of each element constituting the object as a characteristic of the object to be generated. The object design support device according to claim 1 or 2.

5. The selection reception unit receives a reference image for each element constituting the object to be generated. The object design support device according to claim 1.

6. For the images of the plurality of actual objects stored in the storage unit, for each actual object, as three-dimensional information of the actual object, the shape, dimensions, and the relationship of the aspect of the actual object of each element constituting the actual object are learned and created using the generation model, and the image of the virtual object is generated. The object design support device according to claim 3.

7. When the difference between the feature amount calculated from the features of the virtual object generated by the generation unit and the feature amount calculated from the features of the plurality of actual objects stored in the storage unit is equal to or greater than a predetermined threshold value, it is determined that the predetermined conditions are satisfied. The object design support device according to claim 1.

8. The object design support device storing the images of a plurality of actual objects existing in reality in the storage unit in association with the three-dimensional information of the actual objects; receiving a selection of at least one or more images as a reference image from the images of the actual objects stored in the storage unit; receiving a generation instruction specifying the features of the object to be generated; generating an image of a virtual object having the features specified by the generation instruction based on the reference image; determining whether the result of comparing the image of the virtual object with the images of the plurality of actual objects stored in the storage unit satisfies a predetermined condition; including The generating step repeats generating an image of the virtual object until it is determined by the determining step that the predetermined condition is satisfied, and generates three-dimensional information of the virtual object for the virtual object that satisfies the predetermined condition. A control method for an object design support device.

9. In an information processing apparatus, a function of storing in a storage unit images of a plurality of real objects existing in reality in association with three-dimensional information of the real objects; a function of receiving a selection of at least one or more images as a reference image from the images of the real objects stored in the storage unit; a function of receiving a generation instruction for designating characteristics of an object to be generated; a function of generating an image of a virtual object having the characteristics designated by the generation instruction based on the reference image using a predetermined generation model; a function of determining whether or not a result of comparing the image of the virtual object with the images of the plurality of real objects stored in the storage unit satisfies a predetermined condition; to realize The generating function repeats generating an image of the virtual object until it is determined by the determining function that the predetermined condition is satisfied, and generates three-dimensional information of the virtual object for the virtual object that satisfies the predetermined condition. A control program for an object design support device.

Images