Photography support information generation device, photography support information generation method, program, and recording medium

Abstract

Provided are a photography support information generation device, a photography support information generation method, a program, and a recording medium with which it is possible to flexibly cope with various photography sites and photography subjects and to support capturing of an image that aligns with a user's desired mental image. A user terminal (10), which is the photography support information generation device according to one embodiment of the present invention, comprises a processor (11). The processor (11) is configured to: receive an input of an input image (Pf), which is first information relating to photography; receive an input of an input text (Tx), which is second information relating to the user's mental image of the photographed image; and cause a generative AI (211), which is an image generation model, to generate a photography support image (Ps), on the basis of the first information (Pf) and the second information (Tx).

Description

Image shooting support information generation device, image shooting support information generation method, program, and recording medium

[0001] One embodiment of the present invention relates to a shooting support information generation device, a shooting support information generation method, a program, and a recording medium that can flexibly respond to various shooting locations and subjects and support the capture of images that conform to the user's desired image.

[0002] Camera performance has continued to evolve over time, making it possible for even average users to easily capture high-quality images. However, there is a gap between the composition and shooting conditions used by average users and those of professional photographers. It is not easy for average users to improve their shooting skills to the level of professional photographers. Therefore, technologies have been proposed that provide users with shooting support by incorporating appropriate shooting control functions into the camera itself.

[0003] One example of such technology is the technology described in Patent Document 1. Patent Document 1 discloses a technology that provides photographers with an advanced level of enjoyment in photography.

[0004] This technology relates to a photographing support system comprising: an image information database that stores image data of existing photographic images and the image information thereof in association with each other; a management server connected to the image information database via a network; and an imaging device of a user connectable to the management server via a network, wherein the imaging device comprises: imaging means; creation means for extracting features from temporary imaging data temporarily captured by the imaging means and creating temporary imaging information including parameters indicating the features; transmission means for transmitting the temporary imaging information to the management server; receiving means for receiving control information for controlling imaging conditions suitable for imaging from the management server; and setting means for setting imaging conditions in accordance with the control information, and wherein the management server comprises: storage means for storing photographic images pre-registered by each user in association with the user; receiving means for receiving the temporary imaging information from the imaging device; inference means for inferring the features based on the parameters; acquisition means for searching for a photographic image having features close to said features from among the photographic images corresponding to the user that received the temporary imaging information by said receiving means, and acquiring the image information of the searched photographic image; extraction means for comparing the received temporary imaging information with the image information and extracting a difference; control information creation means for creating control information for setting imaging conditions in the user's imaging device based on the extracted difference; and transmission means for transmitting the control information to the imaging device.

[0005] Also, Patent Document 2 discloses a technology developed in view of the situation that it is difficult for a user to imagine what kind of image can be obtained until the user actually goes to the photographing position or receives an actually captured image, and thus a user cannot necessarily obtain a satisfactory image, and the technology is for obtaining images with high user satisfaction.

[0006] This technology relates to a photographing support information generation apparatus comprising a control unit that causes display of a photographing sample image list in which a plurality of sample photographed images captured at a plurality of mutually different photographing locations are arranged, and when any sample photographed image is selected from the photographing sample image list, causes presentation of guidance information for guiding to the photographing location of the selected sample photographed image.

[0007] Japanese Patent Publication No. 2009-55088 Japanese Patent Publication No. 2000-261825

[0008] From the perspective of how the average user can improve their photography skills without difficulty, it is effective to refer to excellent photographs taken by professional photographers and start by adopting their compositions and techniques. However, the compositions and shooting conditions in professional photographers' photos cannot always be directly applied to actual shooting situations.

[0009] In particular, if the user lacks sufficient shooting experience or skills, or if it's their first time shooting in a new location or photographing a new subject, it's not easy to reinterpret and apply the composition and shooting conditions they remember as knowledge to the actual situation.

[0010] On the other hand, in order to deal with the cases described above, it is also possible to search the internet or elsewhere for photographs taken by others of similar shooting locations or subjects to the actual shooting location or subject, and to collect reference information for shooting from those photographs.

[0011] However, even when conducting such searches and collections, it's not guaranteed that similar photos of the same shooting location or subject will be found. Furthermore, even if such photos are found, if the user attempts to take a photo using the exact same composition and shooting conditions, the resulting image will lack the user's originality and creativity. For such users, this could mean losing the joy of photography that they should be experiencing.

[0012] One embodiment of the present invention has been made in view of the above circumstances, and aims to provide a technology that can flexibly respond to various shooting locations and subjects, and that can support the capture of images that conform to the image desired by the user.

[0013] The above objective is achieved by a shooting support information generation device described in any of the following [1] to

[19] . [1] A shooting support information generation device equipped with a processor, wherein the processor receives input of first information relating to shooting, receives input of second information relating to the image of the captured image by the user, and generates a shooting support image using an image generation model based on the first information and the second information.

[0014] [2] The first information is information relating to the subject to be photographed, as described in [1], the photographic support information generation device.

[0015] [3] The first information is information relating to the subject, as described in [1] or [2], a shooting support information generating device.

[0016] [4] The shooting support information generation device according to any one of [1] to [3], wherein the processor generates multiple shooting support images by an image generation model based on the first information and the second information.

[0017] [5] The image generation model is a trained model, and the shooting support information generation device is one of the models described in [1] to [4].

[0018] [6] A shooting support information generation device according to any one of [1] to [5], wherein the processor outputs a shooting support image to a display device.

[0019] [7] The shooting support image is a non-photorealistic image, as described in any of [1] to [6], a shooting support information generation device.

[0020] [8] The shooting support information generation device according to [7], wherein the processor inputs the first information and the second information into an image generation model to generate a non-photorealistic image.

[0021] [9] The shooting support information generating device according to [7] or [8], wherein the non-photorealistic image has a different style from the image that can ultimately be captured or acquired based on the shooting support image.

[0022]

[10] The shooting support information generation device according to [9], wherein the processor applies a transformation process to the image that can be ultimately captured or acquired, which has been generated by the image generation model, thereby changing the style of a non-photorealistic image to a different style.

[0023]

[11] The shooting support information generation device according to

[10] , wherein the processor applies a painterly style conversion process to the image that can ultimately be captured or acquired, thereby changing the style of a non-photorealistic image to a different style.

[0024]

[12] The shooting support information generation device according to

[10] or

[11] , wherein the processor applies a touch change conversion process to the image that can be ultimately captured or acquired, thereby changing the style of a non-photorealistic image to a different style.

[0025]

[13] The shooting support information generation device according to any one of

[10] to

[12] , wherein the processor applies a color reduction conversion process to the image that can be ultimately captured or acquired, thereby changing the style of a non-photorealistic image to a different style.

[0026]

[14] A shooting support information generation device according to any one of [1] to

[13] , wherein the processor accepts input of information relating to at least one of the shooting location and the subject as input of first information.

[0027]

[15] A shooting support information generation device according to any one of [1] to

[14] , wherein the processor accepts image information obtained by shooting as input of first information.

[0028]

[16] The image information obtained by shooting is an image taken at a shooting location necessary for shooting support, as described in

[15] , the shooting support information generation device.

[0029]

[17] A shooting support information generation device according to any one of [1] to

[16] , wherein the processor generates guidance information regarding shooting actions based on a shooting support image selected by the user from among a plurality of shooting support images.

[0030]

[18] The shooting support information generating device according to

[17] , wherein the processor generates information as guidance information regarding at least one of the following for a shooting support image selected by the user: the subject to be photographed, the shooting location, the equipment used for shooting, the shooting conditions, and the shooting environment.

[0031]

[19] The shooting support information generation device according to

[17] or

[18] , wherein the processor outputs guidance information to a display device.

[0032] Furthermore, the above objective can also be achieved by the shooting support information generation method described in

[20] below.

[20] A shooting support information generation method comprising a processor for generating shooting support information, the method comprising: a step of receiving input of first information relating to shooting by the processor; a step of receiving input of second information relating to the image of a captured image by the user by the processor; and a step of generating a shooting support image by an image generation model based on the first information and the second information by the processor.

[0033] Furthermore, the above objectives can also be achieved by the program described in

[21] below.

[21] A program for causing a computer to execute each step included in the method for generating imaging support information described in

[20] .

[0034] Furthermore, the above objectives can also be achieved by the recording medium described in

[22] below.

[22] A computer-readable recording medium on which a program is recorded causing a computer to perform each step included in the method for generating imaging support information described in

[20] .

[0035] According to one embodiment of the present invention, a shooting support information generation device, a shooting support information generation method, a program, and a recording medium are provided that can flexibly respond to various shooting locations and subjects and support the capture of images that conform to the image desired by the user.

[0036] This figure shows an example configuration of the shooting support information generation system according to this embodiment. This figure shows an example hardware configuration of the user terminal (shooting support information generation device) according to this embodiment. This figure shows the functional parts of the user terminal (shooting support information generation device) according to this embodiment. This figure shows an example of an input image table according to this embodiment. This figure shows an example of a text information table according to this embodiment. This figure shows an example of an image table according to this embodiment. This figure shows an example flow of the shooting support information generation method according to this embodiment. This figure shows an example screen according to this embodiment. This figure shows an example screen according to this embodiment. This figure illustrates the flow of the shooting support information generation method according to this embodiment. This figure shows an example screen according to this embodiment. This figure shows an example screen according to this embodiment.

[0037] The following describes specific embodiments of the present invention. For convenience of explanation, the following descriptions may sometimes be based on the perspective of a GUI (Graphical User Interface). Furthermore, since the fundamental data processing technologies for realizing the present invention (communication / transmission technologies, data acquisition technologies, data recording technologies, data processing / analysis technologies, machine learning technologies, image processing technologies, and visualization technologies, etc.) are known technologies, their descriptions will be omitted.

[0038] Furthermore, in this specification, the concept of "device" includes not only a single device that performs a specific function, but also a combination of multiple devices that exist independently and in a distributed manner while cooperating (linking) to perform a specific function.

[0039] Furthermore, in this specification, "user" refers to a user of the shooting support information generation device of the present invention, and specifically, for example, a person who takes appropriate photographs based on shooting conditions such as shooting location and composition using the functions of the shooting support information generation device of the present invention.

[0040] Furthermore, in this specification, "person" means an entity that performs a specific action, and includes individuals, groups, corporations and other legal entities, and organizations, and may also include computers and devices that constitute artificial intelligence (AI). Artificial intelligence (AI) realizes intelligent functions such as reasoning, prediction, and judgment using hardware and software resources. The algorithm of artificial intelligence is arbitrary and includes, for example, expert systems, case-based reasoning (CBR), convolutional neural networks (CNN), deep neural networks (DNN), Bayesian networks, or inclusion architectures.

[0041] <<About one embodiment of the present invention>> [Configuration of the shooting support information generation system] In one embodiment of the present invention (hereinafter, this embodiment), the shooting support information generation system 5 is configured by a user terminal 10 (shooting support information generation device), a shooting device 30, and a generation AI server 40, all connected to the network N shown in Figure 1. The user terminal 10 is an information processing terminal such as a smartphone that functions as the shooting support information generation device of the present invention. Alternatively, the shooting device 30 may be equipped with the functions and configuration of the user terminal 10, and the shooting device 30 may function as the shooting support information generation device. Or, the user terminal 10 may be equipped with the functions and configuration of the shooting device 30, and they may function as an integrated system.

[0042] Among the above components, the imaging device 30 is a device for a user to photograph an image (which is image information obtained through photography, hereinafter referred to as an input image Pf) as needed. Specifically, a digital camera corresponds to such an imaging device 30. The input image Pf is an image that can serve as reference information (first information) about a photographic subject that the user ultimately intends to photograph. It should be noted that the input image Pf captured by the imaging device 30 in the present embodiment may include, for example, not only an image captured by a digital camera and transferred to the user terminal 10, but also a live view image from the digital camera. In addition, the input image Pf, i.e., the first information, "includes information relating to photography for which a user wants to generate a photographing support image".

[0043] The user terminal 10 is an information processing terminal that executes the photographing support information generation method of the present embodiment, inputs the input image Pf transferred from the imaging device 30 and an input text Tx (second information) input regarding the image that the user ultimately intends to photograph to a generative AI 211 (which is an image generation model, described later in FIG. 3), and generates a photographing support image Ps. It should be noted that the above-mentioned "image that the user ultimately intends to photograph" is an "image that the user wants to photograph from now on", and is not an "already photographed image". In addition, the photographing support image Ps is an image that suggests a photographed image considered to be desired by the user, and is preferably a non-photorealistic image.

[0044] A non-photorealistic image is an image that is not photorealistic like a photograph, and specifically refers to images with poor photorealism such as images in a painting style like oil painting, images in an illustration style like animation or manga, coarse-grained images with increased pixel size, and images with a number of colors equal to or less than a predetermined standard. A photographing support image Ps with poor photorealism naturally makes it easy to avoid situations where the user performs photographing that ignores originality or creativity, such as photographing an image that is almost the same as the photographing support image Ps.

[0045] Furthermore, when generating the above-mentioned shooting support image Ps, the user terminal 10 can adopt not only a form that uses the generative AI 211 held by itself, but also a form that calls the corresponding function from the generative AI server 40 and appropriately cooperates therewith. In this case, the user terminal 10 acquires the input image Pf from the photographing device 30 and transmits it to the generative AI server 40, thereby generating the shooting support image Ps. Of course, the user terminal 10 may include a photographing unit similar to that of the photographing device 30, and photograph the input image Pf as needed. Furthermore, the input image Pf may include an image generated by the generative AI 211 of the user terminal 10 or the generative AI server 40.

[0046] Furthermore, the above-mentioned user may cause the UI (User Interface) of the user terminal 10 to scan or read, for example, a photo print held by the user, the user's own screen (on which a photographic image is displayed), or the corresponding data as the above-mentioned input image Pf via a medium. When such a configuration and operation is adopted, the shooting support information generation system 5 can be configured only by the user terminal 10.

[0047] The user terminal 10 stores the input image Pf obtained through shooting by itself or the photographing device 30 or image generation in an input image table 201 (described later with reference to FIGS. 3 and 4), and stores input text Tx received from the user (text information relating to an image that the user ultimately wants to shoot: second information) in a text information table 202 (described later with reference to FIGS. 3 and 5), respectively, to prepare for each process for generating the shooting support image Ps by the generative AI 211.

[0048] Furthermore, as described above, the generative AI server 40 is a server device that provides a generative AI function to the user terminal 10 via the network N. Of course, if the user terminal 10 is configured not to require the function provision of generative AI, the present generative AI server 40 does not need to be included in the shooting support information generation system 5.

[0049] In addition to the configuration in which the user terminal 10 and the generation AI server 40 are connected via a network N, the internal bus wiring of the user terminal 10 may be directly connected to the interface of the generation AI server 40. Similarly, in addition to the configuration in which the user terminal 10 and the imaging device 30 are connected via a network N, the internal bus wiring of the user terminal 10 may be directly connected to the interface of the imaging device 30.

[0050] Furthermore, various situations can be envisioned, such as cases where the photographer who performs various operations related to shooting and outputting with the shooting device 30, the registrant who inputs the image obtained from the shooting (input image Pf) and input text Tx into the user terminal 10 (which may include scanning operations and uploading from the shooting device 30), and the viewer who views the shooting support image Ps, etc., which are the processing results of the user terminal 10 or the generation AI server 40, on the user terminal 10 or the shooting device 30, are all different people, or cases where they are all the same person.

[0051] In this invention, "image" is composed of multiple pixels, represented by the grayscale values ​​of each of the multiple pixels, and includes an image of at least one subject. Furthermore, digital image data (hereinafter referred to as "image data") that defines an image at a set resolution is generated by compressing data in which the grayscale values ​​of each pixel are recorded using a predetermined compression method. Examples of image data include lossy compressed image data such as JPEG (Joint Photographic Experts Group) format, and lossless compressed image data such as GIF (Graphics Interchange Format) or PNG (Portable Network Graphics) format.

[0052] [Example Configuration of the Shooting Support Information Generation Device] Next, an example configuration of the user terminal 10, which is the shooting support information generation device according to this embodiment, will be described with reference to Figures 2 and 3. The user terminal 10 consists of a computer used by the user (including the concept of the computer chip of the user terminal 10), and specifically consists of a smartphone, a PC (Personal Computer), a tablet terminal, or a notebook PC, etc. Note that the user terminal 10 is not limited to an information processing terminal owned by the user, and may also consist of a terminal that the user does not own but can use when visiting a store or facility, such as a store-installed terminal. In the following, we will explain using the case in which the user terminal 10 is composed of a smartphone or PC, which are information processing terminals owned by the user, as an example.

[0053] As shown in Figure 2, the computer comprising the user terminal 10 includes a processor 11, an auxiliary storage device 12, a main storage device 13, an input device 14, an output device 15, and a communication device 16.

[0054] The processor 11 is composed of, for example, a CPU (Central Processing Unit), MPU (Micro-Processing Unit), MCU (Micro Controller Unit), GPU (Graphics Processing Unit), DSP (Digital Signal Processor), TPU (Tensor Processing Unit), or ASIC (Application Specific Integrated Circuit). The processor 11 is responsible for generating, outputting, displaying, and saving the image support image Ps.

[0055] The auxiliary storage device 12 is composed of, for example, flash memory, HDD (Hard Disk Drive), SSD (Solid State Drive), FD (Flexible Disk), MO disk (Magneto-Optical Disk), CD (Compact Disk), DVD (Digital Versatile Disk), SD card (Secure Digital card), or USB memory (Universal Serial Bus memory).

[0056] Such auxiliary storage devices 12 may be built into the main unit of the computer constituting the user terminal 10, or they may be attached to the main unit of the computer in an external form. Alternatively, the auxiliary storage device 12 may be configured as a NAS (Network Attached Storage) or the like. Furthermore, the auxiliary storage device 12 may be an external device that can communicate with one of the computers constituting the user terminal 10 via a communication network, such as an online storage or database server.

[0057] Furthermore, the auxiliary storage device 12 holds programs 121 such as the operating system (OS) and applications related to image generation and conversion processes. When the programs 121 are read and executed by the processor 11, the computer constituting the user terminal 10 performs the functions of the reception unit 20, generation unit 21, determination unit 22, and output unit 23 shown in Figure 3, and specifically performs a series of processes such as acquiring the input image Pf and generating the shooting support image Ps based on the input image Pf. In other words, the processor 11 of the user terminal 10 has the above-mentioned reception unit 20, generation unit 21, determination unit 22, and output unit 23.

[0058] The main memory 13 is composed of semiconductor memory such as ROM (Read Only Memory) and RAM (Random Access Memory). The processor 11 loads the program 121 onto the main memory 13 and executes it there.

[0059] The input device 14 is a device that accepts user input operations and is composed of, for example, a keyboard, mouse, or touch panel. The input device 14 may also include a digital camera unit and a microphone for sound collection. The output device 15 is composed of, for example, a display or speaker. However, in this embodiment, the output device 15 is used for explanation purposes as a display device that displays various images and text. Furthermore, the digital camera unit in the input device 14 of the user terminal 10 may be used in the same way as the shooting device 30.

[0060] The communication device 16 may be composed of, for example, a network interface card or a communication interface board. The computer constituting the user terminal 10 can communicate with other devices connected to a network N, such as the Internet and mobile communication lines, via the communication device 16.

[0061] As shown in Figure 3, the user terminal 10 has a reception unit 20, a generation unit 21, a determination unit 22, and an output unit 23. These functional units are realized when the processor 11 of the user terminal 10 executes the aforementioned program 121 and cooperates with other hardware devices of the user terminal 10. In addition, the generation AI 211 in the generation unit 21 may be called and executed from the generation AI server 40.

[0062] (Reception Unit) The reception unit 20 acquires input images Pf through imaging by the imaging unit of the imaging device 30 or input device 14, or via the communication device 16, and stores them in, for example, the auxiliary storage device 12. The reception unit 20 stores the input images Pf acquired as described above in the input image table 201. In addition, the reception unit 20 acquires input text Tx from the keyboard of the input device 14 or via the communication device 16 in order to generate imaging support images Ps, and stores this in the text information table 202.

[0063] Figure 4 shows an example of the configuration of the input image table 201 in this embodiment. The input image table 201 is a collection of records containing the values ​​of Image ID, Photographer, Image No., Shooting Location, and Image Data. Of these, Image ID is identification information that uniquely identifies the image of the input image Pf. Photographer is the identification information of the person who took the input image Pf, specifically the user. Image No. is identification information related to the individual image data constituting the input image Pf linked to the Image ID. Shooting Location is location information indicating the shooting location of the individual image (e.g., coordinate values ​​in a predetermined map service, specific facility name or address, etc.). Image Data is the data file of the individual image.

[0064] The input text Tx consists of keywords and sentences entered by the user regarding the input image Pf, and is text information that expresses the image the user ultimately wants to capture (e.g., the impression or composition the user desires). In addition to the method of receiving input from the user at the reception unit 20 as described above, the generation unit 21 can also acquire the input text Tx by assigning the input image Pf obtained from the shooting device 30 or the shooting unit of the input device 14 to the generation AI server 40 and requesting the generation of input text Tx.

[0065] In this case, the generation AI server 40 also has a so-called caption generation function and is capable of generating text information that indicates the image of the final image (the image actually obtained by the user through photography) that is presumed to be desired by the user with respect to the input image Pf. For this reason, the generation AI server 40 in this case has, for example, previously performed machine learning using pairs of input image Pf received from the user and input text Tx entered by the user regarding the input image Pf as training data. More preferably, the generation unit 21 presents the input text Tx obtained from the generation AI server 40 as candidate information to the user, and when it receives a response from the user indicating acceptance as input text Tx, it uses it as input text Tx for subsequent processing. Alternatively, the user terminal 10 may have the above caption generation function and perform the automatic generation of the above input text Tx.

[0066] On the other hand, Figure 5 illustrates the text information table 202 in which the input text Tx obtained by the reception unit 20 is stored. Figure 5 shows an example of the configuration of the text information table 202 in this embodiment. The text information table 202 is a collection of records containing an ID that uniquely identifies the input text Tx, a target image, and text information values. The ID may be the identification information of the user who entered the input text Tx. The target image is the identification information of the input image Pf that was the target of the input text Tx.

[0067] The text information stores the input text Tx entered by the user. This input text Tx stores the text that the user entered using the UI when they input using the input device 14 or the imaging device 30. When storing this information, the reception unit 20 may provide the input text Tx to an appropriate morphological analysis engine to extract one or more words and store these words.

[0068] The method for receiving input images Pf and input text Tx in the reception unit 20 is not particularly limited, but includes the method of acquiring them by reading the photographic print of the image taken by the user terminal 10 or the shooting device 30 using the camera unit. In addition, the reception unit 20 may acquire images by downloading image data from an external device or a web server via the network N.

[0069] (Generation Unit) The generation unit 21 inputs the input image Pf (conceptually including other images generated and processed based on the input image Pf) and input text Tx obtained by the reception unit 20 to the generation AI 211 or generation AI server 40, and generates a shooting support image Ps that serves as a reference during shooting, helping to obtain an image that matches the image indicated by the input text Tx for the target to be photographed (place, facility, subject, etc.) indicated by the input image Pf. This shooting support image Ps is stored in the "Shooting Support Image" column of the image table 221 (see Figure 6).

[0070] Figure 6 shows an example of the configuration of the image table 221. This image table 221 is a collection of records that include an ID that identifies the shooting support image Ps, the input image Pf used to generate the shooting support image Ps, file data of one or more shooting support images, the selection result, and the value of the shooting advice. Of these, the selection result is set to "Y" if the user accepts the shooting support image Ps, and to "N" if they do not accept it. The shooting advice is an advice statement for shooting generated by the generation AI 211 (or generation AI server 40) based on the shooting support image Ps.

[0071] An example of such shooting advice text, or shooting advice M1, is shown in Figure 9. The shooting advice M1 shown on screen G20 in Figure 9 is a sentence such as, "Please find the spot where the cherry blossom branches appear largest in the foreground. We recommend using a telephoto lens to focus on the cherry blossoms in the foreground." The generating AI 211 or generating AI server 40 that generates the shooting advice M1 generates information such as the search for the shooting location (e.g., the spot where the cherry blossom branches appear largest in the foreground), the equipment to be used (e.g., telephoto lens), and the shooting conditions (e.g., focus on the cherry blossoms in the foreground) for the subject (e.g., cherry blossom branches, shrine gate) in the shooting support image Ps.

[0072] Therefore, the generating AI 211 and the generating AI server 40 are trained models that have already undergone machine learning using training data that combines a specific subject captured in an image (e.g., cherry blossom branches and a torii gate) in the shooting support image Ps, the composition in the shooting support image Ps (e.g., cherry blossom branches extending from left to right on the screen, with a torii gate visible in the background), the shooting conditions (e.g., the torii gate in the background is blurred), and text for advice (appropriate advice corresponding to the shooting support image Ps, considered by an expert).

[0073] The above-mentioned shooting support image Ps provides information that suggests the subject to be photographed, the composition of the photograph, etc., when the user actually goes to a shooting location corresponding to or similar to the subject indicated by the above-mentioned input image Pf. Note that the input image Pf may include not only images taken by the user, but also those generated by inputting prompts specifying user-desired conditions into the generation AI 211.

[0074] In the generation unit 21, the generation AI 211 (or generation AI server 40) generates, for example, an image representing the events described in the input text Tx with respect to the subject to be photographed in the input image Pf, as a shooting support image Ps. Therefore, the generation AI 211 (or generation AI server 40) becomes a trained model that has already undergone machine learning using training data consisting of text (input text Tx) describing the impression of the photographed image desired by the user regarding a specific subject to be photographed that is captured in the image (input image Pf), and an image for shooting support (shooting support image Ps) created by an expert with knowledge of the subject and the above impression.

[0075] The subjects and backgrounds included in the above images may include, for example, buildings (e.g., historical buildings, shrines and temples, famous commercial facilities, amusement facilities, etc.), terrain (e.g., mountains, hills, sea, rivers), natural objects (e.g., trees, flowers, animals, insects), people (e.g., children, athletes, women in kimonos, etc.), or actual names of individuals (e.g., Imperial Palace, National Diet Building, Meiji Shrine, Senso-ji Temple, Mount Fuji, Northern Alps, Kujukuri Beach, Tama River, cherry blossoms, autumn leaves, cats, etc.). For this reason, the generating AI 211 (or generating AI server 40) is assumed to have already learned the correspondence between the characteristics such as shape, color, and size of buildings, terrain, natural objects, and people that can be recognized from images, and actual buildings, terrain, natural objects, and people. Of course, it is preferable to include location information of the subjects in this learning process (e.g., coordinate system values ​​on an electronic map, latitude and longitude information, address information, etc.).

[0076] Furthermore, it is preferable that the generation AI 211 in the generation unit 21 performs a conversion process on the generated shooting support image Ps (which may be a photorealistic image at this point) when generating the shooting support image Ps, thereby generating a non-photorealistic shooting support image Ps.

[0077] The above conversion process involves applying a pre-stored style conversion filter to a photorealistic image, thereby converting the outlines of the depicted objects to the thickness and color tone of a paintbrush, and transforming each surface of the depicted object to appear as if it were painted with oil paint using a paintbrush. This process converts the image to a painterly style. The above conversion process also includes a process to change the touch of the photorealistic shooting support image Ps to that of anime or manga (a touch change process). Furthermore, the above conversion process includes a color reduction process for the photorealistic shooting support image Ps.

[0078] If the shooting support image Ps is a photorealistic image, the image the user sees when looking through the camera's viewfinder at the actual shooting location will be almost identical to the shooting support image Ps. This makes it easy for the user to take the same picture as the shooting support image Ps without thinking, simply by pressing the shutter button. On the other hand, if the shooting support image Ps is a non-photorealistic image after the above conversion process, the user viewing it can easily recognize that it is a shooting support image and is different from the image obtained when shooting at the actual location. In that case, the user can interpret the shooting support image Ps in their own way, apply their originality to the composition and shooting conditions, and create their own work that is different from the shooting support image Ps.

[0079] Furthermore, the generation unit 21 may generate multiple shooting support images Ps when generating the above-mentioned shooting support images Ps. In this case, the user does not need to refer to all of the multiple shooting support images Ps, but rather views and confirms them on the user terminal 10 or shooting device 30 and selects the one that best suits their image. Of course, the user may also select (i.e., deem suitable as a shooting support image Ps) from only one shooting support image Ps presented.

[0080] The selected shooting support images Ps are recognized by the decision unit 22 as the determined image Pk. As will be described later, the decision unit 22 generates shooting advice M2, M3, etc., based on the determined image Pk, for example, using the generation AI 211 or the generation AI server 40, and outputs these through the output unit 23. Of course, the generation of such shooting advice M2, M3, etc., may be performed in the same way even if there is only one shooting support image Ps.

[0081] (Decision Unit) The decision unit 22 is a functional unit that presents, for example, one or more shooting support images Ps generated by the generation unit 21 to the user via the output unit 23, identifies the one selected by the user from among the shooting support images Ps as the decision image Pk (if there is only one shooting support image Ps, it can remain as the decision image Pk), and generates shooting advice M1 to M3 based on this decision image Pk.

[0082] Therefore, the decision unit 22 displays the above-mentioned shooting support image Ps on the display of the output device 15 or the shooting device 30 in a selectable format and accepts the user's selection. The decision unit 22 then stores the value "Y" in the "Selection Result" column of the image table 221 for the shooting support image Ps that has been accepted for selection.

[0083] Furthermore, the decision unit 22 generates an advice image Pa and shooting advice M1 to M3 using the generation AI 211 or generation AI server 40 based on the decision image Pk selected by the user (see Figures 9 and 12). Of these, the advice image Pa is an image that presents the shooting location, shooting direction, etc., in order to realize the composition and shooting conditions indicated by the decision image Pk.

[0084] Therefore, the determination unit 22 extracts base images related to the shooting location and the facility being photographed, which the generation unit 21 has recognized from the input image Pf, from a group of images previously collected from, for example, websites or electronic map services on the network N, using, for example, a search with the location name or facility name indicated by the supplementary information of each image as a key, or by matching the shooting location or facility obtained through image recognition.

[0085] Alternatively, the decision unit 22 may generate a base image relating to the shooting location or the facility being photographed, as recognized from the input image Pf, for example, using the generation AI 211 or the generation AI server 40. In this case, the generation AI 211 or the generation AI server 40 is a so-called large-scale language model that can generate the base image in response to input prompts specifying the location or facility name and a viewpoint from which to view the location or facility (for example, generated by the decision unit 22 by setting the location or facility name and viewpoint values ​​in a template).

[0086] Furthermore, the determination unit 22 estimates in the base image locations where the subject and background in the determined image Pk appear in the same arrangement and size as in the determined image Pk. In the example of Figure 12, it would estimate locations where a photograph can be taken with a section of the cherry tree-lined path leading to the shrine (e.g., the tips of the blossoming branches) in the foreground and the top of the torii gate on the path in the background.

[0087] The estimation of locations where such photography can be performed may be carried out by the generating AI 211 or the generating AI server 40. In this case, the generating AI 211 and the generating AI server 40 are assumed to have already performed machine learning using, for example, a set of training data consisting of an image of a certain subject, another image of the same subject, and a suitable shooting point for the subject in the space indicated by the other image (a point determined and set by an expert). Therefore, by inputting the determined image Pk and the base image into the generating AI 211 or the generating AI server 40, it becomes possible to identify a suitable shooting point in the base image.

[0088] Furthermore, the decision unit 22 generates an advice image Pa and shooting advice M2 and M3 using the generation AI 211 or generation AI server 40 based on the decision image Pk selected by the user and the base image (see Figure 12). Of these, the advice image Pa is an image that displays the shooting location, shooting direction, etc., necessary to realize the composition and shooting conditions indicated by the decision image Pk, using round objects G41 and arrow objects G42 placed in the base image.

[0089] Furthermore, shooting advice M2 and M3 are explanatory texts regarding the composition and shooting conditions shown in the final image Pk among the shooting support images Ps, and also supplement the advice image Pa mentioned above. Shooting advice M2, shown on screen G40 in Figure 12, reads, "Location P is a candidate shooting location. We recommend a position where the branches of beautifully blooming cherry blossoms extend towards the approach to the shrine, with the torii gate in the background." Shooting advice M3 reads, "Please take the photo from the south side between 12:00 and 14:00 when the weather at the location is sunny."

[0090] The generating AI 211 or generating AI server 40, which generates the above-mentioned shooting advice M2 and M3, generates information such as the search for the shooting location (e.g., a position where the beautifully bloomed cherry blossom branches extend towards the approach to the shrine with the torii gate in the background) and the shooting conditions (e.g., from the south side during the time between 12:00 and 14:00 when the weather is sunny) for the subject in the determined image Pk (e.g., a branch of a cherry tree in full bloom, a torii gate). The shooting advice M2 and M3 are stored in the "Shooting Advice" column of the record related to the corresponding shooting support image Ps in the image table 221.

[0091] Therefore, the generating AI 211 and the generating AI server 40 are trained models that have already undergone machine learning using training data that combines the composition of a specific subject captured in an image (decision image Pk) (e.g., branches of cherry blossoms in bloom and a torii gate) in the decision image Pk (e.g., branches of cherry blossoms in bloom extending towards the approach to the shrine, with a torii gate in the background), the shooting conditions (e.g., from the south side between 12:00 and 14:00 when the weather is sunny), and text for advice (appropriate advice corresponding to the decision image Pk, considered by someone with expertise).

[0092] (Output Unit) The output unit 23 is a functional unit that displays the input image Pf, shooting support image Ps, decision image Pk, advice image Pa, and shooting advice M1 to M3 obtained from the reception unit 20, generation unit 21, and decision unit 22 on an output device 15 such as a display. For this purpose, the output unit 23 appropriately accesses the input image table 201, text information table 202, and image table 221, and appropriately retrieves and outputs information and data in response to user requests or the arrival of predetermined timings.

[0093] The output method in the output unit 23 is not particularly limited, but may include, for example, displaying various images and information on the output device 15, printing with a printer, transmitting to other users or systems, and providing as commercial products. The output format as commercial products may include media consisting of one or more pages or cards on which images are posted, such as albums, photobooks, postcards, message cards, electronic albums, and bromide prints.

[0094] [Example Flowchart of the Method for Generating Shooting Support Information] Next, as an example of the operation of the user terminal 10 (shooting support information generation device) in this embodiment, the flowchart of information processing using the terminal will be described. The flowchart described below uses the shooting support information generation method of the present invention. In other words, each step in the flowchart described below corresponds to a component of the shooting support information generation method of the present invention. Note that the flowchart below is merely an example, and some steps in the flowchart may be deleted, new steps may be added to the flowchart, or the execution order of two steps in the flowchart may be changed, without departing from the spirit of this embodiment.

[0095] Each step in the shooting support information generation flow according to this embodiment is performed by the processor 11 of the user terminal 10 in the order shown in Figure 7. In other words, in each process of the flow, the processor 11 executes the data processing defined in the application program for information processing, which corresponds to each step in Figure 7.

[0096] To explain in more detail, in the flow according to this embodiment, first, the reception unit 20 acquires the input image Pf by taking a picture with the shooting unit of the shooting device 30 or input device 14, or via the communication device 16, and stores it in the input image table 201 (S1). An example of the input image Pf obtained in this way is shown in screen G10 of Figure 8.

[0097] In the case of screen G10, the user clicks the capture button G111 on the image addition button G11 to input the input image Pf by capturing an image with the capture unit or capture device 30 provided on the user terminal 10. Alternatively, the user clicks the image selection button G112 to input a previously captured image, which is already held in the input image table 201 or image table 221, as the input image Pf.

[0098] The input image Pf mentioned above could be an overhead shot of the subject the user plans to photograph (e.g., the main subject or background, such as the temple gate, torii gate, or cherry blossom trees at a shooting location like Senso-ji Temple or Meiji Jingu Shrine) (First Information).

[0099] In addition, the reception unit 20 may generate the input image Pf using the generation AI 211 instead of acquiring the input image Pf by taking a photograph in S1 above. In that case, the reception unit 20 acquires a prompt entered by the user who wishes to generate an image from the keyboard of the input device 14 or via the communication device 16, and inputs this to the generation AI 211 to generate the input image Pf.

[0100] Furthermore, the reception unit 20 acquires input text Tx from the keyboard of the input device 14 or via the communication device 16 in order to generate the shooting support image Ps, and stores this in the text information table 202 (S2). The input text Tx consists of information (second information) that describes the impression or image of the image obtained from the actual shooting by the user.

[0101] An example of the input text Tx obtained in this way is shown in screen G10 of Figure 8. In the example on screen G10, the user's input action of input text Tx is accepted in the text input field G12, and the text "A spring-like, Japanese-style photo with cherry blossoms as the main subject" is obtained. If there are no problems with the input up to this point, the user clicks the OK button G13 to proceed with the process.

[0102] Next, the generation unit 21 inputs the input image Pf (conceptually including other images generated and processed based on the input image Pf) and input text Tx obtained by the reception unit 20 to the generation AI 211 or generation AI server 40, and generates a shooting support image Ps that helps obtain an image that matches the image indicated by the input text Tx for the target to be photographed (place, facility, subject, etc.) indicated by the input image Pf (S3). The generation unit 21 stores this shooting support image Ps in the "Shooting Support Image" column of the image table 221. The output unit 23 then displays the shooting support image Ps on the output device 15 or the shooting device 30.

[0103] Figure 9 shows an example of the generation of a shooting support image Ps. This shooting support image Ps is based on the input text Tx, "A spring-like, distinctly Japanese photograph with cherry blossoms as the main subject," and has a composition with a "shrine" and "torii gate" in the background, as indicated by the input image Pf. The process by which the generation AI 211 and the generation AI server 40 generate such shooting support images Ps, as well as the machine learning content of the learning models of the generation AI 211 and the generation AI server 40, have already been described.

[0104] The example of the shooting support image Ps shown in Figure 9 is an image of cherry blossom branches and a torii gate depicted in a painterly style. In other words, the generation AI 211 in the generation unit 21 applies a filter that corresponds to the conversion process to a painterly style as a style conversion filter to the generated shooting support image Ps (which at this point may be a photorealistic image or the input image Pf itself). As a result, the shooting support image Ps is an image that looks like it was painted as an oil painting, that is, a non-photorealistic image.

[0105] The above conversion process can be implemented by applying a pre-stored style conversion filter to a photorealistic image. In this case, the style conversion filter may include a filter that corresponds to the above-mentioned conversion to a painterly style, as well as a filter that changes the photorealistic shooting support image Ps to an anime or manga-like style, and a filter that performs color reduction on the photorealistic shooting support image Ps.

[0106] The user can view the above-mentioned shooting support image Ps on screen G20, and if they feel something is wrong or unsatisfactory, they can click the regenerate button G22 to request the generation unit 21 to regenerate the shooting support image Ps. In this case, upon receiving the click of the regenerate button G22 (S4:N), the generation unit 21 returns to processing S3 and executes the generation of the shooting support image Ps again.

[0107] On the other hand, if the user does not feel any discomfort or dissatisfaction with the above-mentioned shooting support image Ps and agrees, they click the OK button G23 to proceed with the process. In this case, the decision unit 22 receives the click of the OK button G23 on the screen G20 (S4: Y) and executes the generation of shooting advice M1 by the generation AI 211 or the generation AI server 40 (S5). At this time, the decision unit 22 sets the value of "Y" in the "Selection Result" column of the image table 221 to indicate that the user has accepted the above-mentioned shooting support image Ps. The output unit 23 then displays the shooting advice M1 on the output device 15 or the shooting device 30.

[0108] Furthermore, as shown in Figure 9, the decision unit 22 displays the generated shooting advice M1, "Please find the spot where the cherry blossom branches appear largest in the foreground. We recommend using a telephoto lens to focus on the cherry blossoms in the foreground," on the display area G21 of the screen G20 of the output device 15 or the shooting device 30, and then terminates this flow.

[0109] This shooting advice M1 provides information such as the location for the shot (e.g., the spot on the approach to Meiji Jingu Shrine where the cherry blossom branches appear largest), the equipment to be used (e.g., telephoto lens), and the shooting conditions (e.g., focus on the cherry blossoms in the foreground) for the subject in the shooting support image Ps (e.g., cherry blossom branches, shrine gate). The determination unit 22 stores the generated shooting support image Ps in the image table 221 and the shooting advice M1 in the text information table 202.

[0110] As previously described, the process by which the generating AI 211 and the generating AI server 40 generate this shooting advice M1, as well as the machine learning content of the learning models of the generating AI 211 and the generating AI server 40, are as follows. The shooting advice M1 is guidance information regarding the user's shooting actions based on the shooting support image Ps. This guidance information may include information about at least one of the following regarding the shooting support image Ps selected by the user: the subject to be photographed (e.g., the main gate of Senso-ji Temple, the torii gate of Meiji Jingu Shrine, the row of cherry trees along the approach), the shooting location (e.g., the approach to Senso-ji Temple or Meiji Jingu Shrine, below the torii gate, etc.), the equipment used for shooting (e.g., a zoom lens, etc.), the shooting conditions (e.g., a branch of a blooming cherry tree as the subject, with a torii gate in the background), and the shooting environment (e.g., between 12:00 and 14:00, sunny, etc.).

[0111] The above-mentioned shooting support image Ps provides information that suggests the subject to be photographed, the composition of the photograph, etc., when the user actually goes to a shooting location corresponding to or similar to the subject indicated by the above-mentioned input image Pf. Note that the input image Pf may include not only images taken by the user, but also those generated by inputting prompts specifying user-desired conditions into the generation AI 211.

[0112] [Regarding the processing associated with the generation of multiple shooting support images] Figure 10 is a diagram illustrating the flow of the shooting support information generation method in this embodiment. The generation unit 21 may generate multiple shooting support images Ps when generating the above-mentioned shooting support images Ps, and the output unit 23 may display them on the output device 15 or the shooting device 30 (S10). In this case, the user does not refer to all of the multiple shooting support images Ps, but rather views and confirms the multiple shooting support images Ps on the user terminal 10 or the shooting device 30 and selects the one that best suits their image. Of course, the user may also select (i.e., deem suitable as a shooting support image Ps) from only one shooting support image Ps presented.

[0113] The decision unit 22 then accepts the user's selection via the screen G30 displayed by the output unit 23 on the output device 15 or the shooting device 30 (S11). In this case, the decision unit 22 recognizes the selected shooting support image Ps as the decision image Pk. In the example of screen G30 shown in Figure 11, four shooting support images Ps are displayed, and a checkbox G33 for accepting user selection operations is placed below each shooting support image Ps.

[0114] Therefore, the user checks the checkbox G33 for the image they prefer or that gives them the desired impression from among the four shooting support images Ps, and clicks the OK button G32. On the other hand, if none of the four shooting support images Ps give the user a preferred or desired impression, the user clicks the regenerate button G31.

[0115] If the regeneration button G31 is clicked on screen G30 (S12:N), the decision unit 22 returns to processing S10 and executes the generation of multiple shooting support images Ps again. On the other hand, if the OK button G32 is clicked on screen G30 (S12:Y), the decision unit 22 recognizes the shooting support image Ps selected by the user as the decision image Pk, and based on this, generates an advice image Pa and shooting advice M2 to M3 using the generation AI 211 or the generation AI server 40 (S13, S14).

[0116] The output unit 23 displays the advice image Pa and shooting advice M2 and M3 generated in S13 and S14 on the output device 15 and the screen G40 (Figure 12) of the shooting device 30. Of these, the advice image Pa is an image that presents the shooting location and shooting direction, etc., in order to realize the composition and shooting conditions indicated by the decision image Pk. The advice image Pa displayed on the screen G40 as exemplified in Figure 12 is an image in which the shooting location and shooting direction, etc., in order to realize the composition and shooting conditions indicated by the decision image Pk are displayed using round objects G41 and arrow objects G42 placed in the base image.

[0117] Furthermore, shooting advice M2 and M3 are explanatory texts regarding the composition and shooting conditions shown in the final image Pk among the shooting support images Ps, and also supplement the advice image Pa mentioned above. Shooting advice M2, shown on screen G40 in Figure 12, reads, "Location P is a candidate shooting location. We recommend a position where the branches of beautifully blooming cherry blossoms extend towards the approach to the shrine, with the torii gate in the background." Shooting advice M3 reads, "Please take the photo from the south side between 12:00 and 14:00 when the weather at the location is sunny."

[0118] The generating AI 211 or generating AI server 40, which generates the above-mentioned shooting advice M2 and M3, generates information such as the search for the shooting location (e.g., a position where the beautifully bloomed cherry blossom branches extend towards the approach to the shrine with the torii gate in the background) and the shooting conditions (e.g., from the south side during the time between 12:00 and 14:00 when the weather is sunny) for the subject in the determined image Pk (e.g., a branch of a cherry tree in full bloom, a torii gate). The shooting advice M2 and M3 are stored in the "Shooting Advice" column of the record related to the corresponding shooting support image Ps in the image table 221.

[0119] The user can view the advice image Pa and shooting advice M2 and M3 displayed on screen G40 to understand various information about the shrine approach where the photo will be taken, such as the shooting location, subject, and shooting conditions. If the user does not fully understand the information on screen G40, or has any concerns or dissatisfaction with the advice image Pa or the final image Pk, they can click the back button G43 to return to step S10 in the flow chart of Figure 10. On the other hand, if the user fully understands the shooting location, subject, shooting conditions, etc., after viewing screen G40, they can click the OK button G44. The decision unit 22 then terminates this flow chart upon receiving this click.

[0120] Although specific embodiments of the present invention have been described above, these embodiments are merely examples given to facilitate understanding of the present invention and do not limit it. That is, the present invention can be modified or improved from the embodiments described below, without departing from its spirit. Furthermore, the present invention includes equivalents thereof. Moreover, embodiments of the present invention may include forms that combine the above embodiments with one or more of the following modifications.

[0121] (Regarding the computer constituting the shooting support information generation device) In the above embodiment, the shooting support information generation device of the present invention is configured with a computer used directly by the user, such as a user-owned PC (Personal Computer). However, it is not limited to this, and the shooting support information generation device of the present invention may be configured with a computer that can be used indirectly by the user, for example, the generation AI server 40. Here, the generation AI server 40 may be, for example, a server computer for cloud services, specifically a server computer for ASP (Application Service Provider), SaaS (Software as a Service), PaaS (Platform as a Service), or IaaS (Infrastructure as a Service). In this case, when the user inputs the necessary information on the user terminal 10 owned by the user, the generation AI server 40 performs various processes (calculations), including image generation, based on the input information, and the calculation results are output on the user terminal 10. In other words, the functions of the generation AI server 40, which constitutes the shooting support information generation device of the present invention, can be used on the user terminal 10. Alternatively, the shooting support information generation device may be configured using a shooting device 30 or the like, in addition to the PC or server computer mentioned above.

[0122] (Regarding the processing) In this embodiment, each process is performed on any computer. Furthermore, any computer may perform these processes using a processor, a program, or a combination thereof. Any computer may be a general-purpose computer, a computer designed for a specific purpose, a workstation, or any other hardware element capable of running a program.

[0123] (Regarding the Processor) The processor in this embodiment may be composed of one or more hardware components, and the type of hardware is not limited. For example, the processor may be composed of programmable logic devices such as a CPU (Central Processing Unit), MPU (Micro Processing Unit), FPGA (Field Programmable Gate Array), dedicated circuits for executing specific processes such as an ASIC (Application Specific Integrated Circuit), GPU (Graphic Processing Unit), or NPU (Neural Processing Unit). The processor also has various parts (Units) or means (Means) that execute the various processes in this embodiment. Furthermore, the type of hardware may be a combination of different types of hardware. When multiple hardware components are configured to execute one or more processes of a processor, these components may reside in physically separate devices or in the same device. Furthermore, in any embodiment, the order of the processes performed by the processor is not limited to the order described above and may be changed as appropriate. The hardware components are composed of electrical circuits (circuits) and the like, which are combinations of circuit elements such as semiconductor elements.

[0124] (Regarding the configuration) Furthermore, this embodiment may be implemented by hardware, software, firmware, microcode, or a combination thereof. The software, firmware, and microcode are composed of a program. The program may also be, for example, a group of program modules, each of which may be implemented by a processor configured to perform its respective function. The program may be program code or multiple code segments stored on one or more non-temporary computer-readable media (e.g., storage media or other storage). The program may be divided and stored on multiple non-temporary computer-readable media located on devices that are physically separated from each other. The program code or code segment may represent any combination of procedures, functions, subprograms, routines, subroutines, modules, software packages, classes, or instructions, data structures, or program statements. The program code or code segment may be connected to other code segments or hardware circuits by sending and receiving information, data, arguments, parameters, or memory contents.

[0125] N Network 5 Shooting Support Information Generation System 10 User Terminal (Shooting Support Information Generation Device) 11 Processor 12 Auxiliary Storage Device 121 Program 13 Main Storage Device 14 Input Device 15 Output Device 16 Communication Device 20 Reception Unit 201 Input Image Table 202 Text Information Table 21 Generation Unit 211 Generation AI 22 Decision Unit 221 Image Table 23 Output Unit 30 Shooting Device 40 Generation AI Server Pf Input Image (First Information) Tx Input Text (Second Information) Ps Shooting Support Image Pk Decision Image Pa Advice Image M1-M3 Shooting Advice

Claims

1. A shooting support information generation device equipped with a processor, wherein the processor receives input of first information relating to shooting, receives input of second information relating to the image of a captured image by the user, and generates a shooting support image using an image generation model based on the first information and the second information.

2. The shooting support information generating device according to claim 1, wherein the first information is information relating to the object to be photographed.

3. The shooting support information generation device according to claim 2, wherein the first information is information relating to the subject.

4. The shooting support information generation device according to claim 1, wherein the processor generates a plurality of shooting support images using an image generation model based on the first information and the second information.

5. The image generation model is a trained model, as described in claim 1, for the shooting support information generation device.

6. The shooting support information generation device according to claim 1, wherein the processor outputs the shooting support image to a display device.

7. The shooting support image is a non-photorealistic image, as described in claim 1, for the shooting support information generation device.

8. The shooting support information generation device according to claim 7, wherein the processor inputs the first information and the second information to an image generation model to generate the non-photorealistic image.

9. The shooting support information generation device according to claim 7, wherein the non-photorealistic image has a different style from the image that can ultimately be captured or acquired based on the shooting support image.

10. The shooting support information generation device according to claim 9, wherein the processor applies a transformation process to the image that can be ultimately captured or acquired, which is generated by the image generation model, to change the style of the non-photorealistic image to the different style.

11. The shooting support information generation device according to claim 10, wherein the processor applies a conversion process to the image that can be ultimately captured or acquired to change the style of the non-photorealistic image to the different style.

12. The shooting support information generation device according to claim 10, wherein the processor applies a touch-change conversion process to the image that can be ultimately captured or acquired, thereby changing the style of the non-photorealistic image to the different style.

13. The shooting support information generation device according to claim 10, wherein the processor applies a color reduction conversion process to the image that can be ultimately captured or acquired, thereby changing the style of the non-photorealistic image to the different style.

14. The shooting support information generation device according to claim 1, wherein the processor accepts input of information relating to at least one of the shooting location and the subject as input of the first information.

15. The shooting support information generation device according to claim 1, wherein the processor accepts image information obtained by shooting as input of the first information.

16. The image information obtained by the aforementioned shooting is an image taken at a shooting location necessary for shooting support, as described in claim 15.

17. The shooting support information generation device according to claim 4, wherein the processor generates guidance information regarding shooting actions based on a shooting support image selected by the user from among the plurality of shooting support images.

18. The shooting support information generating device according to claim 17, wherein the processor generates information as guidance information regarding at least one of the following for a shooting support image selected by the user: the target to be photographed, the shooting location, the equipment used for shooting, the shooting conditions, and the shooting environment.

19. The shooting support information generation device according to claim 17, wherein the processor outputs the guidance information to a display device.

20. A method for generating shooting support information, comprising: a step of receiving input of first information relating to shooting by a processor; a step of receiving input of second information relating to the image of a captured image by a user by a processor; and a step of generating a shooting support image by an image generation model based on the first information and the second information by a processor.

21. A program for causing a computer to perform each step included in the method for generating imaging support information according to claim 20.

22. A computer-readable recording medium on which a program is recorded causing a computer to perform each step included in the method for generating photographic support information according to claim 20.

Images