KR-102962335-B1 - IMAGE PROCESSING METHOD, INFORMATION PROCESSING DEVICE, AND COMPUTER PROGRAM

KR102962335B1KR 102962335 B1KR102962335 B1KR 102962335B1KR-102962335-B1

Abstract

When photographing an object and reconstructing a moving image using the captured image of the object, it enables efficient reconstruction processing. The image processing method for reconstructing a moving image comprises: a process in which a processing unit generates a first three-dimensional model data of the model included in the image from a plurality of images generated by capturing images of the exterior of the model from multiple directions by a shooting unit; a process in which the processing unit reconstructs the moving image by replacing the second three-dimensional model data with the first three-dimensional model data in a template data of the moving image configured to include the second three-dimensional model data in advance; and a process in which an output unit outputs information indicating the source of acquisition of the reconstructed moving image.

Inventors

기요미야 료타

Assignees

가부시키가이샤 반다이

Dates

Publication Date: 20260508
Application Date: 20230911
Priority Date: 20220913

Claims (15)

It is an image processing method that reconstructs moving images, and A process in which a processing unit generates first three-dimensional model data of the model included in the images from a plurality of images generated by capturing images of the exterior of the model from multiple directions by a capturing unit, and A processing unit, in a template data of a moving image configured to include a second three-dimensional model data in advance, a process of reconstructing the moving image by replacing the second three-dimensional model data with the first three-dimensional model data, and The output unit includes a process for outputting information indicating the source of acquisition of the reconstructed video image, and The above model is capable of changing movement or posture in three-dimensional space, and The above-mentioned video template data includes multiple template data prepared according to the type of model, and The above processing unit further includes a process of receiving the selection of one template data from the plurality of template data, and The types of the above-mentioned models include a first type of model having an exterior shape that is a reduced version of the life-size shape, and a second type of model having an exterior shape that is a deformed version of the life-size shape. In the above generating process, the first three-dimensional model data is generated by adjusting the size according to the content of the video image, and The above size adjustment is performed on the first three-dimensional model data of the same type of model as the type of model in the above-mentioned video template data that received the above selection, Image processing method.
In paragraph 1, The plurality of images above include markers for specifying the direction and position of the model, and An image processing method in which the first three-dimensional model data is generated by correcting the direction and position based on the marker.
delete
delete
delete
In paragraph 1, An image processing method in which the above-mentioned size adjustment is not performed on the first three-dimensional model data of a different type from the model of the above-mentioned template data of the above-mentioned video image.
In paragraph 1, In the template data of the above video, a recommended pose for the above model is associated, and An image processing method in which the above plurality of images are generated by photographing the appearance of the above model in the above recommended pose.
delete
In paragraph 1, An image processing method further comprising, upon receiving the selection of template data for the above-mentioned video image, a processing unit displaying a designation of a recommended pose for the above-mentioned video image on a display device.
In paragraph 1, An image processing method in which the above multiple directions are determined to encompass the entire perimeter of the above model.
In paragraph 1, An image processing method in which the above plurality of images are generated by the above-mentioned photographing unit photographing the above-mentioned model irradiated by a first light source and at least one second light source that cancels out the shadow caused by the irradiation light from the first light source.
In paragraph 1, An image processing method in which the processing unit further includes a process of receiving the plurality of images from the shooting unit.
In paragraph 1, An image processing method in which at least one of the position, movement, camera angle, and lighting in the three-dimensional space of the second three-dimensional model data is set in alignment with the time axis of the moving image.
A generating means for generating first three-dimensional model data of the model included in the images from a plurality of images generated by photographing the exterior of the model from a plurality of directions, and In template data of a moving image configured to include a second three-dimensional model data in advance, a reconstruction means for reconstructing the moving image by replacing the second three-dimensional model data with the first three-dimensional model data, and A control means for controlling the output of information indicating the source of acquisition of a reconstructed video image from an output unit, and A receiving means for receiving the selection of the above-mentioned video template data, and The above model is capable of changing movement or posture in three-dimensional space, and The above-mentioned video template data includes multiple template data prepared according to the type of model, and The types of the above-mentioned models include a first type of model having an exterior shape that is a reduced version of the life-size shape, and a second type of model having an exterior shape that is a deformed version of the life-size shape. The above-mentioned generating means generates the above-mentioned first three-dimensional model data by adjusting it to a size according to the content of the above-mentioned video image, and the size adjustment is performed on the above-mentioned first three-dimensional model data of a model of the same type as the type of model in the template data of the above-mentioned video image for which the above-mentioned receiving means received the selection. Information processing device.
A computer program stored on a computer-readable recording medium for executing an image processing method described in any one of claims 1, 2, 6, 7 and 9 through 13 on a computer.

Description

Image processing method, information processing device, and computer program The present invention relates to an image processing method, an information processing device, and a computer program. Patent Document 1 describes a technique for generating a texture from a group of captured images of an object captured from a plurality of shooting directions by a shooting unit, and mapping this texture to a primitive in virtual space to generate a virtual space image visible from a virtual camera in virtual space. FIG. 1 is a drawing illustrating an example of the configuration of an image processing system corresponding to an embodiment and a drawing illustrating an example of the hardware configuration of an information processing device (100). FIG. 2 is a drawing illustrating an example of the appearance of a model corresponding to an embodiment. FIG. 3 is a drawing illustrating an example of an image processing system implementation corresponding to an embodiment, and an example of an AR marker. FIG. 4 is a drawing illustrating an example of a data table data configuration corresponding to an embodiment. FIG. 5 is a flowchart corresponding to an example of processing for generating PV data corresponding to an embodiment. FIG. 6 is a flowchart corresponding to an example of shooting processing corresponding to an embodiment. FIG. 7 is a flowchart showing an example of processing for PV reconstruction corresponding to an embodiment. FIG. 8 is a drawing for explaining the shooting environment when taking an image of a model corresponding to an embodiment. FIG. 9 is a diagram illustrating a comparison example of output results when the conversion of a PV template corresponding to an embodiment is performed on virtual data and when it is performed on real data. Hereinafter, embodiments are described in detail with reference to the attached drawings. Furthermore, the following embodiments do not limit the invention with respect to the patent claims, and not all combinations of features described in the embodiments are essential to the invention. Two or more features among the multiple features described in the embodiments may be arbitrarily combined. Also, identical or similar configurations are assigned the same reference number, and redundant descriptions are omitted. Additionally, in each drawing, the up, down, left, and right front and back directions relative to the surface are defined as the up, down, left, and right front and back directions of the component (or part) in this embodiment, and are used for descriptions in the text. First, the configuration of an image processing system corresponding to the present embodiment will be described. FIG. 1 (A) is a diagram illustrating an example of the configuration of an image processing system (10) corresponding to the present embodiment. The image processing system (10) is configured such that a shooting unit (110), a support arm (120), a model support device (130), a display device (140), a printing device (150), etc. are connected to an information processing device (100). Furthermore, the system configuration is not limited to that shown in FIG. 1 (A), and the information processing device (100) may also be connected to an external server, a cloud server, etc., via a network. Such external server, etc., can perform at least some of the processing of the embodiment described below. The information processing device (100) controls the operation of at least one of the shooting unit (110), the support arm (120), and the model support device (130), and generates a plurality of images by shooting an item to be shot from any angle, and generates three-dimensional model data (main data) from the plurality of images. Then, by using a template (PV template) of a moving image (promotional video: PV data) containing pre-prepared virtual three-dimensional model data (virtual data), the PV data can be reconstructed by replacing and converting the virtual data of the PV template with the main data. In addition, the information processing device (100) can also function as an image processing device that generates an image displayed in a virtual space by using the generated main data as data for a virtual space. The image processing device may be prepared separately from the information processing device (100). In this embodiment, the item to be shot is an assembleable plastic model, an action figure (a figure equipped with movable joints), a toy, a doll, etc., and these are collectively referred to as "models." Furthermore, in the present embodiment, the term "promotional video (PV)" is not limited to video images intended for advertising, promotion, or sales promotion of the model being filmed, but refers to attractive video images using the model being filmed (such as short movies, movies, or demo videos, with no restrictions on the format or type of the video images). In the following description as well, "PV" or "promotional video" will be used as a general term encompas