KR-20260067584-A - DEVICE, METHOD AND COMPUTER PROGRAM FOR GENERATING 3D IMAGE DATA FROM 2D IMAGE DATA

KR20260067584AKR 20260067584 AKR20260067584 AKR 20260067584AKR-20260067584-A

Abstract

A device for generating 3D image data from 2D image data includes an input unit that receives at least one vertex and a depth value for said at least one vertex for 2D image data, a depth map generating unit that generates a depth map of said 2D image data based on the depth value for said at least one vertex, a 3D image data generating unit that generates 3D image data from said 2D image data based on the depth map of said 2D image data, and a 3D image data correction unit that corrects pixel values of said 3D image data based on whether there is a correspondence between the depth value of said 2D image data and the depth value of said 3D image data.

Inventors

길종인

Assignees

주식회사 케이티

Dates

Publication Date: 20260513
Application Date: 20241106

Claims (17)

In a device for generating 3D image data from 2D image data, An input unit that receives at least one vertex and a depth value for said at least one vertex for 2D image data; A depth map generating unit that generates a depth map of the 2D image data based on a depth value for at least one vertex; A 3D image data generation unit that generates 3D image data from the 2D image data based on a depth map of the 2D image data; and A 3D image data correction unit that corrects the pixel values of the 3D image data based on whether there is a correspondence between the depth values of the 2D image data and the depth values of the 3D image data. A 3D image data generation device including
In Article 1, It further includes a dividing unit that divides the internal region of the 2D image data into a plurality of triangles based on at least one vertex, and A 3D image data generation device in which the depth map generating unit calculates weights for the plurality of target vertices based on depth values of the plurality of target vertices constituting the first triangle among the plurality of triangles.
In Article 2, The depth map generating unit calculates the depth value of a center point located inside the first triangle based on weights for the plurality of target vertices, and A 3D image data generating device that generates a depth map for the internal pixels of the first triangle based on the depth values of the plurality of target vertices and the depth values of the center point.
In Article 1, A 3D image data generating device wherein the 3D image data generating unit generates a depth map of the 3D image data by copying the depth map of the 2D image data.
In Article 4, The above 3D image data correction unit derives a first mapping result by mapping the pixel values of the 2D image data in the reverse direction from the pixel values of the 3D image data, and A 3D image data generating device that derives a second mapping result by forward mapping the pixel values of the 2D image data from the pixel values of the 3D image data.
In Article 5, The above 3D image data correction unit determines whether the pixel-wise depth values are identical through a comparison between the first mapping result and the second mapping result, and A 3D image data generation device that, as a result of judgment, derives mismapping pixels from the 3D image data in which the depth values per pixel are not the same.
In Article 6, A 3D image data generation device in which the 3D image data correction unit performs correction for the mismapping pixel based on the difference between the depth value of the pixel of the 3D image data and the depth value of the pixel of the 2D image data.
In Article 1, The above input unit receives camera viewpoint information for the 3D image data, and A 3D image data generating device further comprising an output unit that adjusts and outputs the viewpoint of the 3D image data based on the camera viewpoint information.
A method for generating 3D image data from 2D image data performed in a 3D image data generating device, A step of receiving at least one vertex and a depth value for said at least one vertex for 2D image data; A step of generating a depth map of the 2D image data based on a depth value for at least one vertex; A step of generating 3D image data from the 2D image data based on a depth map of the 2D image data; and A step of correcting the pixel values of the 3D image data based on whether there is a correspondence between the depth values of the 2D image data and the depth values of the 3D image data. A method for generating 3D image data including
In Article 9, A step of dividing the internal region of the 2D image data into a plurality of triangles based on at least one vertex; and A method for generating 3D image data, further comprising the step of calculating weights for a plurality of target vertices based on depth values of a plurality of target vertices constituting a first triangle among the plurality of triangles.
In Article 10, The step of generating a depth map of the above 2D image data is, A step of calculating the depth value of a center point located inside the first triangle based on weights for the plurality of target vertices; and A method for generating 3D image data, comprising the step of generating a depth map for the internal pixels of the first triangle based on the depth values of the plurality of target vertices and the depth values of the center point.
In Article 9, The step of generating the above 3D image data is, A method for generating 3D image data, comprising the step of copying the depth map of the 2D image data to generate the depth map of the 3D image data.
In Article 12, The above 3D image data correction unit derives a first mapping result by mapping the pixel values of the 2D image data in the reverse direction from the pixel values of the 3D image data, and A method for generating 3D image data, wherein a second mapping result is derived by mapping the pixel values of the 2D image data in the forward direction from the pixel values of the 3D image data.
In Article 13, The step of correcting the pixel values of the above 3D image data is, A step of determining whether the pixel-wise depth values are identical through a comparison between the first mapping result and the second mapping result; and A method for generating 3D image data, comprising the step of deriving mismapping pixels from the 3D image data in which the depth values per pixel are not identical, based on the result of judgment.
In Article 14, The step of correcting the pixel values of the above 3D image data is, A method for generating 3D image data, comprising the step of performing correction based on the difference between the depth value of the pixel of the 3D image data and the depth value of the pixel of the 2D image data for the above mismapping pixel.
In Article 9, A step of receiving camera viewpoint information for the above 3D image data; and A method for generating 3D image data, further comprising the step of adjusting and outputting the viewpoint of the 3D image data based on the camera viewpoint information.
In a computer program stored on a computer storage medium comprising a sequence of instructions for generating 3D image data from 2D image data, When the above computer program is executed by a computing device, For 2D image data, at least one vertex and a depth value for said at least one vertex are received as input, and A depth map of the 2D image data is generated based on the depth value for at least one vertex, and Based on the depth map of the above 2D image data, 3D image data is generated from the above 2D image data, and A computer program stored on a computer storage medium, comprising a sequence of instructions to correct pixel values of 3D image data based on whether there is a correspondence between the depth values of the 2D image data and the depth values of the 3D image data.

Description

Device, method and computer program for generating 3D image data from 2D image data The present invention relates to an apparatus, a method, and a computer program for generating 3D image data from 2D image data. 3D content is produced by designing a 3D model using a 3D modeling tool and then rendering it into an image. 3D models are classified into object models, which represent characters and objects, and space models, which represent spaces, such as rooms and building interiors. 3D content can be created through 3D production tools such as Maya and Blender, and in this regard, prior art Korean Registered Patent No. 10-2475520 discloses a method and system for converting 3D models for implementing a photorealistic metaverse. Previously, 3D content was produced by professionals such as 3D graphic designers who could handle 3D production tools, and general users faced difficulties in creating or editing 3D content because it was not easy for them to handle 3D production tools. Therefore, there was a need among general users for a method to easily create the 3D content they wanted without having to create 3D models themselves. FIG. 1 is a configuration diagram of a 3D image data generation device according to one embodiment of the present invention. FIG. 2 is an exemplary drawing for explaining the process of receiving a depth value for at least one vertex of 2D image data according to one embodiment of the present invention. FIG. 3 is an exemplary drawing for explaining the process of dividing an internal area of 2D image data into a plurality of triangles according to an embodiment of the present invention. FIG. 4 is an exemplary drawing for explaining the process of generating a depth map for the internal pixels of a first triangle according to an embodiment of the present invention. Figure 5 is a diagram illustrating the process of mapping pixel values of 2D image data in the forward direction from pixel values of conventional 3D image data. FIG. 6 is an exemplary drawing for explaining the process of mapping pixel values of 2D image data in reverse from pixel values of 3D image data according to one embodiment of the present invention. FIG. 7 is an exemplary diagram illustrating the process of performing correction for mis-mapped pixels through comparison between a first mapping result and a second mapping result according to an embodiment of the present invention. FIG. 8 is a flowchart of a method for generating 3D image data from 2D image data performed in a 3D image data generating device according to an embodiment of the present invention. Embodiments of the present invention are described below with reference to the attached drawings so that those skilled in the art can easily implement the invention. However, the present invention may be embodied in various different forms and is not limited to the embodiments described herein. Furthermore, in order to clearly explain the present invention in the drawings, parts unrelated to the explanation have been omitted, and similar parts throughout the specification are denoted by similar reference numerals. Throughout the specification, when a part is described as being "connected" to another part, this includes not only cases where they are "directly connected" but also cases where they are "electrically connected" with other elements interposed between them. Furthermore, when a part is described as "including" a component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components, and it should be understood that this does not preclude the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof. In this specification, the term "part" includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Additionally, one unit may be realized using two or more hardware, and two or more units may be realized by one hardware. Some of the operations or functions described in this specification as being performed by a terminal or device may instead be performed by a server connected to said terminal or device. Likewise, some of the operations or functions described as being performed by a server may also be performed by a terminal or device connected to said server. An embodiment of the present invention will be described in detail below with reference to the attached drawings. FIG. 1 is a configuration diagram of a 3D image data generation device according to an embodiment of the present invention. Referring to FIG. 1, the 3D image data generation device (100) may include an input unit (110), a segmentation unit (120), a depth map generation unit (130), a 3D image data generation unit (140), a 3D image data correction unit (150), and an output unit (160). The 3D image data generation device (100) proposed in the present invention receives at least one vertex and a depth value for at least one vert