- Number
- 10832469
- Published
- 2020-11-10
- Filed
- 2018-08-06
- Assignee
- Disney Enterprises, Inc.
- Inventors
- Chapman; Steven M., Kosakura; Steven T., Popp; Joseph M., Patel; Mehul A.
- CPC
- G06V40/162; G06T17/05; G06T17/00; G06V10/56; G06V20/647; G06V10/82
- Verdict
- Low Notable software
- Source
- Google Patents · FreePatentsOnline
The keeper's note
CV technique optimizing images for 3D model construction (granted).
Abstract
Methods, systems, and computer readable media related to generating a three-dimensional model of a target object. A first source image, of a plurality of source images of a target object, is analyzed to identify a first region of the first image, the first region having attributes meeting one or more pre-defined criteria. The first region is marked for exclusion from use in generating a three-dimensional model of the target object. The three-dimensional model of the target object is generated using the plurality of source images. The marked first region is excluded in the generation of the three-dimensional model.
Background
BACKGROUNDField of the Invention(1) The present invention relates to construction of a three-dimensional model of an object.Description of the Related Art(2) A series of two dimensional images of an object can be used to construct a three-dimensional model of the object. But this process can be time consuming and computationally expensive, and can result in an inaccurate three-dimensional model. It is desirable to improve construction of a three-dimensional model from a series of two dimensional images.SUMMARY(3) Embodiments described herein include a method of generating a three-dimensional model of a target object. The method includes analyzing a first source image, of a plurality of source images of a target object, to identify a first region of the first image, the first region having attributes meeting one or more pre-defined criteria. The method further includes marking the first region for exclusion from use in generating a three-dimensional model of the target object. The method further includes generating the three-dimensional model of the target object using the plurality of source images. The marked first region is excluded in the generation of the three-dimensional model.(4) Embodiments described herein further include a computer program product for generating a three-dimensional model of a target object. The computer program product includes a computer-readable storage medium having computer-readable program code embodied therewith. The code, when executed by a p
Claims
1. A method of generating a three-dimensional model of a target object, comprising: analyzing a first source image, of a plurality of source images of a target object, to identify a first region of the first source image, the first region having attributes meeting one or more pre-defined criteria; marking the first region for exclusion from use in generating a three-dimensional point cloud for the target object and inclusion in generating one or more textures relating to the target object; and generating a three-dimensional model of the target object using the plurality of source images, comprising: generating the three-dimensional point cloud for the target object while excluding the first region; and generating the one or more textures relating to the target object using the first region.
9. A computer program product for generating a three-dimensional model of a target object, the computer program product comprising: a non-transitory computer-readable storage medium having computer-readable program code embodied therewith, wherein the program code, when executed by a processor, performs an operation, the operation comprising: analyzing a first source image, of a plurality of source images of a target object, to identify a first region of the first source image, the first region having attributes meeting one or more pre-defined criteria; marking the first region for exclusion from use in generating a three-dimensional point cloud for the target object and inclusion in generating one or more textures relating to the target object; and generating a three-dimensional model of the target object using the plurality of source images, comprising: generating the three-dimensional point cloud for the target object while excluding the first region; and generating the one or more textures relating to the target object using the first region.
15. A system, comprising: a processor; and a memory storing a program, which, when executed on the processor, performs an operation, the operation comprising: analyzing a first source image, of a plurality of source images of a target object, to identify a first region of the first source image, the first region having attributes meeting one or more pre-defined criteria; marking the first region for exclusion from use in generating a three-dimensional point cloud for the target object and inclusion in generating one or more textures relating to the target object; and generating a three-dimensional model of the target object using the plurality of source images, comprising: generating the three-dimensional point cloud for the target object while excluding the first region; and generating the one or more textures relating to the target object using the first region.