发明名称 Systems and methods for merging textures
摘要 Examples disclose a method and system for merging textures. The method may be executable to receive one or more images of an object, identify a texture value for a point in a first image of the one or more images, and determine a metric indicative of a relation between a view reference point vector and a normal vector of a position of a point on the object relative to the image capturing device. Based on the metrics, the method may be executable to determine a weighted average texture value to apply to a corresponding point of a three-dimensional mesh of the object.
申请公布号 US9147279(B1) 申请公布日期 2015.09.29
申请号 US201313839508 申请日期 2013.03.15
申请人 Google Inc. 发明人 Bruce James R.;Frueh Christian;Poursohi Arshan
分类号 G06T15/04 主分类号 G06T15/04
代理机构 McDonnell Boehnen Hulbert & Berghoff LLP 代理人 McDonnell Boehnen Hulbert & Berghoff LLP
主权项 1. A method executed by a computing device, the method comprising: receiving, at the computing device, a plurality of images of an object; identifying (i) a first texture value for a point in a first image of the plurality of images of the object, and (ii) a second texture value for a respective point in a second image of the plurality of images of the object; identifying (i) a view reference point vector between the point in the first image and an image capturing device, and (ii) a respective view reference point vector between the respective point in the second image and the image capturing device; identifying a first normal vector of the point in the first image and a second normal vector of the respective point in the second image; determining a first metric based at least on: (i) a relation between the view reference point vector and the first normal vector, (ii) a distance between the point and the image capturing device, and (iii) a size of a surface area of the object as depicted in the first image; determining a second metric based at least on: (i) a respective relation between the respective view reference point vector and the second normal vector, (ii) a distance between the respective point and the image capturing device, and (iii) a size of a surface area of the object as depicted in the second image; and based on the first metric and the second metric, using the first texture value and the second texture value to determine a weighted average texture value to apply to a corresponding point of a three-dimensional (3D) mesh of the object.
地址 Mountain View CA US