Merging three-dimensional models based on confidence scores
First Claim
1. A method for merging a plurality of three-dimensional models, each generated from images of a camera having a different viewpoint, comprising:
- (a) determining a plurality of voxels in three-dimensional space;
for respective voxels in the plurality of voxels;
(b) determining a plurality of distance values, each distance value being a distance from the voxel to a corresponding three dimensional model from the plurality of three-dimensional models along a perspective of a camera model used to generate the three-dimensional model;
when (i) a first distance value from the plurality of distance values indicates that the distance between the voxel and the three dimensional model corresponding to the first distance value is within a threshold and (ii) a second distance value from the plurality of distance values indicates that the voxel is outside the threshold and above the three dimensional model corresponding to the second distance value;
(c) determining a first confidence score indicating a degree to which the perspective of the camera model of the three-dimensional model corresponding to the first distance value is oriented to face the voxel;
(d) determining a second confidence score indicating a degree to which the perspective of the camera model of the three-dimensional model corresponding to the second distance value is oriented to face the voxel; and
(e) determining whether to include a point corresponding to the voxel into a merged three-dimensional model based, at least in part, on the determined first and second confidence scores such that, when the second confidence score is greater than the first confidence score by a predetermined degree, the voxel is not included in the merged three dimensional model.
2 Assignments
0 Petitions
Accused Products
Abstract
In an embodiment, a method merges a plurality of three-dimensional models, each having been generated from images of a camera having a different viewpoint. For respective voxels in a plurality of voxels, a plurality of distance values are determined. Each determined distance value is a distance from the voxel to a three dimensional model from the plurality of three-dimensional models along a perspective of a camera model used to generate the three-dimensional model. When at least one of the determined distance values indicates that the distance between the voxel and the three dimensional model exceeds a threshold and the voxel is located above the corresponding three-dimensional model, a confidence score is determined indicating a degree to which the perspective of the camera model of the corresponding three-dimensional model is oriented to face the voxel. Based on the determined confidence score, the voxel into a merged three-dimensional model is determined.
16 Citations
21 Claims
-
1. A method for merging a plurality of three-dimensional models, each generated from images of a camera having a different viewpoint, comprising:
-
(a) determining a plurality of voxels in three-dimensional space;
for respective voxels in the plurality of voxels;(b) determining a plurality of distance values, each distance value being a distance from the voxel to a corresponding three dimensional model from the plurality of three-dimensional models along a perspective of a camera model used to generate the three-dimensional model; when (i) a first distance value from the plurality of distance values indicates that the distance between the voxel and the three dimensional model corresponding to the first distance value is within a threshold and (ii) a second distance value from the plurality of distance values indicates that the voxel is outside the threshold and above the three dimensional model corresponding to the second distance value; (c) determining a first confidence score indicating a degree to which the perspective of the camera model of the three-dimensional model corresponding to the first distance value is oriented to face the voxel; (d) determining a second confidence score indicating a degree to which the perspective of the camera model of the three-dimensional model corresponding to the second distance value is oriented to face the voxel; and (e) determining whether to include a point corresponding to the voxel into a merged three-dimensional model based, at least in part, on the determined first and second confidence scores such that, when the second confidence score is greater than the first confidence score by a predetermined degree, the voxel is not included in the merged three dimensional model. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. A system for merging a plurality of three-dimensional models each generated from images of a camera having a different viewpoint, comprising:
-
one or more processors; a memory coupled to the one or more processors; a voxel determination module configured to determine a plurality of voxels in three-dimensional space; a distance test module configured to, for respective voxels in the plurality of voxels, determine a plurality of distance values, each distance value being a distance from the voxel to a three dimensional model from the plurality of three-dimensional models along a perspective of a camera model used to generate the three-dimensional model, wherein the distance test module is implemented on the one or more processors; a confidence score module configured to, when (i) a first distance value from the plurality of distance values indicates that the distance between the voxel and the three dimensional model corresponding to the first distance value is within a threshold and (ii) a second distance value from the plurality of distance values indicates that the voxel is outside the threshold and above the three dimensional model corresponding to the second distance value; determine a first confidence score indicating a degree to which the perspective of the camera model of the three-dimensional model corresponding to the first distance value is oriented to face the voxel, and determine a second confidence score indicating a degree to which the perspective of the camera model of the three-dimensional model corresponding to the second distance value is oriented to face the voxel; and a point selector module configured to determine whether to include a point corresponding to the voxel into a merged three-dimensional model based, at least in part, on the determined first and second confidence scores such that, when the second confidence score is greater than the first confidence score by a predetermined degree, the voxel is not included in the merged three dimensional model. - View Dependent Claims (9, 10, 11, 12, 13, 14)
-
-
15. A computer program product including a non-transitory computer-readable medium having instructions stored thereon that, when executed by a computing device, cause the computing device to perform operations for merging a plurality of three-dimensional models each generated from images of a camera having a different viewpoint, the operations comprising:
-
(a) determining a plurality of voxels in three-dimensional space; for respective voxels in the plurality of voxels; (b) determining a plurality of distance values, each distance value being a distance from the voxel to a corresponding three dimensional model from the plurality of three-dimensional models along a perspective of a camera model used to generate the three-dimensional model; when (i) a first distance value from the plurality of distance values indicates that the distance between the voxel and the three dimensional model corresponding to the first distance value is within a threshold and (ii) a second distance value from the plurality of distance values indicates that the voxel is outside the threshold and above the three dimensional model corresponding to the second distance value; (c) determining a first confidence score indicating a degree to which the perspective of the camera model of the three-dimensional model corresponding to the first distance value is oriented to face the voxel; (d) determining a second confidence score indicating a degree to which the perspective of the camera model of the three-dimensional model corresponding to the second distance value is oriented to face the voxel; and (e) determining whether to include a point corresponding to the voxel into a merged three-dimensional model based, at least in part, on the determined first and second confidence scores such that, when the second confidence score is greater than the first confidence score by a predetermined degree, the voxel is not included in the merged three dimensional model. - View Dependent Claims (16, 17, 18, 19, 20, 21)
-
Specification