High-Quality Stereo Reconstruction Featuring Depth Map Alignment and Outlier Identification
First Claim
1. A computer-implemented method for generating three-dimensional models, the method comprising:
- obtaining, by one or more computing devices, a plurality of images depicting a scene;
determining, by the one or more computing devices, a pose for each of the plurality of images;
determining, by the one or more computing devices, a depth map for each of the plurality of images such that a plurality of depth maps are determined, wherein each of the plurality of depth maps describes a plurality of points in three-dimensional space that correspond to objects in the scene;
aligning, by the one or more computing devices, the plurality of depth maps by transforming one or more of the plurality of depth maps so as to improve an alignment between the plurality of depth maps;
after aligning the plurality of depth maps, identifying, by the one or more computing devices, one or more of the plurality of points described by one or more of the plurality of depth maps as one or more outlying points; and
generating, by the one or more computing devices, a three-dimensional model of the scene based at least in part on the plurality of depth maps.
2 Assignments
0 Petitions
Accused Products
Abstract
A novel stereo reconstruction pipeline that features depth map alignment and outlier identification is provided. One example method includes obtaining a plurality of images depicting a scene. The method includes determining a pose for each of the plurality of images. The method includes determining a depth map for each of the plurality of images such that a plurality of depth maps are determined Each of the plurality of depth maps describes a plurality of points in three-dimensional space that correspond to objects in the scene. The method includes aligning the plurality of depth maps by transforming one or more of the plurality of depth maps so as to improve an alignment between the plurality of depth maps. The method includes identifying one or more outlying points. The method includes generating a three-dimensional model of the scene based at least in part on the plurality of depth maps.
33 Citations
20 Claims
-
1. A computer-implemented method for generating three-dimensional models, the method comprising:
-
obtaining, by one or more computing devices, a plurality of images depicting a scene; determining, by the one or more computing devices, a pose for each of the plurality of images; determining, by the one or more computing devices, a depth map for each of the plurality of images such that a plurality of depth maps are determined, wherein each of the plurality of depth maps describes a plurality of points in three-dimensional space that correspond to objects in the scene; aligning, by the one or more computing devices, the plurality of depth maps by transforming one or more of the plurality of depth maps so as to improve an alignment between the plurality of depth maps; after aligning the plurality of depth maps, identifying, by the one or more computing devices, one or more of the plurality of points described by one or more of the plurality of depth maps as one or more outlying points; and generating, by the one or more computing devices, a three-dimensional model of the scene based at least in part on the plurality of depth maps. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13)
-
-
14. One or more non-transitory computer-readable media storing instructions that, when executed by one or more processors, cause the one or more processors to perform operations, the operations comprising:
-
obtaining a plurality of depth maps, each of the plurality of depth maps describing a plurality of points in three-dimensional space that respectively correspond to locations of objects in a scene; iteratively transforming the plurality of depth maps to iteratively minimize an objective function, such that an alignment of the plurality of depth maps is improved; identifying one or more of the plurality of points of one or more of the plurality of depth maps as outlying points; and reducing an influence of each of the outlying points on the generation of a three-dimensional model from the plurality of depth maps; wherein the objective function comprises a sum, for all of a plurality of pairs of the depth maps that overlap one another, of a plurality of squared distances respectively between one or more of the plurality of points described by a source depth map of each pair of depth maps and one or more planes respectively associated with one or more of the plurality of points described by a target depth map of such pair of depth maps; and wherein the objective function allows for transformation of both the source depth map and the target depth map for each pair of depth maps. - View Dependent Claims (15, 16, 17)
-
-
18. A computing system comprising:
-
one or more computing devices respectively comprising one or more processors; and one or more non-transitory computer-readable media storing instructions that, when executed by the one or more processors, cause the one or more computing devices to perform operations, the operations comprising; bundle adjusting a plurality of images depicting a scene to obtain a pose for each image; performing a stereo algorithm to obtain a depth map for each image, such that a plurality of depth maps are obtained, wherein each depth map describes locations of a plurality of points in three-dimensional space; aligning the plurality of depth maps by iteratively minimizing an objective function, wherein the objective function comprises a distance term that sums, for all of the plurality of depth maps, a plurality of squared point-to-plane distances, and wherein the distance term allows transformation of both a source depth map and a target depth map for each of a plurality of pairs of the depth maps; identifying one or more of the plurality of points described by one or more of the plurality of depth maps as outlying points; reducing a confidence score associated with each of the outlying points; merging the plurality of depth maps to generate a signed distance function for the scene, wherein the merging is based at least in part on the confidence scores; and generating a mesh model of the scene based at least in part on the signed distance function. - View Dependent Claims (19, 20)
-
Specification