Enabling use of three-dimensional locations of features images

摘要

The disclosed embodiments provide a system that facilitates use of an image. During operation, the system uses a set of images from a camera on a device to obtain a set of features in proximity to the device, wherein the set of images comprises the image. Next, the system uses the set of images and inertial data from one or more inertial sensors on the device to obtain a set of three-dimensional (3D) locations of the features. Finally, the system enables use of the set of 3D locations with the image.

主权项

1. A computer-implemented method for facilitating use of an image, comprising:
using a set of images from a camera on a device to obtain a set of features in proximity to the device; using the set of images and inertial data from one or more inertial sensors on the device to generate a three-dimensional (3D) model of an environment around the device; obtaining a selection of the image from the set of images; selecting, as a subset of the generated 3D model, a set of 3D locations of the features and a set of 2D locations of the features in the image; storing the selected subset of the 3D model comprising the 3D locations and the 2D locations as metadata for the image for subsequent use of the 3D locations with the features in the image; and omitting a remainder of the 3D model that is not in the subset from the metadata.