Systems and methods for augmented reality preparation, processing, and application

A device to determine a final pose, the device comprising:

• an interface configured to receive data from an augmented reality (AR) experience device;
• at least one processor;
• at least one memory comprising instructions configured to cause the at least one processor to perform a method comprising:
• receiving depth information from the AR experience device via the interface, the depth information comprising distances from a depth sensor to surfaces in a real-world environment;
• determining a final pose, wherein determining the final pose comprises:
• determining a first pose;
• determining at least one neighborhood based upon the first pose;
• and
• iteratively, through two or more iterations:
• selecting a new pose from a plurality of poses within a neighborhood of a plurality of neighborhoods, each neighborhood of the plurality of neighborhoods covering a portion of a search space associated with a virtual model of the real-world environment;
• pruning a neighborhood from the plurality of neighborhoods, at least in part, by determining correspondences between the depth information oriented using a pose from the pruned neighborhood and at least a portion of the virtual model of the real-world environment;
• and
• setting a size of at least one neighborhood in a subsequent iteration to be smaller than a size of at least one neighborhood in a preceding iteration, wherein
• the final pose is the new pose so iteratively determined to more closely correspond to the virtual model than a pose of a previous iteration;
• and
• making the final pose available to the AR experience device.

A computer-implemented method for determining a pose of a device relative to a real-world environment, comprising:

• receiving depth information associated with the device, the depth information comprising distances from the device to surfaces in a real-world environment;
• and
• determining a final pose, wherein determining the final pose comprises applying a Pose Search Algorithm (PSA) to a virtual model of the real-world environment and a first pose determined from the depth information, wherein the PSA comprises:
• determining at least one neighborhood based upon the first pose;
• and
• iteratively, through two or more iterations:
• selecting a new pose from a plurality of poses within a neighborhood of a plurality of neighborhoods, each neighborhood of the plurality of neighborhoods covering a portion of a search space associated with the virtual model of the real-world environment;
• pruning a neighborhood from the plurality of neighborhoods, at least in part, by determining correspondences between the depth information oriented using a pose from the pruned neighborhood and at least a portion of the virtual model of the real-world environment;
• and
• setting a size of at least one neighborhood in a subsequent iteration to be smaller than a size of at least one neighborhood in a preceding iteration, and
• wherein
• the final pose is the new pose so iteratively determined to more closely correspond to the virtual model than a pose of a previous iteration.

A non-transitory computer-readable medium comprising instructions configured to cause a device to perform a method, the method comprising:

• receiving depth information associated with the device, the depth information comprising distances from the device to surfaces in a real-world environment;
• and
• determining a final pose, wherein determining the final pose comprises applying a Pose Search Algorithm (PSA) to a virtual model of the real-world environment and a first pose determined from the depth information, wherein the PSA comprises:
• determining at least one neighborhood based upon the first pose;
• and
• iteratively, through two or more iterations:
• selecting a new pose from a plurality of poses within a neighborhood of a plurality of neighborhoods, each neighborhood of the plurality of neighborhoods covering a portion of a search space associated with the virtual model of the real-world environment;
• pruning a neighborhood from the plurality of neighborhoods, at least in part, by determining correspondences between the depth information oriented using a pose from the pruned neighborhood and at least a portion of the virtual model of the real-world environment;
• and
• setting a size of at least one neighborhood in a subsequent iteration to be smaller than a size of at least one neighborhood in a preceding iteration, wherein
• the final pose is the new pose so iteratively determined to more closely correspond to the virtual model than a pose of a previous iteration.