US 12,390,734 B2
Refining camera re-localization determination using prior pose model
Ben Benfold, Oxford (GB); and Victor Adrian Prisacariu, Oxford (GB)
Assigned to Niantic Spatial, Inc., San Francisco, CA (US)
Filed by Niantic Spatial, Inc., San Francisco, CA (US)
Filed on Mar. 15, 2024, as Appl. No. 18/607,233.
Application 18/607,233 is a continuation of application No. 17/686,119, filed on Mar. 3, 2022, granted, now 11,957,978.
Prior Publication US 2024/0216809 A1, Jul. 4, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. A63F 13/53 (2014.01); A63F 13/213 (2014.01); A63F 13/216 (2014.01); A63F 13/5378 (2014.01); G06T 7/70 (2017.01); G06T 19/00 (2011.01)
CPC A63F 13/5378 (2014.09) [A63F 13/213 (2014.09); A63F 13/216 (2014.09); G06T 7/70 (2017.01); G06T 19/006 (2013.01); G06T 2207/20076 (2013.01); G06T 2207/30244 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
receiving camera frame and sensor data from a client device associated with a location-based application;
inputting the received data into a computer vision algorithm to generate candidate pose estimates, each pose estimate representing a prediction of a three-dimensional position and orientation of the client device and having an associated confidence score that is generated based on a combination of a comparison between a captured image of a scene and one or more other images of the scene and a probability map indicating likelihoods of potential candidate poses;
selecting an authoritative candidate pose estimate from the pose estimates using the confidence scores; and
causing the client device to provide location-based content within the location-based application using the authoritative pose estimate.