US 11,816,810 B2
3-D reconstruction using augmented reality frameworks
Manish Upendran, San Francisco, CA (US); William Castillo, Belmont, CA (US); Jena Dzitsiuk, San Francisco, CA (US); Yunwen Zhou, Belmont, CA (US); and Matthew Thomas, San Francisco, CA (US)
Assigned to HOVER INC., San Francisco, CA (US)
Filed by HOVER, INC., San Francisco, CA (US)
Filed on May 31, 2022, as Appl. No. 17/829,203.
Application 17/829,203 is a continuation of application No. 17/118,370, filed on Dec. 10, 2020, granted, now 11,380,078.
Claims priority of provisional application 63/123,379, filed on Dec. 9, 2020.
Claims priority of provisional application 62/948,151, filed on Dec. 13, 2019.
Prior Publication US 2022/0327792 A1, Oct. 13, 2022
Int. Cl. G06T 19/20 (2011.01); G06T 7/73 (2017.01)
CPC G06T 19/20 (2013.01) [G06T 7/74 (2017.01); G06T 2207/10028 (2013.01); G06T 2210/04 (2013.01); G06T 2219/2016 (2013.01)] 24 Claims
OG exemplary drawing
 
1. A method for generating a scaling factor for a building structure in a 3-D scene, the method comprising:
obtaining a plurality of 2-D images of the 3-D scene, wherein the plurality of images comprises image features co-visible among at least two 2-D images;
deriving reference poses for an imager based on the image features;
obtaining world map data including real-world poses of the imager associated with the plurality of images, wherein the real-world poses are derived from an augmented reality framework and comprise geometric position information;
selecting at least two candidate poses from the real-world poses based on translation changes between the real-world poses proportional with translation changes of corresponding reference poses; and
calculating a scaling factor for the building structure based on the geometric position information of the at least two candidate poses.