US 11,731,053 B2
Detection of counterfeit virtual objects
Robin E. Mayes, San Francisco, CA (US); Courtland R. Caldwell, Millbrae, CA (US); Rebecca L. Herndon, San Francisco, CA (US); and Hariharan Natarajan, Fremont, CA (US)
Assigned to Roblox Corporation, San Mateo, CA (US)
Filed by Roblox Corporation, San Mateo, CA (US)
Filed on Dec. 29, 2021, as Appl. No. 17/564,939.
Application 17/564,939 is a continuation of application No. 16/703,823, filed on Dec. 4, 2019, granted, now 11,238,316.
Prior Publication US 2022/0121874 A1, Apr. 21, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06K 9/62 (2022.01); A63F 13/75 (2014.01); G06K 9/00 (2022.01); G06V 20/64 (2022.01); G06F 18/2413 (2023.01); G06V 10/764 (2022.01)
CPC A63F 13/75 (2014.09) [G06F 18/2413 (2023.01); G06V 10/764 (2022.01); G06V 20/647 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
determining a plurality of two-dimensional (2D) views of an unauthenticated virtual three-dimensional (3D) object based on a 3D mesh of the unauthenticated virtual 3D object, wherein each 2D view of the plurality of 2D views is a rendered view of the 3D mesh from a respective viewpoint;
calculating a hash value for each 2D view;
determining a plurality of distance values, wherein each distance value is indicative of distance between a respective hash value of a particular 2D view and a hash value of a corresponding 2D view of an authentic virtual 3D object, wherein the corresponding 2D view is from a same viewpoint as the viewpoint of the particular 2D view;
determining an aggregate distance value based on the plurality of distance values; and
classifying the unauthenticated virtual 3D object as a counterfeit 3D object if the aggregate distance value meets a predetermined threshold.