	US 12,014,471 B2
	Generation of synthetic 3-dimensional object images for recognition systems
Amit Bleiweiss, Yad Binyamin (IL); Chen Paz, Modiin (IL); Ofir Levy, Jerusalem (IL); Itamar Ben-Ari, Givat HaShlosha (IL); and Yaron Yanai, Modiin (IL)
Assigned to Tahoe Research, Ltd., Dublin (IE)
Filed by Tahoe Research, Ltd., Dublin (IE)
Filed on Feb. 6, 2023, as Appl. No. 18/165,291.
Application 18/165,291 is a continuation of application No. 17/012,881, filed on Sep. 4, 2020, granted, now 11,574,453, issued on Feb. 7, 2023.
Application 17/012,881 is a continuation of application No. 16/053,135, filed on Aug. 2, 2018, granted, now 10,769,862, issued on Sep. 8, 2023.
Application 16/053,135 is a continuation of application No. 14/969,563, filed on Dec. 15, 2015, granted, now 10,068,385, issued on Sep. 4, 2018.
Prior Publication US 2023/0186584 A1, Jun. 15, 2023
Int. Cl. G06T 19/20 (2011.01); G06F 30/00 (2020.01); G06N 20/00 (2019.01); G06T 3/20 (2006.01); G06T 3/40 (2006.01); G06T 3/60 (2006.01); G06T 15/00 (2011.01); G06T 15/20 (2011.01); G06T 15/50 (2011.01); G06T 17/00 (2006.01); G06V 20/64 (2022.01)

CPC G06T 19/20 (2013.01) [G06F 30/00 (2020.01); G06N 20/00 (2019.01); G06T 3/20 (2013.01); G06T 3/40 (2013.01); G06T 3/60 (2013.01); G06T 15/00 (2013.01); G06T 15/20 (2013.01); G06T 15/50 (2013.01); G06T 17/00 (2013.01); G06V 20/64 (2022.01); G06V 2201/12 (2022.01)]

24 Claims

1. A processor-implemented method for generating 3-Dimensional (3D) object image variations, the method comprising:

rendering a plurality of color and depth (RGB-D) image pair variations of an object based on a synthesized RGB-D image pair of the object, ones of the RGB-D image pair variations being associated with a plurality of different poses of the object, the plurality of different poses of the object being generated by adjusting one or more of an orientation in space of one or more subcomponents of the object or a position in space of the one or more subcomponents of the object relative to one or more other subcomponents of the object.