US 12,169,765 B2
Virtual object machine learning
Xuehan Xiong, Los Angeles, CA (US); and Zehao Xue, Los Angeles, CA (US)
Assigned to Snap Inc., Santa Monica, CA (US)
Filed by Snap Inc., Santa Monica, CA (US)
Filed on Sep. 8, 2023, as Appl. No. 18/244,016.
Application 18/244,016 is a continuation of application No. 17/322,609, filed on May 17, 2021, granted, now 11,790,276.
Application 17/322,609 is a continuation of application No. 16/777,098, filed on Jan. 30, 2020, granted, now 11,030,454.
Application 16/777,098 is a continuation of application No. 15/653,186, filed on Jul. 18, 2017, granted, now 10,579,869.
Prior Publication US 2023/0419188 A1, Dec. 28, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 17/20 (2006.01); G06N 20/00 (2019.01); G06N 20/10 (2019.01); G06V 10/772 (2022.01); G06V 20/10 (2022.01); G06V 20/80 (2022.01); G06V 40/10 (2022.01)
CPC G06N 20/10 (2019.01) [G06N 20/00 (2019.01); G06T 17/20 (2013.01); G06V 10/772 (2022.01); G06V 20/10 (2022.01); G06V 20/80 (2022.01); G06V 40/103 (2022.01); G06V 40/107 (2022.01)] 18 Claims
OG exemplary drawing
 
1. A method comprising:
storing, on a device, a convolutional neural network trained to detect different gestures of different objects, the convolutional neural network trained on a plurality of images generated from three-dimensional models of the different objects, each of the plurality of images depicting a three-dimensional model of one of the different objects in a combination of the different gestures, textures, and three-dimensional environments, wherein the textures comprise a skin shade texture;
identifying an image depicting a physical object; and
classifying, using the convolutional neural network operating on one or more processors of the device, the physical object as being in a gesture from the different gestures of the different objects by applying the convolutional neural network to the image depicting the physical object.