US 12,266,144 B2
Training and inferencing using a neural network to predict orientations of objects in images
Siva Karthik Mustikovela, Lowell, MA (US); Varun Jampani, Nashua, NH (US); Shalini De Mello, San Francisco, CA (US); Sifei Liu, Santa Clara, CA (US); Umar Iqbal, San Jose, CA (US); and Jan Kautz, Lexington, MA (US)
Assigned to NVIDIA Corporation, Santa Clara, CA (US)
Filed by NVIDIA Corporation, Santa Clara, CA (US)
Filed on Nov. 20, 2019, as Appl. No. 16/690,015.
Prior Publication US 2021/0150757 A1, May 20, 2021
Int. Cl. G06V 10/24 (2022.01); G06F 18/21 (2023.01); G06F 18/214 (2023.01); G06N 3/045 (2023.01); G06N 3/08 (2023.01); G06T 7/73 (2017.01); G06V 10/44 (2022.01); G06V 10/764 (2022.01); G06V 10/778 (2022.01); G06V 10/82 (2022.01); G06V 20/56 (2022.01)
CPC G06V 10/242 (2022.01) [G06F 18/214 (2023.01); G06F 18/217 (2023.01); G06N 3/045 (2023.01); G06N 3/08 (2013.01); G06T 7/74 (2017.01); G06V 10/454 (2022.01); G06V 10/764 (2022.01); G06V 10/7784 (2022.01); G06V 10/82 (2022.01); G06V 20/56 (2022.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30196 (2013.01); G06T 2207/30252 (2013.01)] 52 Claims
OG exemplary drawing
 
1. A processor, comprising: one or more circuits to help train one or more neural networks to identify an orientation of an object within an image based, at least in part, on one or more labels indicating one or more characteristics of the object other than the object's orientation.
 
7. A system, comprising:
one or more processors to calculate parameters to help train one or more neural networks to identify an orientation of an object within an image based, at least in part, on one or more labels indicating one or more characteristics of the object other than the object's orientation; and
one or more memories to store the parameters.
 
22. A processor, comprising: one or more circuits to identify one or more orientations of an object within an image based, at least in part, on one or more labels indicating one or more characteristics of the object other than the object's one or more orientations.
 
28. A system, comprising:
one or more memories; and
one or more processors to identify one or more orientations of an object within an image based, at least in part, on one or more labels indicating one or more characteristics of the object other than the object's one or more orientations.
 
35. A method, comprising: identifying one or more orientations of an object within an image based, at least in part, on one or more labels indicating one or more characteristics of the object other than the object's one or more orientations.