US 11,810,270 B2
Machine learning training images from a constrained set of three-dimensional object models associated with prescribed scene types
Clarence Chui, Los Altos Hills, CA (US); and Manu Parmar, Sunnyvale, CA (US)
Assigned to Outward, Inc., San Jose, CA (US)
Filed by Outward, Inc., San Jose, CA (US)
Filed on Jul. 22, 2022, as Appl. No. 17/870,830.
Application 17/870,830 is a continuation of application No. 17/131,586, filed on Dec. 22, 2020, granted, now 11,449,967.
Application 17/131,586 is a continuation of application No. 16/056,110, filed on Aug. 6, 2018, granted, now 10,902,559, issued on Jan. 26, 2021.
Claims priority of provisional application 62/541,603, filed on Aug. 4, 2017.
Prior Publication US 2022/0358626 A1, Nov. 10, 2022
Int. Cl. G06T 5/00 (2006.01); G06K 9/62 (2022.01); G06T 7/60 (2017.01); G06T 7/40 (2017.01); G06N 20/00 (2019.01); G06T 19/20 (2011.01); G06V 10/46 (2022.01); G06V 20/10 (2022.01); G06V 20/64 (2022.01); G06T 15/06 (2011.01); G06N 3/04 (2023.01); G06F 18/214 (2023.01); G06F 18/21 (2023.01); G06V 10/774 (2022.01); G06V 10/776 (2022.01); G06N 3/045 (2023.01)
CPC G06T 5/002 (2013.01) [G06F 18/214 (2023.01); G06F 18/217 (2023.01); G06N 20/00 (2019.01); G06T 7/40 (2013.01); G06T 7/60 (2013.01); G06T 15/06 (2013.01); G06T 19/20 (2013.01); G06V 10/774 (2022.01); G06V 10/776 (2022.01); G06V 20/10 (2022.01); G06V 20/64 (2022.01); G06N 3/045 (2023.01); G06T 2207/20081 (2013.01); G06T 2219/2024 (2013.01)] 69 Claims
OG exemplary drawing
 
24. A system, comprising:
a processor configured to:
detect a set of one or more attributes of an input image using a machine learning framework, wherein the machine learning framework is trained at least in part on a set of training images comprising a prescribed scene type, wherein one or more training images of the set of training images are rendered from a constrained set of one or more three-dimensional object models associated with the prescribed scene type, wherein the input image comprises the prescribed scene type, and wherein the detected set of attributes is not known for the input image prior to detection by the machine learning framework; and
generate an output image comprising a modified version of the input image by modifying at least a subset of the detected set of attributes; and
a memory coupled to the processor and configured to provide the processor with instructions.