	US 11,720,782 B2
	Multi-sensor, multi-view, multi-frame, multi-task synthetic image fusion engine for mobile imaging system
Chenchi Luo, Plano, TX (US); Gyeongmin Choe, Plano, TX (US); Yingmao Li, Allen, TX (US); Zeeshan Nadir, Richardson, TX (US); Hamid R. Sheikh, Allen, TX (US); John Seokjun Lee, Allen, TX (US); and Youngjun Yoo, Plano, TX (US)
Assigned to Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed by Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed on Dec. 28, 2020, as Appl. No. 17/135,573.
Claims priority of provisional application 63/039,249, filed on Jun. 15, 2020.
Prior Publication US 2021/0390375 A1, Dec. 16, 2021
Int. Cl. G06N 3/00 (2023.01); G06N 3/045 (2023.01); G06T 7/60 (2017.01); G06T 7/44 (2017.01); G06N 3/08 (2023.01); G06N 3/042 (2023.01)

CPC G06N 3/045 (2023.01) [G06N 3/042 (2023.01); G06N 3/08 (2013.01); G06T 7/44 (2017.01); G06T 7/60 (2013.01); G06T 2207/10024 (2013.01); G06T 2207/20081 (2013.01)]

20 Claims

1. A method comprising:

obtaining, using at least one processor of an electronic device, multiple calibration parameters associated with multiple sensors of a selected mobile device, the calibration parameters comprising at least one noise histogram generated during a noise calibration of the mobile device and at least one color lookup table generated during a photometric calibration of the mobile device;

obtaining, using the at least one processor, an identification of multiple imaging tasks;

obtaining, using the at least one processor, multiple synthetically-generated scene images; and

generating, using the at least one processor, multiple training images and corresponding meta information based on the calibration parameters, the identification of the imaging tasks, and the scene images;

wherein the training images and the corresponding meta information are generated concurrently, different ones of the training images correspond to different ones of the sensors, and different pieces of the meta information correspond to different ones of the imaging tasks.