US 12,169,917 B2
Method and device with data processing using neural network
Sujin Jang, Hwaseong-si (KR); Joohan Na, Suwon-si (KR); and Dokwan Oh, Hwaseong-si (KR)
Assigned to Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed by Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed on Jan. 13, 2022, as Appl. No. 17/575,002.
Claims priority of application No. 10-2021-0063699 (KR), filed on May 17, 2021; and application No. 10-2021-0083974 (KR), filed on Jun. 28, 2021.
Prior Publication US 2022/0366548 A1, Nov. 17, 2022
Int. Cl. G06T 5/80 (2024.01); G06N 3/088 (2023.01); G06T 5/50 (2006.01)
CPC G06T 5/80 (2024.01) [G06N 3/088 (2013.01); G06T 5/50 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A processor-implemented method with data processing using a neural network, the method comprising:
determining a first translated image by translating a first image based on a second image, the first image and a second image having different distortions, such that a distortion of the first translated image corresponds to a distortion of the second image;
determining a first retranslated image by translating the first translated image such that a distortion of the first retranslated image corresponds to a distortion of the first image; and
training a first deformation field generator configured to determine a first relative deformation field that represents a relative deformation from the first image to the second image and a second deformation field generator configured to determine a second relative deformation field that represents a relative deformation from the second image to the first image, based on a loss between the first retranslated image and the first image.