US 12,470,838 B2
Method and apparatus with white balancing
Junsang Yu, Suwon-si (KR); Dong Young Kim, Seoul (KR); Seon Joo Kim, Seoul (KR); Kinam Kwon, Suwon-si (KR); and Hyong Euk Lee, Suwon-si (KR)
Assigned to Samsung Electronics Co., Ltd., Suwon-si (KR); and UIF (University Industry Foundation), Yonsei University, Seoul (KR)
Filed by SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR); and UIF (University Industry Foundation), Yonsei University, Seoul (KR)
Filed on Jul. 25, 2023, as Appl. No. 18/358,250.
Claims priority of application No. 10-2023-0026937 (KR), filed on Feb. 28, 2023; and application No. 10-2023-0038178 (KR), filed on Mar. 23, 2023.
Prior Publication US 2024/0292116 A1, Aug. 29, 2024
Int. Cl. H04N 23/88 (2023.01); G06T 7/90 (2017.01); H04N 1/60 (2006.01)
CPC H04N 23/88 (2023.01) [G06T 7/90 (2017.01); H04N 1/6086 (2013.01); G06T 2207/10024 (2013.01)] 27 Claims
OG exemplary drawing
 
1. A processor-implemented method, the method comprising:
inputting an image into an encoder to generate a feature map including information about an illumination present in the input image;
iteratively updating a plurality of slot vectors using the calculated feature map to calculate a plurality of predicted illumination vectors;
calculating, using the calculated plurality of predicted illumination vectors, a plurality of mixture maps representing respective effects of a plurality of virtual illuminations on pixels in the input image and a plurality of illumination color vectors representing respective color values of the plurality of virtual illuminations; and
generating an illumination map using the calculated plurality of mixture maps and the calculated plurality of illumination color vectors.