US 12,249,047 B2
Methods and systems for denoising media using contextual information of the media
Green Rosh K S, Bangalore (IN); Bindigan Hariprasanna Pawan Prasad, Bangalore (IN); Nikhil Krishnan, Bangalore (IN); Sachin Deepak Lomte, Bangalore (IN); and Anmol Biswas, Bangalore (IN)
Assigned to SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR)
Filed by SAMSUNG ELECTRONICS CO., LTD., Suwon-si (KR)
Filed on Nov. 15, 2021, as Appl. No. 17/526,714.
Application 17/526,714 is a continuation of application No. PCT/KR2021/002708, filed on Mar. 4, 2021.
Claims priority of application No. 202041009368 (IN), filed on Mar. 4, 2020; and application No. 202041009368 (IN), filed on Mar. 1, 2021.
Prior Publication US 2022/0076385 A1, Mar. 10, 2022
Int. Cl. G06K 9/00 (2022.01); G06T 5/20 (2006.01); G06T 5/70 (2024.01); G06T 7/11 (2017.01)
CPC G06T 5/70 (2024.01) [G06T 5/20 (2013.01); G06T 7/11 (2017.01); G06T 2207/20024 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)] 23 Claims
OG exemplary drawing
 
17. An electronic device comprising:
a memory storing instructions; and
a processor configured to execute the instructions to:
receive at least one image;
select at least one region in the at least one image, based on at least one of a user touch input, face detection, or scene analysis;
generate at least one updated control feature from an initial control feature of the at least one input image for the selected at least one region to adjust an extent of denoising with respect to the selected at least one region;
denoise the at least one image, by inputting an input image including the selected at least one region and the at least one updated control feature into a neural network and process the input image based on the updated control features by the neural network.