公开(公告)号：US20220076385A1

公开(公告)日：2022-03-10

申请号：US17526714

申请日：2021-11-15

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Green Rosh K S ,  Bindigan Hariprasanna Pawan Prasad ,  Nikhil Krishnan ,  Sachin Deepak Lomte ,  Anmol Biswas

IPC: G06T5/00 ,  G06T5/20 ,  G06T7/11

Abstract: A method for processing image data, may include: receiving at least one image; segregating the at least one image into at least one region, based on a requested noise reduction level; and denoising the at least one image by varying at least one control feature of the segregated at least one region by a neural network to achieve the requested noise reduction level.

公开(公告)号：US12288317B2

公开(公告)日：2025-04-29

申请号：US17890868

申请日：2022-08-18

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Gaurav Khandelwal ,  Sachin Deepak Lomte ,  Umang Chaturvedi ,  Diplav

IPC: G06T7/00 ,  G06T5/50 ,  G06T5/70 ,  G06V10/44

Abstract: A method for enhancing image quality may be provided. The method may include receiving a plurality of input frames and metadata, and determining one or more feature scores for a received input frame from the plurality of input frames. The method may further include determining a parametric score for the received input frame based on an analysis of the one or more feature scores of the received input frame and the metadata. The method may include identifying one or more artifacts for correction in the received input frame based on the parametric score, and determining a strength of correction required for at least one identified artifact in the received input frame based on the parametric score, then applying the determined strength of correction to the received input frame. The method may further include performing multi-frame blending for a plurality of received input frames with applied determined strength of correction.

公开(公告)号：US12249047B2

公开(公告)日：2025-03-11

申请号：US17526714

申请日：2021-11-15

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Green Rosh K S ,  Bindigan Hariprasanna Pawan Prasad ,  Nikhil Krishnan ,  Sachin Deepak Lomte ,  Anmol Biswas

IPC: G06K9/00 ,  G06T5/20 ,  G06T5/70 ,  G06T7/11

Abstract: A method for processing image data, may include: receiving at least one image; segregating the at least one image into at least one region, based on a requested noise reduction level; and denoising the at least one image by varying at least one control feature of the segregated at least one region by a neural network to achieve the requested noise reduction level.