公开(公告)号：US20250029212A1

公开(公告)日：2025-01-23

申请号：US18417629

申请日：2024-01-19

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Mengmeng BAI ,  Jiahui Yuan ,  Xiansong Song ,  Jaekeun Na ,  Changwei Wang ,  Li Zuo ,  Wei Wen

IPC: G06T5/60 ,  G06T3/4046 ,  G06T5/10 ,  G06T5/50 ,  G06T5/70 ,  G06T5/77

Abstract: A method may include acquiring a first image that is obtained by adding noise to a second image, the second image comprising a target restoration region. The method may include performing at least one first denoising process on the first image using a first artificial intelligence (AI) network to obtain a first denoising result. The method may include restoring the target restoration region based on the first denoising result using a second AI network to obtain a restored image.

公开(公告)号：US11790655B2

公开(公告)日：2023-10-17

申请号：US17136368

申请日：2020-12-29

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jiahui Yuan ,  Wei Wen ,  Jianhua Fan

IPC: G06K9/00 ,  G06K9/62 ,  G06V20/40 ,  G06F18/214 ,  G06V10/82 ,  G06V10/44 ,  G06V40/20

CPC classification number: G06V20/46 ,  G06F18/214 ,  G06V10/454 ,  G06V10/82 ,  G06V20/41 ,  G06V20/44 ,  G06V40/20

Abstract: A video sampling method, including sampling a video based on a sampling window to obtain a current sequence of sampled images; acquiring action parameters corresponding to the current sequence of sampled images; adjusting the sampling window according to the action parameters; and sampling the video based on the adjusted sampling window.

公开(公告)号：US11507615B2

公开(公告)日：2022-11-22

申请号：US16775712

申请日：2020-01-29

Applicant: Samsung Electronics Co., Ltd.

Inventor： Zhonghua Luo ,  Jiahui Yuan ,  Wei Wen ,  Zuozhou Pan ,  Yuanyang Xue

IPC: G06F16/00 ,  G06F16/532 ,  G06K9/62 ,  G06N3/08 ,  G06N3/04 ,  G06V10/32 ,  G06V10/40

Abstract: A method and apparatus for image searching based on artificial intelligent (AI) are provided. The method includes obtaining first feature information by extracting features from an image based on a first neural network, obtaining second feature information corresponding to a target area of a query image by processing the first feature information based on a second neural network and at least two filters having different sizes, and identifying an image corresponding to the query image according to the second feature information.