公开(公告)号：US20230410446A1

公开(公告)日：2023-12-21

申请号：US18456823

申请日：2023-08-28

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Gyehyun KIM ,  Yoonhee CHOI ,  Keunjoo KWON ,  Beomseok KIM ,  Sangwon LEE ,  Youjin LEE ,  Taeyoung JANG

IPC: G06T19/00 ,  G06T11/00 ,  G06T7/50 ,  G06T11/60 ,  G06F18/00 ,  G06V10/82 ,  G06V10/26

CPC classification number: G06T19/006 ,  G06T11/001 ,  G06T7/50 ,  G06T11/60 ,  G06T2207/20212 ,  G06V10/82 ,  G06V10/26 ,  G06T2207/30192 ,  G06F18/00

Abstract: A system and method for providing a weather effect in an image includes selecting at least one weather texture image indicating weather, and providing a weather effect in the image by overlapping the selected weather texture image on the image.

公开(公告)号：US20220237833A1

公开(公告)日：2022-07-28

申请号：US17717937

申请日：2022-04-11

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Gyehyun KIM ,  Yoonhee CHOI ,  Keunjoo KWON ,  Beomseok KIM ,  Sangwon LEE ,  Youjin LEE ,  Taeyoung JANG

IPC: G06T11/00 ,  G06T7/50 ,  G06K9/62 ,  G06T11/60

Abstract: A system and method for providing a weather effect in an image includes selecting at least one weather texture image indicating weather, and providing a weather effect in the image by overlapping the selected weather texture image on the image.

公开(公告)号：US20240233092A1

公开(公告)日：2024-07-11

申请号：US18616953

申请日：2024-03-26

Applicant: Samsung Electronics Co., Ltd.

Inventor： Gyehyun KIM ,  Beomseok KIM ,  Youjin LEE ,  Taeyoung JANG ,  Youngo PARK ,  Yongsup PARK ,  Sangmi LEE ,  Kwangpyo CHOI

IPC: G06T5/60 ,  G06T5/50

CPC classification number: G06T5/60 ,  G06T5/50 ,  G06T2207/20016 ,  G06T2207/20084 ,  G06T2207/20216

Abstract: Provided are an image processing method and an input processing device based on a neural network, the method including: obtaining a feature map distinguishing between a near object and a distant object of a low-resolution input image, obtaining a composited weight map for the low-resolution input image by inputting the feature map to a first Deep Neural Network (DNN), obtaining a first image by inputting the low-resolution input image to a second DNN suitable for restoring a distant object, obtaining a second image by inputting the low-resolution input image to a third DNN suitable for restoring a near object, and obtaining a high-resolution image for the low-resolution input image by performing weighted averaging on the first image and the second image using the composited weight map.