公开(公告)号：US20250069199A1

公开(公告)日：2025-02-27

申请号：US18945107

申请日：2024-11-12

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Nazrinbanu Nurmohammad NAGORI ,  Mrinmoy SEN ,  Venkat Ramana PEDDIGARI ,  Sai Pradyumna CHERMALA ,  Praful MATHUR ,  Darshana Venkatesh MURTHY ,  Moonhwan JEONG

IPC: G06T5/60 ,  G06T5/50 ,  G06T7/00

Abstract: A method may include: receiving, by a first camera of a multi-camera device, a first image of an input scene; identifying at least one shadow in the first image; determining at least one of at least one property of the at least one shadow or a region of interest (ROI) of the at least one shadow in the first image; applying at least one configuration to a second camera for obtaining a second image of the input scene based on the at least one of at least one property of the at least one shadow or the ROI of the at least one shadow, to identify at least one additional context of the input scene, where the at least one additional context is not obtained using the first camera; and removing the at least one shadow from the first image, based on the first image and the second image.

公开(公告)号：US20220301235A1

公开(公告)日：2022-09-22

申请号：US17720962

申请日：2022-04-14

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Mrinmoy SEN ,  Sai Pradyumna CHERMALA ,  Venkat Ramana PEDDIGARI ,  Nazrinbanu Nurmohammad NAGORI ,  Mansi SINGH ,  Bindigan Hariprasanna Pawan PRASAD ,  Moonhwan JEONG

IPC: G06T11/00 ,  G06T3/40 ,  G06V10/74

Abstract: The present disclosure relates to method and apparatus for removing shadows from a High Resolution (HR) image. The HR image including shadows is received. The HR image converted into Low Resolution (LR) image. LR shadow-free image is generated from the LR image using first Artificial Intelligence (AI) model. A HR shadow-free image is generated based on combination of the LR shadow-free image and the HR image using second AI model. The present disclosure provides an efficient framework and lightweight network architectures which are used to remove the shadows based on corresponding shadow characteristics. The framework can be deployed in resource-constrained platforms. The present disclosure facilitates processing selected areas of the HR image and retaining the unselected area. Thus, less computational resources are required.

公开(公告)号：US20240404010A1

公开(公告)日：2024-12-05

申请号：US18798017

申请日：2024-08-08

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Praful MATHUR ,  Siddhant KHANDELWAL ,  Mrinmoy SEN ,  Sai Pradyumna CHERMALA ,  Nazrinbanu Nurmohammad NAGORI ,  Venkat Ramana PEDDIGARI ,  Darshana Venkatesh MURTHY ,  Moonhwan JEONG

IPC: G06T5/20 ,  G06T5/50 ,  G06T7/11 ,  G06T7/136 ,  G06V20/70

Abstract: A method for generating one or more artifact images is disclosed. The method includes obtaining one or more artifact free images and one or more artifacts represented by one or more artifact masks; obtaining a region of interest (ROI) mask identifying one or more ROIs in the one or more artifact free images; generating one or more transformed artifact masks by applying at least one localization parameter amongst a plurality of localization parameters to the one or more artifact masks; generating one or more localized artifact masks by placing the one or more transformed artifact masks on the ROI mask; and generating one or more artifact images by combining the one or more artifact free images and the one or more localized artifact masks.

公开(公告)号：US20220130019A1

公开(公告)日：2022-04-28

申请号：US17571664

申请日：2022-01-10

Applicant: Samsung Electronics Co., Ltd.

Inventor： Moonhwan JEONG ,  Yoonsang KIM ,  Sujung BAE ,  Inho CHOI ,  Seon HEO

IPC: G06T5/00 ,  G06N20/00 ,  G06T5/50 ,  G06N3/04 ,  G06V10/25 ,  G06V40/16

Abstract: An electronic device according to an embodiment disclosed herein may include a communication circuit, a processor; and a memory configured to be operatively connected to the processor. The memory according to an embodiment may store instructions that, when executed, cause the processor to: recognize an area comprising at least part of a face in an image to be transmitted to an external device; generate perturbation data about the recognized area based on a machine learning model stored in the memory; apply the perturbation data to the recognized area; and transmit the image to which the perturbation data has been applied to the external device. Various other embodiments are possible.