公开(公告)号：US20240070955A1

公开(公告)日：2024-02-29

申请号：US18057117

申请日：2022-11-18

Applicant: Samsung Electronics Co., Ltd.

Inventor： Wenbo Li ,  Yi Wei ,  Jing Zhu ,  Hongxia Jin

IPC: G06T13/80 ,  G06T7/246 ,  G06T7/70 ,  G06V10/82 ,  G06V40/16

CPC classification number: G06T13/80 ,  G06T7/246 ,  G06T7/70 ,  G06V10/82 ,  G06V40/171 ,  G06V40/176 ,  G06T2207/10016 ,  G06T2207/30201 ,  G06V2201/10

Abstract: A method includes obtaining a source image of a user and obtaining a driving video in which a face or a head of the user is moving. The method also includes generating metadata identifying animations to be applied to the source image so that the source image mimics at least some movements of the user's face or head in the driving video. The method further includes transmitting the source image and the metadata to an end user device configured to animate the source image based on the metadata. Generating the metadata includes suppressing one or more artifacts associated with one or more objects that temporarily occlude at least a portion of the user's head or body in the driving video or that temporarily appear in the driving video.

公开(公告)号：US12081880B2

公开(公告)日：2024-09-03

申请号：US17493268

申请日：2021-10-04

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jing Zhu ,  Wenbo Li ,  Hongxia Jin

IPC: H04N23/951 ,  G06T5/20 ,  G06T5/50 ,  G06T5/75

CPC classification number: H04N23/951 ,  G06T5/20 ,  G06T5/50 ,  G06T5/75 ,  G06T2207/20016

Abstract: A super resolution is produced using multiple reference images. Reference images are upsampled and blurred as needed for comparison between images of different resolution. Patches in blurred images are searched to find those patches which can be assembled into vectors for improving feature content over multiple resolution levels. The searches are based on similarity maps. The assembled vectors are concatenated with one or more other vectors, up-converted and then passed through convolutional layers to obtain new feature vectors. A final feature vector is passed through a convolutional layer to obtain the super resolution image.

公开(公告)号：US11483719B2

公开(公告)日：2022-10-25

申请号：US17018683

申请日：2020-09-11

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Huiyang Wang ,  Yi Zhao ,  Chanjuan Wei ,  Jing Zhu ,  Hao Ni ,  Meifang Jing ,  Xiaohui Yang ,  Ranran Zhang

IPC: H04W16/28 ,  H04W72/04 ,  H04W88/08

Abstract: An apparatus for beam configuration in a wireless communication system, including a transceiver; and at least one processor connected with the transceiver and configured to: form at least one beam cluster from beams of a base station; determine a configuration of the at least one beam cluster; and configure the beams in the at least one beam cluster according to the determined configuration

公开(公告)号：US20240386575A1

公开(公告)日：2024-11-21

申请号：US18526875

申请日：2023-12-01

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Jing Zhu ,  Karim Ahmed ,  Wenbo Li ,  Yilin Shen ,  Hongxia Jin

IPC: G06T7/194 ,  G06T3/40

Abstract: Provided is a method and apparatus for obtaining a foreground image from an input image containing the foreground object in a scene. Embodiments use multi-scale convolutional attention values, one or more hamburger heads and one or more multilayer perceptrons to obtain a segmentation map of the input image. In some embodiments, progressive segmentation is applied to obtain the segmentation map.