公开(公告)号：US20220237945A1

公开(公告)日：2022-07-28

申请号：US17658620

申请日：2022-04-08

Applicant: Hyperconnect Inc.

Inventor： Sangil Ahn ,  Seokjun Seo ,  Hyountaek Yong ,  Sungjoo Ha ,  Martin Kersner ,  Beomsu Kim ,  Dongyoung Kim

IPC: G06V40/16 ,  G06T7/70 ,  G06V10/80 ,  G06T11/00

Abstract: A method of generating a reenacted image includes: extracting a landmark from each of a driver image and a target image; generating a driver feature map based on pose information and expression information of a first face shown in the driver image; generating a target feature map and a pose-normalized target feature map based on style information of a second face shown in the target image; generating a mixed feature map by using the driver feature map and the target feature map; and generating the reenacted image by using the mixed feature map and the pose-normalized target feature map.

公开(公告)号：US11301534B2

公开(公告)日：2022-04-12

申请号：US17028031

申请日：2020-09-22

Applicant: Hyperconnect Inc.

Inventor： Sangil Ahn ,  Kangsik Jung ,  Hyountaek Yong

IPC: G06F16/9536 ,  G06F16/9538 ,  H04N7/14

Abstract: A mediating method by a mediating device comprises receiving a first list including at least one item from a first terminal and receiving at least one list from at least one terminal different from the first terminal, searching for a list including an item corresponding to at least one item among the at least one item of the first list, among the received at least one list, and transmitting information on the corresponded item, according to a result of the search, to each of the first terminal and a terminal which provides the list including the item corresponding to the at least one item among the at least one terminal.

公开(公告)号：US11080325B2

公开(公告)日：2021-08-03

申请号：US16268924

申请日：2019-02-06

Applicant: HYPERCONNECT, INC.

Inventor： Sangil Ahn ,  Beomjun Shin ,  Minsik Oh ,  Eunhee Choi

IPC: G06F16/30 ,  G06F16/532 ,  G06F16/9032 ,  G06T5/50 ,  G06F17/18 ,  G06N20/00 ,  G06N3/08 ,  G06T5/00

Abstract: A server may include a communicator for receiving an image from a subject terminal from among a plurality of terminals; and a controller for identifying a type of a content included in the received image, and for controlling two or more different image filters using a recommended algorithm regarding an image filter to be applied to the image, wherein the controller may select a first image filter predicted to have a highest probability to be selected by a user of the subject terminal and a second image filter predicted to have a second highest probability to be selected by the user of the subject terminal using the recommended algorithm, and the communicator may transmit information on the first image filter and information on the second image filter to the subject terminal.

公开(公告)号：US10855727B2

公开(公告)日：2020-12-01

申请号：US16827788

申请日：2020-03-24

Applicant: HYPERCONNECT, INC.

Inventor： Sangil Ahn ,  Sangpil Yoon

IPC: H04N7/15 ,  H04L29/06 ,  G06F3/0484

Abstract: A video call mediating method includes: connecting, by a first terminal and a second terminal, to a video call platform; extracting a first identifier (ID) of a user of the first terminal and a second ID of a user of the second terminal, that is not displayed on the first terminal and the second terminal, during a video call; creating a first identification code for the first terminal and a second identification code of the second terminal from the first ID and the second ID, respectively; establishing a first video call session between the first terminal and the second terminal; creating a first image and a second image corresponding to the first terminal and the second terminal, respectively, with reference to the first identification code and the second identification code, respectively; and displaying the first image and the second image on a display of the first terminal and on a display of the second terminal, respectively.

公开(公告)号：US20200336493A1

公开(公告)日：2020-10-22

申请号：US16851248

申请日：2020-04-17

Applicant: HYPERCONNECT, INC.

Inventor： Sangil Ahn ,  Kangsik Jung

IPC: H04L29/06 ,  H04L29/12 ,  H04W12/00

Abstract: A server may include a communication interface for receiving a log in request for a video call service from a terminal, and for receiving at least one information to be used to determine a country of a log in attempt from the terminal; a memory for storing country information received from the terminal when subscribing the video call service of the terminal; and a processor for determining the country of the log in attempt of the terminal based on the at least one information, comparing a prestored country information corresponding to the terminal with the determined country of the log in attempt, and allowing the log in of the terminal depending on a result of the comparison.

公开(公告)号：US10728498B2

公开(公告)日：2020-07-28

申请号：US16177597

申请日：2018-11-01

Applicant: Hyperconnect, Inc.

Inventor： Sangil Ahn ,  Kangsik Jung

IPC: H04N7/14 ,  H04L29/06 ,  G06K9/00

Abstract: The communication method includes performing, by a first terminal, consecutive video call with at least one or more second terminal; selecting, by the first terminal, at least one or more representative frame from among a plurality of frames of an image being photographed during each video call; detecting, by the first terminal, a face from the at least one or more representative frame; generating, by the first terminal, a face recognition result that includes information on a number of the faces detected from the at least one or more representative frame; outputting, by the first terminal, the face recognition result to a server; and upon completion of the video call with the at least one or more second terminal, performing, by the first terminal, video call with a third terminal selected based on the face recognition result from the server.

公开(公告)号：US10602091B2

公开(公告)日：2020-03-24

申请号：US16363856

申请日：2019-03-25

Applicant: Hyperconnect, Inc.

Inventor： Sangil Ahn ,  Hyeok Choi

IPC: H04N7/14 ,  H04N7/15 ,  G06K9/00

Abstract: Disclosed are a method of learning relationship among characters in video call or its background, temporal and spatial information, and visual objects and automatically recommending and providing a visual object using the relationship, and a system configured to execute the method. A method of providing video call may include: storing a visual object selection model including relation information between at least one visual object and at least one selection factor, by a video call providing system; and automatically determining, by the video call providing system, a recommended visual object to be displayed on at least one of a terminal and a counterpart terminal of the terminal performing video call, at a point of time specified for displaying a visual object, based on the visual object selection model.

公开(公告)号：US10430523B2

公开(公告)日：2019-10-01

申请号：US15699588

申请日：2017-09-08

Applicant: Hyperconnect, Inc.

Inventor： Sangil Ahn

IPC: G10L21/00 ,  G06F17/28 ,  G10L15/00 ,  G10L15/22 ,  G10L15/30 ,  G10L21/10 ,  H04N7/15 ,  H04N7/14

Abstract: A terminal control method may include: establishing, by a first terminal used by a first user who speaks a first language, connection to a second terminal used by a second user who speaks a second language different from the first language; and acquiring a second-language greeting transliterated into the first language.