公开(公告)号：US20220207367A1

公开(公告)日：2022-06-30

申请号：US17646465

申请日：2021-12-29

Applicant: Hyperconnect, Inc.

Inventor： Sang Il Ahn ,  Youngkyu Hong ,  Seungju Han ,  Kwanghee Choi ,  Seokjun Seo ,  Beomsu Kim ,  Buru Chang

IPC: G06N3/08 ,  G06F16/28

Abstract: A method of classifying data includes: training a classification model for classifying input data into at least one class, such that a first output value is generated according to a second equation in which a component corresponding to a label distribution of source data is disentangled in a first equation corresponding to the classification model; generating a second output value by applying, to the first output value, information indicating a label distribution of target data; and classifying the target data into the at least one class by using the second output value.

公开(公告)号：US20210142440A1

公开(公告)日：2021-05-13

申请号：US17092486

申请日：2020-11-09

Applicant: HYPERCONNECT, INC.

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

IPC: G06T3/00 ,  G06K9/00

Abstract: An image conversion apparatus for converting an image by using an artificial neural network includes: an image receiver receiving an image from a user; a template obtainer obtaining at least one image conversion template; and an image converter converting the static image into a moving image by using the obtained at least one image conversion template, wherein the image converter converts the static image received by the image receiver, into the moving image.

公开(公告)号：US20220253970A1

公开(公告)日：2022-08-11

申请号：US17658623

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: G06T3/00 ,  G06V40/16

Abstract: Provided is a method of transforming a landmark including: receiving an input image including a facial image of a first person and a landmark corresponding to the facial image; estimating a transformation matrix corresponding to the landmark; and calculating an expression landmark and an identity landmark corresponding to the input image by using the transformation matrix.

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.