知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

48 条记录 (耗时 0.021 秒)

    PERFORMING VIRTUAL NON-VERBAL COMMUNICATION CUES WITHIN A VIRTUAL ENVIRONMENT OF A VIDEO CONFERENCE
    3.
    发明申请
    PERFORMING VIRTUAL NON-VERBAL COMMUNICATION CUES WITHIN A VIRTUAL ENVIRONMENT OF A VIDEO CONFERENCE 有权

    公开(公告)号：US20220368857A1

    公开(公告)日：2022-11-17

    申请号：US17804841

    申请日：2022-05-31

    申请人： TRUE MEETING INC.

    发明人： RAN OZ ,  Omri KADURI

    IPC分类号： H04N7/15 ,  G06T15/04 ,  G06T15/20 ,  G06T7/11 ,  G06T7/70 ,  G06F3/01 ,  G06N3/04 ,  G06T17/20 ,  G06T19/00 ,  G06T19/20 ,  H04N7/14

    摘要： A method for performing virtual non-verbal communication cues within a virtual environment of a video conference, the method may include: (i) sensing that a certain participant of a video conference performs non-verbal communication cues in relation to virtual items that appear in a version of a virtual video conference environment that is displayed on a display of the certain participant; (ii) determining, by a machine learning process, virtual non-verbal communication cues to be executed by a certain avatar that represents the certain participant, wherein the virtual non-verbal communication cues mimic the non-verbal communication cues performed by the certain participant; and (iii) assisting to perform the virtual non-verbal communication cues of the certain avatar within the virtual video conference environment.

    UPDATING 3D MODELS OF PERSONS
    4.
    发明申请
    UPDATING 3D MODELS OF PERSONS 有权

    公开(公告)号：US20210358227A1

    公开(公告)日：2021-11-18

    申请号：US17249469

    申请日：2021-03-02

    申请人： TRUE MEETING INC.

    发明人： Ran Oz ,  Yuval Gronau ,  Michael Rabinovich ,  Osnat Goren-Peyser ,  Tal Perl

    IPC分类号： G06T19/20 ,  G06T17/20 ,  G06T7/70 ,  G06T7/11

    摘要： A method for updating a current three dimensional (3D) model of a person, that method may include calculating current locations, within a two-dimensional (2D) space, of current face landmark points of a face of a person within a first image; the calculating is based on the current 3D model, and one or more current acquisition parameters of a 2D camera; wherein the current 3D model of the person is located within a 3D space; calculating second locations, within the 2D space, of second face landmark points of the face of the person within a second image that follows the first image; calculating correspondences between the current locations and the second locations; calculating, based on the correspondences, locations of the second face landmark points within the 3D space; and modifying the current 3D model based on the locations of the second face landmark points within the 3D space.

    GENERATING AN ALPHA CHANNEL
    10.
    发明申请
    GENERATING AN ALPHA CHANNEL 有权

    公开(公告)号：US20220191431A1

    公开(公告)日：2022-06-16

    申请号：US17653026

    申请日：2022-03-01

    申请人： TRUE MEETING INC.

    发明人： Ran OZ ,  Eyal GAVISH ,  Rima GANDLIN

    IPC分类号： H04N7/15 ,  G06T15/04 ,  G06T15/20 ,  G06T7/11 ,  G06T7/70 ,  G06T17/20 ,  G06T19/20 ,  G06N3/04 ,  G06T19/00 ,  H04N7/14 ,  G06F3/01

    摘要： A method for generating alpha channel information related to a person, the method may include generating the alpha channel information related to the person by an alpha channel neural network; wherein the alpha channel machine learning process is trained using ground truth alpha channel information that is associated with background information; wherein the ground-truth alpha channel information is generated by: obtaining input images of the person; wherein each image comprises the person and an arbitrary background; repeating, for each input image of the input images, converting the input image, by a portrait matting predictor, to (a) a first colored background image that comprises the person and a background of a first color, and (b) a second colored background image that comprises the person and a background of a second color; wherein the first color differs from the second color.