Voice note with face tracking
    3.
    发明授权

    公开(公告)号:US12086916B2

    公开(公告)日:2024-09-10

    申请号:US17508636

    申请日:2021-10-22

    申请人: Snap Inc.

    摘要: Methods and systems are disclosed for performing operations for generating a voice note. The operations include receiving, by a messaging application, a request from a first participant to send a voice message to a second participant in a communication session. The operations include, in response to receiving the request, generating an audio file comprising a specified duration of speech input received from the first participant. The operations include associating the audio file with an avatar that represents the first participant. The operations include presenting an interactive visual indicator of the avatar among a plurality of messages in the communication session. The operations include receiving, by the messaging application, input that selects the interactive visual indicator of the avatar. The operations include, in response to receiving the input, rendering an animation of the avatar speaking the speech input while playing the audio file.

    VR SCENE SWITCHING METHOD AND DEVICE, VR HEAD-MOUNTED EQUIPMENT AND STORAGE MEDIUM

    公开(公告)号:US20240296631A1

    公开(公告)日:2024-09-05

    申请号:US18245702

    申请日:2021-12-07

    申请人: GOERTEK INC.

    发明人: Feng CHEN Zengsen CUI

    IPC分类号: G06T19/00 G06T13/20

    CPC分类号: G06T19/006 G06T13/20

    摘要: A VR scene switching method applied to a VR head-mounted equipment is disclosed. The method is applied to a VR head-mounted equipment equipped with a camera. The VR scene switching method comprises: collecting a real environment picture using the camera, and generating a real scene content added with a scene switching element according to the real environment picture; displaying the real scene content on a display screen of the VR head-mounted equipment; judging whether a control instruction of entering a virtual scene is received; if yes, displaying a transition animation on the display screen of the VR head-mounted equipment, wherein the transition animation comprises a process that a user enters the virtual scene via the scene switching element; and displaying the virtual scene content on the display screen of the VR head-mounted equipment.

    TEMPORALLY COHERENT VOLUMETRIC VIDEO
    7.
    发明公开

    公开(公告)号:US20240282046A1

    公开(公告)日:2024-08-22

    申请号:US18110497

    申请日:2023-02-16

    申请人: YOOM.COM LTD.

    摘要: Systems and methods for generating a volumetric video in which all frames are temporally coherent. Method for generating a temporally coherent plurality of frames in a volumetric video, including finding a deformation field transforming a source frame of the volumetric video into a target frame of the volumetric video including building a texture implicit function for said target frame; training a neural network to generate said deformation field between said source frame and said target frame, said texture implicit function for said target frame being a texture matching loss for said neural network; applying said deformation field to said source frame, thereby generating a deformed source frame; selecting a plurality of frames in said volumetric video; selecting a first source frame in said plurality of frames; repeating the steps of finding said deformed source frame for each target frame, said finding of said deformed source frame following one of the following paths: finding a first deformed source frame from said first source frame; and each subsequent source frame being a deformed source frame from a previous pair of frames; or each of said target frames being a deformation of said first source frame.

    METHODS FOR SIMULATING QUASI-STATIC VOLUME PRESERVING DEFORMATION

    公开(公告)号:US20240282032A1

    公开(公告)日:2024-08-22

    申请号:US18625164

    申请日:2024-04-02

    摘要: A computer-implemented method of simulating deformation of a solid body comprises: defining a mesh representation of the solid body, the mesh representation comprising a plurality of mesh elements, each mesh element defined by a plurality of vertices; receiving a material model comprising one or more material properties of the solid body; and for each of the plurality of vertices defining the plurality of mesh elements, determining a subsequent position of the vertex at a subsequent time step, wherein determining the subsequent position comprises: defining a current position and a current velocity of the vertex; defining a positional constraint of the vertex based on the material model; and computing a subsequent position of the vertex based on at least the current position, the current velocity and the positional constraint.