中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

5367 records (took 0.042 seconds)

    Automated dance animation
    781.
    发明授权
    Automated dance animation 有权

    公开(公告)号：US11176723B2

    公开(公告)日：2021-11-16

    申请号：US16588446

    申请日：2019-09-30

    Applicant: Snap Inc.

    Inventor： Gurunandan Krishnan Gorumkonda ,  Shree K. Nayar

    IPC: G06T13/20 ,  G06T7/246 ,  G06T13/80 ,  G06T13/40

    Abstract: Methods, devices, media, and other embodiments are described for generating, modifying, and outputting pseudorandom animations that can be synchronized to audio data. In one embodiment, a computer animation model made up of comprising one or more control points is accessed by one or more processors, which associate motion patterns with a first control point of the one or more control points, and associate one or more speed harmonics with the first control point. A set of motion states is identify with a motion state for the combinations of possibilities, and a probability value is assigned to each motion state of the set of motion states. The probability value can be used to probabilistically determine a particular motion state to be part of displayed animation for the computer animation model.

    CHARGE CABLE DEADZONE MITIGATION
    783.
    发明申请
    CHARGE CABLE DEADZONE MITIGATION 有权

    公开(公告)号：US20210344207A1

    公开(公告)日：2021-11-04

    申请号：US17377113

    申请日：2021-07-15

    Applicant: Snap Inc.

    Inventor： Shaheen Moubedi

    IPC: H02J7/00

    Abstract: A charging cable is configured to rotate freely while attached to a cable plug on a chargeable device. The plug has contact pads separated by an insulator, and the matching cable head has pins for contacting the pads of the plug. There may be a ‘deadzone’ position where one or more pins of the cable head rest of the separator and do not make contact with the charge pads on the cable plug. The examples include pins in the cable head for redundant charging paths that are complimentary such that only one of the power paths will be on at any given time.

    VIDEO GENERATION SYSTEM TO RENDER FRAMES ON DEMAND USING A FLEET OF SERVERS
    787.
    发明申请
    VIDEO GENERATION SYSTEM TO RENDER FRAMES ON DEMAND USING A FLEET OF SERVERS 有权

    公开(公告)号：US20210342384A1

    公开(公告)日：2021-11-04

    申请号：US17327050

    申请日：2021-05-21

    Applicant: Snap Inc.

    Inventor： Allan Baril ,  Chirag Gada

    IPC: G06F16/438 ,  H04N21/262 ,  H04L29/06 ,  G06F16/48 ,  H04N21/845

    Abstract: Content controller system comprising rendering server system comprising a plurality of servers. The servers receiving a plurality of segment render requests that correspond respectively to segments included in a set of media content item segments. The servers render the segments corresponding to the segment render requests using a media content identification and a main user identification. Rendering the segments comprises retrieving metadata from a metadata database associated with the media content identification, rendering the segments using the metadata, generating a main user avatar based on the main user identification, and incorporating the main user avatar into the segments. The servers can upload the segments to a segment database and update segment states in a segment state database to indicate that the segments are available. Other embodiments are disclosed herein.

    TEXT AND AUDIO-BASED REAL-TIME FACE REENACTMENT
    788.
    发明申请
    TEXT AND AUDIO-BASED REAL-TIME FACE REENACTMENT 有权

    公开(公告)号：US20210327404A1

    公开(公告)日：2021-10-21

    申请号：US17355834

    申请日：2021-06-23

    Applicant: Snap Inc.

    Inventor： Pavel Savchenkov ,  Maxim Lukin ,  Aleksandr Mashrabov

    IPC: G10L13/00 ,  G06K9/00 ,  G10L13/08 ,  G06T13/40

    Abstract: Provided are systems and methods for text and audio-based real-time face reenactment. An example method includes receiving an input text and a target image, the target image including a target face; generating, based on the input text, a sequence of sets of acoustic features representing the input text; generating, based on the sequence of sets of acoustic features, a sequence of sets of mouth key points; generating, based on the sequence of sets of mouth key points, a sequence of sets of facial key points; generating, by the computing device and based on the sequence of sets of the facial key points and the target image, a sequence of frames; and generating, based on the sequence of frames, an output video. Each of the frames includes the target face modified based on at least one set of mouth key points of the sequence of sets of mouth key points.

    OCCLUSION DETECTION SYSTEM
    789.
    发明申请
    OCCLUSION DETECTION SYSTEM 有权

    公开(公告)号：US20210326635A1

    公开(公告)日：2021-10-21

    申请号：US17361857

    申请日：2021-06-29

    Applicant: Snap Inc.

    Inventor： Piers Cowburn ,  David Li ,  Isac Andreas Müller Sandvik ,  Qi Pan

    IPC: G06K9/62 ,  G06T7/90 ,  H04W4/30 ,  G06T19/00 ,  H04L12/58 ,  H04W4/021

    Abstract: An occlusion detection system to perform operations that include: capturing image data that depicts an environment at a client device, the environment including a target object at a position within the environment; causing display of a presentation of the environment at the client device, the presentation of the environment including a display of the target object at the position within the environment; detecting a first attribute of the display of the target object at the client device; performing a comparison of the first attribute of the display of the target object and a second attribute associated with the target object; and detecting an occlusion based on the comparison.

Patent Agency Ranking