中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

6 records (took 0.035 seconds)

    Surface normals for pixel-aligned object
    1.
    发明授权
    Surface normals for pixel-aligned object 有权

    公开(公告)号：US12148105B2

    公开(公告)日：2024-11-19

    申请号：US17841994

    申请日：2022-06-16

    Applicant: Snap Inc.

    Inventor： Madiyar Aitbayev ,  Brian Fulkerson ,  Riza Alp Guler ,  Georgios Papandreou ,  Himmy Tam

    IPC: G06T19/00 ,  G06T7/11 ,  G06T7/194 ,  G06T7/70 ,  G06T15/50 ,  G06T15/60 ,  G06T19/20

    Abstract: Methods and systems are disclosed for performing operations for applying augmented reality elements to a person depicted in an image. The operations include receiving an image that includes data representing a depiction of a person; generating a segmentation of the data representing the person depicted in the image; extracting a portion of the image corresponding to the segmentation of the data representing the person depicted in the image; applying a machine learning model to the portion of the image to predict a surface normal tensor for the data representing the depiction of the person, the surface normal tensor representing surface normals of each pixel within the portion of the image; and applying one or more augmented reality (AR) elements to the image based on the surface normal tensor.

    Pixel depth determination for object
    2.
    发明授权
    Pixel depth determination for object 有权

    公开(公告)号：US12254577B2

    公开(公告)日：2025-03-18

    申请号：US17842006

    申请日：2022-06-16

    Applicant: Snap Inc.

    Inventor： Madiyar Aitbayev ,  Brian Fulkerson ,  Riza Alp Guler ,  Georgios Papandreou ,  Himmy Tam

    IPC: G06T19/00 ,  G06N20/20 ,  G06V10/26 ,  G06V10/70 ,  G06V20/20

    Abstract: Methods and systems are disclosed for performing operations for applying augmented reality elements to a person depicted in an image. The operations include receiving an image that includes data representing a depiction of a person; extracting a portion of the image; applying a first machine learning model stage to the portion to predict a depth of a point of interest for the data representing the depiction of the person; applying a second machine learning model stage to the portion of the image to predict a relative depth of each pixel in the portion of the image to the predicted depth of the point of interest; generating dense depth reconstruction of the data representing the depiction of the person based on outputs of the first and second stages of the machine learning model; and applying one or more AR elements to the image based on the dense depth reconstruction.

    SURFACE NORMALS FOR PIXEL-ALIGNED OBJECT
    3.
    发明申请
    SURFACE NORMALS FOR PIXEL-ALIGNED OBJECT 有权

    公开(公告)号：US20240404220A1

    公开(公告)日：2024-12-05

    申请号：US18798370

    申请日：2024-08-08

    Applicant: Snap Inc.

    Inventor： Madiyar Aitbayev ,  Brian Fulkerson ,  Riza Alp Guler ,  Georgios Papandreou ,  Himmy Tam

    IPC: G06T19/00 ,  G06T7/11 ,  G06T7/194 ,  G06T7/70 ,  G06T15/50 ,  G06T15/60 ,  G06T19/20

    Abstract: Methods and systems are disclosed for performing operations for applying augmented reality elements to a person depicted in an image. The operations include receiving an image that includes data representing a depiction of a person; generating a segmentation of the data representing the person depicted in the image; extracting a portion of the image corresponding to the segmentation of the data representing the person depicted in the image; applying a machine learning model to the portion of the image to predict a surface normal tensor for the data representing the depiction of the person, the surface normal tensor representing surface normals of each pixel within the portion of the image; and applying one or more augmented reality (AR) elements to the image based on the surface normal tensor.

    PIXEL DEPTH DETERMINATION FOR OBJECT
    5.
    发明公开
    PIXEL DEPTH DETERMINATION FOR OBJECT 审中-公开

    公开(公告)号：US20230316666A1

    公开(公告)日：2023-10-05

    申请号：US17842006

    申请日：2022-06-16

    Applicant: Snap Inc.

    Inventor： Madiyar Aitbayev ,  Brian Fulkerson ,  Riza Alp Guler ,  Georgios Papandreou ,  Himmy Tam

    IPC: G06T19/00 ,  G06V10/70 ,  G06V10/26 ,  G06V20/20 ,  G06N20/20

    CPC classification number: G06T19/006 ,  G06V10/70 ,  G06V10/26 ,  G06V20/20 ,  G06N20/20

    Abstract: Methods and systems are disclosed for performing operations for applying augmented reality elements to a person depicted in an image. The operations include receiving an image that includes data representing a depiction of a person; extracting a portion of the image; applying a first machine learning model stage to the portion to predict a depth of a point of interest for the data representing the depiction of the person; applying a second machine learning model stage to the portion of the image to predict a relative depth of each pixel in the portion of the image to the predicted depth of the point of interest; generating dense depth reconstruction of the data representing the depiction of the person based on outputs of the first and second stages of the machine learning model; and applying one or more AR elements to the image based on the dense depth reconstruction.

Patent Agency Ranking