Pixel depth determination for object

    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.

    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

    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.

    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.

    SURFACE NORMALS FOR PIXEL-ALIGNED OBJECT

    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.

    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

    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.

    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