中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

15 records (took 0.018 seconds)

    SENDER-SIDE GEOMETRIC FUSION OF DEPTH DATA
    1.
    发明公开
    SENDER-SIDE GEOMETRIC FUSION OF DEPTH DATA 审中-公开

    公开(公告)号：US20230396751A1

    公开(公告)日：2023-12-07

    申请号：US18250059

    申请日：2020-10-23

    Applicant: Google LLC

    Inventor： Hugues Herve Hoppe ,  Ricardo Martin Brualla ,  Harris Nover

    IPC: H04N13/128 ,  H04N13/111

    CPC classification number: H04N13/128 ,  H04N13/111

    Abstract: Systems and methods are described for utilizing an image processing system with at least one processing device to perform operations including receiving a plurality of depth views of an object, each of the plurality of depth views being captured from a respective viewpoint of the object, each of the plurality of depth views including respective depth data associated with a depth image of the object captured from the respective viewpoint, performing an aggregation operation on the plurality of depth views, and generating an image of the object from a target viewpoint based on the updated depth views, the target viewpoint being different from each of the respective viewpoints from which each of the plurality of depth views are captured.

    FEW-SHOT SYNTHESIS OF TALKING HEADS
    2.
    发明申请
    FEW-SHOT SYNTHESIS OF TALKING HEADS 有权

    公开(公告)号：US20220130111A1

    公开(公告)日：2022-04-28

    申请号：US17310678

    申请日：2020-10-28

    Applicant: Google LLC

    Inventor： Ricardo Martin Brualla ,  Moustafa Meshry ,  Daniel Goldman ,  Rohit Kumar Pandey ,  Sofien Bouaziz ,  Ke Li

    IPC: G06T17/20 ,  G06T15/04 ,  G06T7/40

    Abstract: Systems and methods are described for utilizing an image processing system with at least one processing device to perform operations including receiving a plurality of input images of a user, generating a three-dimensional mesh proxy based on a first set of features extracted from the plurality of input images and a second set of features extracted from the plurality of input images. The method may further include generating a neural texture based on a three-dimensional mesh proxy and the plurality of input images, generating a representation of the user including at least a neural texture, and sampling at least one portion of the neural texture from the three-dimensional mesh proxy. In response to providing the at least one sampled portion to a neural renderer, the method may include receiving, from the neural renderer, a synthesized image of the user that is previously not captured by the image processing system.

    Image-based geometric fusion of multiple depth images using ray casting
    4.
    发明授权
    Image-based geometric fusion of multiple depth images using ray casting 有权

    公开(公告)号：US10818071B1

    公开(公告)日：2020-10-27

    申请号：US16523702

    申请日：2019-07-26

    Applicant: Google LLC

    Inventor： Hugues Hoppe ,  Ricardo Martin Brualla ,  Harris Nover

    IPC: G06T15/06 ,  G06T7/70 ,  G06T7/55 ,  G06T15/20 ,  H04N13/111

    Abstract: Techniques of rendering images includes generating signed distance values (SDVs) along a ray from a specified viewpoint in terms of projected distances along that ray from given depth images. For each pixel in an image of from the perspective of the specified viewpoint, a ray is traced into the three-dimensional scene represented by the image. An iterative step is performed along the ray, obtaining in each iteration a three-dimensional world-space point p. The result is the signed distance sj as measured from depth view Dj. If the absolute value of the signed distance sj is greater than some truncation threshold parameter, the signed distance sj is replaced by a special undefined value. The defined signed-distance values are aggregated to obtain an overall signed distance s. Finally, the roots or zero set (isosurface) of the signed distance field is determined.

    Few-shot synthesis of talking heads
    5.
    发明授权
    Few-shot synthesis of talking heads 有权

    公开(公告)号：US12026833B2

    公开(公告)日：2024-07-02

    申请号：US17310678

    申请日：2020-10-28

    Applicant: Google LLC

    Inventor： Ricardo Martin Brualla ,  Moustafa Meshry ,  Daniel Goldman ,  Rohit Kumar Pandey ,  Sofien Bouaziz ,  Ke Li

    IPC: G06T17/20 ,  G06T7/40 ,  G06T15/04

    CPC classification number: G06T17/20 ,  G06T7/40 ,  G06T15/04 ,  G06T2207/10028 ,  G06T2207/20081 ,  G06T2207/30201

    Abstract: Systems and methods are described for utilizing an image processing system with at least one processing device to perform operations including receiving a plurality of input images of a user, generating a three-dimensional mesh proxy based on a first set of features extracted from the plurality of input images and a second set of features extracted from the plurality of input images. The method may further include generating a neural texture based on a three-dimensional mesh proxy and the plurality of input images, generating a representation of the user including at least a neural texture, and sampling at least one portion of the neural texture from the three-dimensional mesh proxy. In response to providing the at least one sampled portion to a neural renderer, the method may include receiving, from the neural renderer, a synthesized image of the user that is previously not captured by the image processing system.

    DEFORMABLE NEURAL RADIANCE FIELDS
    9.
    发明公开
    DEFORMABLE NEURAL RADIANCE FIELDS 审中-公开

    公开(公告)号：US20240005590A1

    公开(公告)日：2024-01-04

    申请号：US18251995

    申请日：2021-01-14

    Applicant: GOOGLE LLC

    Inventor： Ricardo Martin Brualla ,  Keunhong Park ,  Utkarsh Sinha ,  Sofien Bouaziz ,  Daniel Goldman ,  Jonathan Tilton Barron ,  Steven Maxwell Seitz

    IPC: G06T15/20 ,  G06T15/55 ,  G06T15/04

    CPC classification number: G06T15/20 ,  G06T15/55 ,  G06T15/04

    Abstract: Techniques of image synthesis using a neural radiance field (NeRF) includes generating a deformation model of movement experienced by a subject in a non-rigidly deforming scene. For example, when an image synthesis system uses NeRFs, the system takes as input multiple poses of subjects for training data. In contrast to conventional NeRFs, the technical solution first expresses the positions of the subjects from various perspectives in an observation frame. The technical solution then involves deriving a deformation model, i.e., a mapping between the observation frame and a canonical frame in which the subject's movements are taken into account. This mapping is accomplished using latent deformation codes for each pose that are determined using a multilayer perceptron (MLP). A NeRF is then derived from positions and casted ray directions in the canonical frame using another MLP. New poses for the subject may then be derived using the NeRF.

    NEURAL BLENDING FOR NOVEL VIEW SYNTHESIS
    10.
    发明申请
    NEURAL BLENDING FOR NOVEL VIEW SYNTHESIS 有权

    公开(公告)号：US20220398705A1

    公开(公告)日：2022-12-15

    申请号：US17754392

    申请日：2021-04-08

    Applicant: GOOGLE LLC

    Inventor： Ricardo Martin Brualla ,  Daniel Goldman ,  Hugues Herve Hoppe ,  Lynn Tsai ,  Lars Peter Johannes Hedman

    IPC: G06T5/50 ,  G06T3/00 ,  G06T5/00 ,  G06T15/20 ,  G06T7/55

    Abstract: Systems and methods are described for receiving a plurality of input images, a plurality of depth images, and a plurality of view parameters for generating a virtual view of a target subject. The systems and methods may generate a plurality of warped images based on the plurality of input images, the plurality of view parameters, and at least one of the plurality of depth images. In response to providing the plurality of depth images, the plurality of view parameters, and the plurality of warped images to a neural network, the systems and methods may receive, from the neural network, blending weights for assigning color to pixels of the virtual view of the target subject and may generate, based on the blending weights and the virtual view, a synthesized image according to the view parameters.

Patent Agency Ranking