中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

17 records (took 0.028 seconds)

    Few-shot synthesis of talking heads
    1.
    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
    2.
    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
    3.
    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.

    Real-time spacetime stereo using spacetime descriptors
    6.
    发明授权
    Real-time spacetime stereo using spacetime descriptors 有权

    公开(公告)号：US11190746B2

    公开(公告)日：2021-11-30

    申请号：US16710655

    申请日：2019-12-11

    Applicant: GOOGLE LLC

    Inventor： Daniel Goldman ,  Harris Nover ,  Supreeth Achar

    IPC: H04N13/106 ,  H04N13/254 ,  G06T7/593 ,  G06T7/11 ,  G06T5/00 ,  G06T7/174 ,  H04N13/00

    Abstract: According to an aspect, a real-time active stereo system includes a capture system configured to capture stereo image data, where the image data includes a plurality of pairs of a reference image and a secondary image, and each pair of the plurality of pairs relates a different temporal window. The real-time active stereo system includes a depth sensing computing system including at least one processor and a non-transitory computer-readable medium having executable instructions that when executed by the at least one processor are configured to execute a local stereo reconstruction algorithm configured to compute spacetime descriptors from the plurality of pairs of the stereo image data and generate depth maps based on the spacetime descriptors.

    CROSS SPECTRAL FEATURE MAPPING FOR CAMERA CALIBRATION
    9.
    发明申请
    CROSS SPECTRAL FEATURE MAPPING FOR CAMERA CALIBRATION 有权

    公开(公告)号：US20220277485A1

    公开(公告)日：2022-09-01

    申请号：US17597428

    申请日：2021-01-19

    Applicant: Google LLC

    Inventor： Supreeth Achar ,  Daniel Goldman

    IPC: G06T7/80 ,  H04N5/225 ,  G06V10/48 ,  G06V10/60 ,  G06V10/75 ,  H04N13/246 ,  G06T7/73

    Abstract: A method including capturing a first image of a real-world scene by a first camera sensitive to a first spectrum of light, the first camera having a first light source, capturing a second image of the real-world scene by a second camera sensitive to a second spectrum of light, the second camera having a second light source, identifying at least one feature in the first image, identifying, using a machine learning (ML) model, at least one feature in the second image that matches the at least one feature identified in the first image, mapping pixels in the first image and the second image to rays in a three-dimensional (3D) space based on the matched at least one feature, and calibrating the first camera and the second camera based on the mapping.

    Neural rerendering from 3D models
    10.
    发明授权
    Neural rerendering from 3D models 有权

    公开(公告)号：US11288857B2

    公开(公告)日：2022-03-29

    申请号：US16837612

    申请日：2020-04-01

    Applicant: Google LLC

    Inventor： Moustafa Meshry ,  Ricardo Martin Brualla ,  Sameh Khamis ,  Daniel Goldman ,  Hugues Hoppe ,  Noah Snavely ,  Rohit Pandey

    IPC: G06T15/00 ,  G06T15/20 ,  G06T7/174 ,  G06N3/08

    Abstract: According to an aspect, a method for neural rerendering includes obtaining a three-dimensional (3D) model representing a scene of a physical space, where the 3D model is constructed from a collection of input images, rendering an image data buffer from the 3D model according to a viewpoint, where the image data buffer represents a reconstructed image from the 3D model, receiving, by a neural rerendering network, the image data buffer, receiving, by the neural rerendering network, an appearance code representing an appearance condition, and transforming, by the neural rerendering network, the image data buffer into a rerendered image with the viewpoint of the image data buffer and the appearance condition specified by the appearance code.

Patent Agency Ranking