中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

11 records (took 0.018 seconds)

    LEARNING AND PROPAGATING VISUAL ATTRIBUTES
    1.
    发明申请
    LEARNING AND PROPAGATING VISUAL ATTRIBUTES 有权

    公开(公告)号：US20220076128A1

    公开(公告)日：2022-03-10

    申请号：US17017597

    申请日：2020-09-10

    Applicant: NVIDIA CORPORATION

    Inventor： Sifei LIU ,  Shalini DE MELLO ,  Varun JAMPANI ,  Jan KAUTZ

    IPC: G06N3/08 ,  G06N3/04 ,  G06K9/62

    Abstract: One embodiment of the present invention sets forth a technique for performing spatial propagation. The technique includes generating a first directed acyclic graph (DAG) by connecting spatially adjacent points included in a set of unstructured points via directed edges along a first direction. The technique also includes applying a first set of neural network layers to one or more images associated with the set of unstructured points to generate (i) a set of features for the set of unstructured points and (ii) a set of pairwise affinities between the spatially adjacent points connected by the directed edges. The technique further includes generating a set of labels for the set of unstructured points by propagating the set of features across the first DAG based on the set of pairwise affinities.

    FEW-SHOT CONTINUAL LEARNING WITH TASK-SPECIFIC PARAMETER SELECTION
    3.
    发明申请
    FEW-SHOT CONTINUAL LEARNING WITH TASK-SPECIFIC PARAMETER SELECTION 有权

    公开(公告)号：US20250094819A1

    公开(公告)日：2025-03-20

    申请号：US18471184

    申请日：2023-09-20

    Applicant: NVIDIA CORPORATION

    Inventor： Wonmin BYEON ,  Sudarshan BABU ,  Shalini DE MELLO ,  Jan KAUTZ

    IPC: G06N3/096 ,  G06N3/0455

    Abstract: One embodiment of the present invention sets forth a technique for executing a transformer neural network. The technique includes executing a first attention unit included in the transformer neural network to convert a first input token into a first query, a first key, and a first plurality of values, where each value included in the first plurality of values represents a sub-task associated with the transformer neural network. The technique also includes computing a first plurality of outputs associated with the first input token based on the first query, the first key, and the first plurality of values. The technique further includes performing a task associated with an input corresponding to the first input token based on the first input token and the first plurality of outputs.

    TECHNIQUES FOR TRAINING A MACHINE LEARNING MODEL TO RECONSTRUCT DIFFERENT THREE-DIMENSIONAL SCENES
    6.
    发明公开
    TECHNIQUES FOR TRAINING A MACHINE LEARNING MODEL TO RECONSTRUCT DIFFERENT THREE-DIMENSIONAL SCENES 审中-公开

    公开(公告)号：US20240161404A1

    公开(公告)日：2024-05-16

    申请号：US18497938

    申请日：2023-10-30

    Applicant: NVIDIA CORPORATION

    Inventor： Yang FU ,  Sifei LIU ,  Jan KAUTZ ,  Xueting LI ,  Shalini DE MELLO ,  Amey KULKARNI ,  Milind NAPHADE

    IPC: G06T17/20

    CPC classification number: G06T17/20

    Abstract: In various embodiments, a training application trains a machine learning model to generate three-dimensional (3D) representations of two-dimensional images. The training application maps a depth image and a viewpoint to signed distance function (SDF) values associated with 3D query points. The training application maps a red, blue, and green (RGB) image to radiance values associated with the 3DI query points. The training application computes a red, blue, green, and depth (RGBD) reconstruction loss based on at least the SDF values and the radiance values. The training application modifies at least one of a pre-trained geometry encoder, a pre-trained geometry decoder, an untrained texture encoder, or an untrained texture decoder based on the RGBD reconstruction loss to generate a trained machine learning model that generates 3D representations of RGBD images.

    ANIMATABLE CHARACTER GENERATION USING 3D REPRESENTATIONS
    7.
    发明申请
    ANIMATABLE CHARACTER GENERATION USING 3D REPRESENTATIONS 有权

    公开(公告)号：US20250157114A1

    公开(公告)日：2025-05-15

    申请号：US18623745

    申请日：2024-04-01

    Applicant: NVIDIA Corporation

    Inventor： Ye YUAN ,  Xueting LI ,  Umar IQBAL ,  Koki NAGANO ,  Shalini DE MELLO ,  Jan KAUTZ

    IPC: G06T13/40 ,  G06T17/20

    Abstract: In various examples, systems and methods are disclosed relating to generating animatable characters or avatars. The system can assign a plurality of first elements of a three-dimensional (3D) model of a subject to a plurality of locations on a surface of the subject in an initial pose. Further, the system can assign a plurality of second elements to the plurality of first elements, each second element of the plurality of second elements having an opacity corresponding to a distance between the second element and the surface of the subject. Further, the system can update the plurality of second elements based at least on a target pose for the subject and one or more attributes of the subject to determine a plurality of updated second elements. Further, the system can render a representation of the subject based at least on the plurality of updated second elements.

    META-LEARNING OF REPRESENTATIONS USING SELF-SUPERVISED TASKS
    8.
    发明申请
    META-LEARNING OF REPRESENTATIONS USING SELF-SUPERVISED TASKS 有权

    公开(公告)号：US20250103906A1

    公开(公告)日：2025-03-27

    申请号：US18471196

    申请日：2023-09-20

    Applicant: NVIDIA CORPORATION

    Inventor： Wonmin BYEON ,  Sudarshan BABU ,  Shalini DE MELLO ,  Jan KAUTZ

    IPC: G06N3/0985 ,  G06N3/0895

    Abstract: One embodiment of the present invention sets forth a technique for performing meta-learning. The technique includes performing a first set of training iterations to convert a prediction learning network into a first trained prediction learning network based on a first support set of training data and executing a representation learning network and the first trained prediction learning network to generate a first set of supervised training output and a first set of self-supervised training output based on a first query set of training data corresponding to the first support set of training data. The technique also includes performing a first training iteration to convert the representation learning network into a first trained representation learning network based on a first loss associated with the first set of supervised training output and a second loss associated with the first set of self-supervised training output.

    META-TESTING OF REPRESENTATIONS LEARNED USING SELF-SUPERVISED TASKS
    9.
    发明申请
    META-TESTING OF REPRESENTATIONS LEARNED USING SELF-SUPERVISED TASKS 有权

    公开(公告)号：US20250095350A1

    公开(公告)日：2025-03-20

    申请号：US18471209

    申请日：2023-09-20

    Applicant: NVIDIA CORPORATION

    Inventor： Wonmin BYEON ,  Sudarshan BABU ,  Shalini DE MELLO ,  Jan KAUTZ

    IPC: G06V10/82 ,  G06V10/776

    Abstract: One embodiment of the present invention sets forth a technique for executing a machine learning model. The technique includes performing a first set of training iterations to convert a prediction learning network into a first trained prediction learning network based on a first support set associated with a first set of classes. The technique also includes executing a first trained representation learning network to convert a first data sample into a first latent representation, where the first trained representation learning network is generated by training a representation learning network using a first query set, a first set of self-supervised losses, and a first set of supervised losses. The technique further includes executing the first trained prediction learning network to convert the first latent representation into a first prediction of a first class that is not included in the second set of classes.

    TRAINING A TRANSFORMER NEURAL NETWORK TO PERFORM TASK-SPECIFIC PARAMETER SELECTION
    10.
    发明申请
    TRAINING A TRANSFORMER NEURAL NETWORK TO PERFORM TASK-SPECIFIC PARAMETER SELECTION 有权

    公开(公告)号：US20250094813A1

    公开(公告)日：2025-03-20

    申请号：US18471204

    申请日：2023-09-20

    Applicant: NVIDIA CORPORATION

    Inventor： Wonmin BYEON ,  Sudarshan BABU ,  Shalini DE MELLO ,  Jan KAUTZ

    IPC: G06N3/0895

    Abstract: One embodiment of the present invention sets forth a technique for training a transformer neural network. The technique includes inputting a first task token and a first set of samples into the transformer neural network and training the transformer neural network using a first set of losses between predictions generated by the transformer neural network from the first task token and first set of samples as well as a first set of labels. The technique also includes converting the first task token into a second task token that is larger than the first task token, inputting the second task token and a second set of samples into the transformer neural network, and training the transformer neural network using a second set of losses between predictions generated by the transformer neural network from the second task token and the second set of samples as well as a second set of labels.

Patent Agency Ranking