中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

32 records (took 0.023 seconds)

    MODEL-BASED THREE-DIMENSIONAL HEAD POSE ESTIMATION
    12.
    发明申请
    MODEL-BASED THREE-DIMENSIONAL HEAD POSE ESTIMATION 审中-公开

    公开(公告)号：US20180075611A1

    公开(公告)日：2018-03-15

    申请号：US15823370

    申请日：2017-11-27

    Applicant: NVIDIA Corporation

    Inventor： Gregory P. MEYER ,  Shalini GUPTA ,  Iuri FROSIO ,  Nagilla Dikpal REDDY ,  Jan KAUTZ

    IPC: G06T7/507 ,  G06T7/70

    CPC classification number: G06T7/507 ,  G06K9/6276 ,  G06T7/251 ,  G06T7/277 ,  G06T7/70 ,  G06T7/75 ,  G06T7/77 ,  G06T2200/28 ,  G06T2207/10016 ,  G06T2207/10028 ,  G06T2207/30201

    Abstract: One embodiment of the present invention sets forth a technique for estimating a head pose of a user. The technique includes acquiring depth data associated with a head of the user and initializing each particle included in a set of particles with a different candidate head pose. The technique further includes performing one or more optimization passes that include performing at least one iterative closest point (ICP) iteration for each particle and performing at least one particle swarm optimization (PSO) iteration. Each ICP iteration includes rendering the three-dimensional reference model based on the candidate head pose associated with the particle and comparing the three-dimensional reference model to the depth data. Each PSO iteration comprises updating a global best head pose associated with the set of particles and modifying at least one candidate head pose. The technique further includes modifying a shape of the three-dimensional reference model based on depth data.

    MODEL-BASED THREE-DIMENSIONAL HEAD POSE ESTIMATION
    13.
    发明申请
    MODEL-BASED THREE-DIMENSIONAL HEAD POSE ESTIMATION 有权
    基于模型的三维头位估计

    公开(公告)号：US20170046827A1

    公开(公告)日：2017-02-16

    申请号：US14825129

    申请日：2015-08-12

    Applicant: NVIDIA CORPORATION

    Inventor： Gregory P. MEYER ,  Shalini GUPTA ,  Iuri FROSIO ,  Nagilla Dikpal REDDY ,  Jan KAUTZ

    IPC: G06T7/00

    CPC classification number: G06T7/507 ,  G06K9/6276 ,  G06T7/251 ,  G06T7/277 ,  G06T7/70 ,  G06T7/75 ,  G06T7/77 ,  G06T2200/28 ,  G06T2207/10016 ,  G06T2207/10028 ,  G06T2207/30201

    Abstract: One embodiment of the present invention sets forth a technique for estimating a head pose of a user. The technique includes acquiring depth data associated with a head of the user and initializing each particle included in a set of particles with a different candidate head pose. The technique further includes performing one or more optimization passes that include performing at least one iterative closest point (ICP) iteration for each particle and performing at least one particle swarm optimization (PSO) iteration. Each ICP iteration includes rendering the three-dimensional reference model based on the candidate head pose associated with the particle and comparing the three-dimensional reference model to the depth data. Each PSO iteration comprises updating a global best head pose associated with the set of particles and modifying at least one candidate head pose. The technique further includes modifying a shape of the three-dimensional reference model based on depth data.

    Abstract translation: 本发明的一个实施例提出了一种用于估计用户的头部姿势的技术。 该技术包括获取与用户头部相关联的深度数据并且初始化包含在具有不同候选头姿势的一组粒子中的每个粒子。 该技术还包括执行一个或多个优化遍，包括对每个粒子执行至少一个迭代最近点（ICP）迭代并且执行至少一个粒子群优化（PSO）迭代。 每个ICP迭代包括基于与粒子相关联的候选头部姿态来渲染三维参考模型，并将三维参考模型与深度数据进行比较。 每个PSO迭代包括更新与该组粒子相关联的全局最佳头部姿态并修改至少一个候选头姿势。 该技术还包括基于深度数据修改三维参考模型的形状。

    FEW-SHOT CONTINUAL LEARNING WITH TASK-SPECIFIC PARAMETER SELECTION
    14.
    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
    15.
    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.

    IMAGE STITCHING WITH DYNAMIC SEAM PLACEMENT BASED ON EGO-VEHICLE STATE FOR SURROUND VIEW VISUALIZATION
    16.
    发明公开
    IMAGE STITCHING WITH DYNAMIC SEAM PLACEMENT BASED ON EGO-VEHICLE STATE FOR SURROUND VIEW VISUALIZATION 审中-公开

    公开(公告)号：US20230319218A1

    公开(公告)日：2023-10-05

    申请号：US18173603

    申请日：2023-02-23

    Applicant: NVIDIA Corporation

    Inventor： Yuzhuo REN ,  Nuri Murat ARAR ,  Orazio GALLO ,  Jan KAUTZ ,  Niranjan AVADHANAM ,  Hang SU

    IPC: H04N5/262 ,  G06V20/56

    CPC classification number: H04N5/2624 ,  G06V20/56

    Abstract: In various examples, a state machine is used to select between a default seam placement or dynamic seam placement that avoids salient regions, and to enable and disable dynamic seam placement based on speed of ego-motion, direction of ego-motion, proximity to salient objects, active viewport, driver gaze, and/or other factors. Images representing overlapping views of an environment may be aligned to create an aligned composite image or surface (e.g., a panorama, a 360° image, bowl shaped surface) with overlapping regions of image data, and a default or dynamic seam placement may be selected based on driving scenario (e.g., driving direction, speed, proximity to nearby objects). As such, seams may be positioned in the overlapping regions of image data, and the image data may be blended at the seams to create a stitched image or surface (e.g., a stitched panorama, stitched 360° image, stitched textured surface).

    MACHINE-LEARNING TECHNIQUES FOR SPARSE-TO-DENSE SPECTRAL RECONSTRUCTION
    18.
    发明公开
    MACHINE-LEARNING TECHNIQUES FOR SPARSE-TO-DENSE SPECTRAL RECONSTRUCTION 审中-公开

    公开(公告)号：US20230267659A1

    公开(公告)日：2023-08-24

    申请号：US17933811

    申请日：2022-09-20

    Applicant: NVIDIA CORPORATION

    Inventor： Benjamin ECKART ,  Jan KAUTZ ,  Chao LIU ,  Benjamin WU

    IPC: G06T11/00 ,  G06F17/14 ,  G01B9/02

    CPC classification number: G06T11/006 ,  G06F17/141 ,  G01B9/02041

    Abstract: In various embodiments, an inference application reconstructs representations of items in a spectral domain. The inference application maps a first set of data points associated with a both an item and the spectral domain to conditioning information via a first trained machine learning model. The inference application updates a second trained machine learning model based on the conditioning information to generate a model that represents the item within the spectral domain. The inference application generates a second set of data points associated with both the item and the spectral domain via the model. The inference application constructs an image associated with the item based on the second set of data points.

    SCORE-BASED GENERATIVE MODELING IN LATENT SPACE
    19.
    发明申请
    SCORE-BASED GENERATIVE MODELING IN LATENT SPACE 有权

    公开(公告)号：US20220398697A1

    公开(公告)日：2022-12-15

    申请号：US17681625

    申请日：2022-02-25

    Applicant: NVIDIA CORPORATION

    Inventor： Arash VAHDAT ,  Karsten KREIS ,  Jan KAUTZ

    IPC: G06T5/00 ,  G06N3/08

    Abstract: One embodiment of the present invention sets forth a technique for generating data. The technique includes sampling from a first distribution associated with the score-based generative model to generate a first set of values. The technique also includes performing one or more denoising operations via the score-based generative model to convert the first set of values into a first set of latent variable values associated with a latent space. The technique further includes converting the first set of latent variable values into a generative output.

Patent Agency Ranking