利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

66 条记录 (耗时 0.026 秒)

    USING MACHINE LEARNING FOR SURFACE RECONSTRUCTION IN SYNTHETIC CONTENT GENERATION SYSTEMS AND APPLICATIONS
    2.
    发明公开
    USING MACHINE LEARNING FOR SURFACE RECONSTRUCTION IN SYNTHETIC CONTENT GENERATION SYSTEMS AND APPLICATIONS 审中-公开

    公开(公告)号：US20240296623A1

    公开(公告)日：2024-09-05

    申请号：US18169825

    申请日：2023-02-15

    申请人： Nvidia Corporation

    发明人： Jiahui Huang ,  Francis Williams ,  Zan Gojcic ,  Matan Atzmon ,  Or Litany ,  Sanja Fidler

    IPC分类号： G06T17/20 ,  G06T15/08

    CPC分类号： G06T17/20 ,  G06T15/08 ,  G06T2210/56

    摘要： Approaches presented herein provide for the reconstruction of implicit multi-dimensional shapes. In one embodiment, oriented point cloud data representative of an object can be obtained using a physical scanning process. The point cloud data can be provided as input to a trained density model that can infer density functions for various points. The points can be mapped to a voxel hierarchy, allowing density functions to be determined for those voxels at the various levels that are associated with at least one point of the input point cloud. Contribution weights can be determined for the various density functions for the sparse voxel hierarchy, and the weighted density functions combined to obtain a density field. The density field can be evaluated to generate a geometric mesh where points having a zero, or near-zero, value are determined to contribute to the surface of the object.

    UNSUPERVISED DOMAIN ADAPTATION WITH NEURAL NETWORKS
    3.
    发明公开
    UNSUPERVISED DOMAIN ADAPTATION WITH NEURAL NETWORKS 审中-公开

    公开(公告)号：US20240296205A1

    公开(公告)日：2024-09-05

    申请号：US18656298

    申请日：2024-05-06

    申请人： Nvidia Corporation

    发明人： David Acuna Marrero ,  Guojun Zhang ,  Marc Law ,  Sanja Fidler

    IPC分类号： G06F18/214 ,  G06F18/21 ,  G06F18/241 ,  G06N3/045 ,  G06N3/08 ,  G06V10/40

    CPC分类号： G06F18/2148 ,  G06F18/217 ,  G06F18/241 ,  G06N3/045 ,  G06N3/08 ,  G06V10/40

    摘要： Approaches presented herein provide for unsupervised domain transfer learning. In particular, three neural networks can be trained together using at least labeled data from a first domain and unlabeled data from a second domain. Features of the data are extracted using a feature extraction network. A first classifier network uses these features to classify the data, while a second classifier network uses these features to determine the relevant domain. A combined loss function is used to optimize the networks, with a goal of the feature extraction network extracting features that the first classifier network is able to use to accurately classify the data, but prevent the second classifier from determining the domain for the image. Such optimization enables object classification to be performed with high accuracy for either domain, even though there may have been little to no labeled training data for the second domain.

    SYNTHESIZING HIGH RESOLUTION 3D SHAPES FROM LOWER RESOLUTION REPRESENTATIONS FOR SYNTHETIC DATA GENERATION SYSTEMS AND APPLICATIONS
    9.
    发明申请
    SYNTHESIZING HIGH RESOLUTION 3D SHAPES FROM LOWER RESOLUTION REPRESENTATIONS FOR SYNTHETIC DATA GENERATION SYSTEMS AND APPLICATIONS 有权

    公开(公告)号：US20220392162A1

    公开(公告)日：2022-12-08

    申请号：US17718172

    申请日：2022-04-11

    申请人： NVIDIA Corporation

    发明人： Tianchang Shen ,  Jun Gao ,  Kangxue Yin ,  Ming-Yu Liu ,  Sanja Fidler

    IPC分类号： G06T17/20 ,  G06T7/50

    摘要： In various examples, a deep three-dimensional (3D) conditional generative model is implemented that can synthesize high resolution 3D shapes using simple guides—such as coarse voxels, point clouds, etc.—by marrying implicit and explicit 3D representations into a hybrid 3D representation. The present approach may directly optimize for the reconstructed surface, allowing for the synthesis of finer geometric details with fewer artifacts. The systems and methods described herein may use a deformable tetrahedral grid that encodes a discretized signed distance function (SDF) and a differentiable marching tetrahedral layer that converts the implicit SDF representation to an explicit surface mesh representation. This combination allows joint optimization of the surface geometry and topology as well as generation of the hierarchy of subdivisions using reconstruction and adversarial losses defined explicitly on the surface mesh.

    ARCHITECTURE-AGNOSTIC FEDERATED LEARNING SYSTEM
    10.
    发明申请
    ARCHITECTURE-AGNOSTIC FEDERATED LEARNING SYSTEM 有权

    公开(公告)号：US20220391781A1

    公开(公告)日：2022-12-08

    申请号：US17827446

    申请日：2022-05-27

    申请人： NVIDIA Corporation

    发明人： Or Litany ,  Haggai Maron ,  David Jesus Acuna Marrero ,  Jan Kautz ,  Sanja Fidler ,  Gal Chechik

    IPC分类号： G06N20/20 ,  G06K9/62 ,  G06N7/00

    摘要： A method performed by a server is provided. The method comprises sending copies of a set of parameters of a hyper network (HN) to at least one client device, receiving from each client device in the at least one client device, a corresponding set of updated parameters of the HN, and determining a next set of parameters of the HN based on the corresponding sets of updated parameters received from the at least one client device. Each client device generates the corresponding set of updated parameters based on a local model architecture of the client device.