知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

172 records (took 0.026 seconds)

    NEURAL NETWORK ARCHITECTURE FOR IMPLICIT LEARNING OF A PARAMETRIC DISTRIBUTION OF DATA
    71.
    发明申请
    NEURAL NETWORK ARCHITECTURE FOR IMPLICIT LEARNING OF A PARAMETRIC DISTRIBUTION OF DATA 有权

    公开(公告)号：US20250111476A1

    公开(公告)日：2025-04-03

    申请号：US18890544

    申请日：2024-09-19

    Applicant: NVIDIA Corporation

    Inventor： Benjamin David Eckart ,  Anthea Li ,  Chao Liu ,  Kevin Shih ,  Jan Kautz

    IPC: G06T3/4046

    Abstract: Parametric distributions of data are one type of data model that can be used for various purposes such as for computer vision tasks that may include classification, segmentation, 3D reconstruction, etc. These parametric distributions of data may be computed from a given data set, which may be unstructured and/or which may include low-dimensional data. Current solutions for learning parametric distributions of data involve explicitly learning kernel parameters. However, this explicit learning approach is not only inefficient in that it requires a high computational cost (i.e. from a large number of floating point operations per second), but it also leaves room for improvement in terms of accuracy of the resulting learned model. The present disclosure provides a neural network architecture that implicitly learns a parametric distribution of data, which can reduce the computational cost while improve accuracy when compared with prior solutions that rely on the explicit learning design.

    Learning dense correspondences for images
    72.
    发明授权
    Learning dense correspondences for images 有权

    公开(公告)号：US12169882B2

    公开(公告)日：2024-12-17

    申请号：US17929182

    申请日：2022-09-01

    Applicant: NVIDIA Corporation

    Inventor： Sifei Liu ,  Jiteng Mu ,  Shalini De Mello ,  Zhiding Yu ,  Jan Kautz

    IPC: G06T11/00 ,  G06T3/18

    Abstract: Embodiments of the present disclosure relate to learning dense correspondences for images. Systems and methods are disclosed that disentangle structure and texture (or style) representations of GAN synthesized images by learning a dense pixel-level correspondence map for each image during image synthesis. A canonical coordinate frame is defined and a structure latent code for each generated image is warped to align with the canonical coordinate frame. In sum, the structure associated with the latent code is mapped into a shared coordinate space (canonical coordinate space), thereby establishing correspondences in the shared coordinate space. A correspondence generation system receives the warped coordinate correspondences as an encoded image structure. The encoded image structure and a texture latent code are used to synthesize an image. The shared coordinate space enables propagation of semantic labels from reference images to synthesized images.

    LANDMARK DETECTION WITH AN ITERATIVE NEURAL NETWORK
    75.
    发明公开
    LANDMARK DETECTION WITH AN ITERATIVE NEURAL NETWORK 审中-公开

    公开(公告)号：US20240096115A1

    公开(公告)日：2024-03-21

    申请号：US18243555

    申请日：2023-09-07

    Applicant: NVIDIA Corporation

    Inventor： Pavlo Molchanov ,  Jan Kautz ,  Arash Vahdat ,  Hongxu Yin ,  Paul Micaelli

    IPC: G06V20/59 ,  G06T7/70 ,  G06V10/82 ,  G06V20/70 ,  G06V40/16

    CPC classification number: G06V20/597 ,  G06T7/70 ,  G06V10/82 ,  G06V20/70 ,  G06V40/171 ,  G06T2207/30201 ,  G06V2201/07

    Abstract: Landmark detection refers to the detection of landmarks within an image or a video, and is used in many computer vision tasks such emotion recognition, face identity verification, hand tracking, gesture recognition, and eye gaze tracking. Current landmark detection methods rely on a cascaded computation through cascaded networks or an ensemble of multiple models, which starts with an initial guess of the landmarks and iteratively produces corrected landmarks which match the input more finely. However, the iterations required by current methods typically increase the training memory cost linearly, and do not have an obvious stopping criteria. Moreover, these methods tend to exhibit jitter in landmark detection results for video. The present disclosure improves current landmark detection methods by providing landmark detection using an iterative neural network. Furthermore, when detecting landmarks in video, the present disclosure provides for a reduction in jitter due to reuse of previous hidden states from previous frames.

    Few-shot viewpoint estimation
    78.
    发明授权
    Few-shot viewpoint estimation 有权

    公开(公告)号：US11375176B2

    公开(公告)日：2022-06-28

    申请号：US16780738

    申请日：2020-02-03

    Applicant: NVIDIA Corporation

    Inventor： Hung-Yu Tseng ,  Shalini De Mello ,  Jonathan Tremblay ,  Sifei Liu ,  Jan Kautz ,  Stanley Thomas Birchfield

    IPC: H04N13/282 ,  H04N13/268 ,  G06K9/62 ,  G06N3/08

    Abstract: When an image is projected from 3D, the viewpoint of objects in the image, relative to the camera, must be determined. Since the image itself will not have sufficient information to determine the viewpoint of the various objects in the image, techniques to estimate the viewpoint must be employed. To date, neural networks have been used to infer such viewpoint estimates on an object category basis, but must first be trained with numerous examples that have been manually created. The present disclosure provides a neural network that is trained to learn, from just a few example images, a unique viewpoint estimation network capable of inferring viewpoint estimations for a new object category.

    Systems and methods for pruning neural networks for resource efficient inference
    80.
    发明授权
    Systems and methods for pruning neural networks for resource efficient inference 有权

    公开(公告)号：US11315018B2

    公开(公告)日：2022-04-26

    申请号：US15786406

    申请日：2017-10-17

    Applicant: NVIDIA Corporation

    Inventor： Pavlo Molchanov ,  Stephen Walter Tyree ,  Tero Tapani Karras ,  Timo Oskari Aila ,  Jan Kautz

    IPC: G06N3/08 ,  G06N3/04

    Abstract: A method, computer readable medium, and system are disclosed for neural network pruning. The method includes the steps of receiving first-order gradients of a cost function relative to layer parameters for a trained neural network and computing a pruning criterion for each layer parameter based on the first-order gradient corresponding to the layer parameter, where the pruning criterion indicates an importance of each neuron that is included in the trained neural network and is associated with the layer parameter. The method includes the additional steps of identifying at least one neuron having a lowest importance and removing the at least one neuron from the trained neural network to produce a pruned neural network.

Patent Agency Ranking