中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

30 records (took 0.016 seconds)

    Deep novel view synthesis from unstructured input
    1.
    发明授权
    Deep novel view synthesis from unstructured input 有权

    公开(公告)号：US11928787B2

    公开(公告)日：2024-03-12

    申请号：US17028434

    申请日：2020-09-22

    Applicant: Intel Corporation

    Inventor： Gernot Riegler ,  Vladlen Koltun

    IPC: G06T19/00 ,  G06F9/38 ,  G06N3/045 ,  G06T3/00 ,  G06T7/73 ,  G06T19/20

    CPC classification number: G06T19/20 ,  G06F9/3877 ,  G06N3/045 ,  G06T3/0093 ,  G06T7/74

    Abstract: Systems, apparatuses and methods may provide for technology that estimates poses of a plurality of input images, reconstructs a proxy three-dimensional (3D) geometry based on the estimated poses and the plurality of input images, detects a user selection of a virtual viewpoint, encodes, via a first neural network, the plurality of input images with feature maps, warps the feature maps of the encoded plurality of input images based on the virtual viewpoint and the proxy 3D geometry, and blends, via a second neural network, the warped feature maps into a single image, wherein the first neural network is deep convolutional network and the second neural network is a recurrent convolutional network.

    METHODS AND APPARATUS TO PERFORM DENSE PREDICTION USING TRANSFORMER BLOCKS
    3.
    发明申请
    METHODS AND APPARATUS TO PERFORM DENSE PREDICTION USING TRANSFORMER BLOCKS 有权

    公开(公告)号：US20230113271A1

    公开(公告)日：2023-04-13

    申请号：US17855763

    申请日：2022-06-30

    Applicant: Intel Corporation

    Inventor： Renee Ranftl ,  Alexey Bochkovskiy ,  Vladlen Koltun

    IPC: G06T3/40 ,  G06T5/00 ,  G06N3/04

    Abstract: Methods, apparatus, systems and articles of manufacture disclosed herein perform dense prediction of an input image using transformers at an encoder stage and at a reassembly stage of an image processing system. A disclosed apparatus includes an encoder with an embedder to convert an input image to a plurality of tokens representing features extracted from the input image. The tokens are embedded with a learnable position embedding. The encoder also includes one or more transformers configured in a sequence of stages to relate the tokens to each other. The apparatus further includes a decoder that includes one or more of reassemblers to assemble the tokens into feature representations, one or more of fusion blocks to combine the feature representations to generate a final feature representation, and an output head to generate a dense prediction based on the final feature representation and based on an output task.

    Approximating image processing functions using convolutional neural networks
    4.
    发明授权
    Approximating image processing functions using convolutional neural networks 有权

    公开(公告)号：US10430913B2

    公开(公告)日：2019-10-01

    申请号：US15639000

    申请日：2017-06-30

    Applicant: INTEL CORPORATION

    Inventor： Qifeng Chen ,  Jia Xu ,  Vladlen Koltun

    IPC: G06T1/20 ,  G06T5/00

    Abstract: Techniques are provided for approximating image processing functions using convolutional neural networks (CNNs). A methodology implementing the techniques according to an embodiment includes performing, by a CNN, a sequence of non-linear operations on an input image to generate an output image. The generated output image approximates the application of a targeted image processing operator to the input image. The CNN is trained on pairs of training input and output images, wherein the training output images are generated by application of the targeted image processing operator to the training input images. The CNN training process generates bias parameters and convolutional kernel parameters to be employed by the CNN for processing of intermediate image layers associated with processing stages between the input image and the output image, each of the processing stages associated with one of the sequence of non-linear operations. The parameters are associated with the targeted image processing operator.

    METHODS AND APPARATUS TO IMPLEMENT PARALLEL ARCHITECTURES FOR NEURAL NETWORK CLASSIFIERS
    7.
    发明申请
    METHODS AND APPARATUS TO IMPLEMENT PARALLEL ARCHITECTURES FOR NEURAL NETWORK CLASSIFIERS 有权

    公开(公告)号：US20210319319A1

    公开(公告)日：2021-10-14

    申请号：US17359232

    申请日：2021-06-25

    Applicant: Intel Corporation

    Inventor： Ankit Goyal ,  Alexey Bochkovkiy ,  Vladlen Koltun

    IPC: G06N3/08 ,  G06N3/04 ,  G06N3/063 ,  G06K9/62

    Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed to implement parallel architectures for neural network classifiers. An example non-transitory computer readable medium comprises instructions that, when executed, cause a machine to at least: process a first stream using first neural network blocks, the first stream based on an input image; process a second stream using second neural network blocks, the second stream based on the input image; fuse a result of the first neural network blocks and the second neural network blocks; perform average pooling on the fused result; process a fully connected layer based on the result of the average pooling; and classify the image based on the output of the fully connected layer.

    DEEP GEOMETRIC MODEL FITTING
    8.
    发明申请
    DEEP GEOMETRIC MODEL FITTING 审中-公开

    公开(公告)号：US20190043244A1

    公开(公告)日：2019-02-07

    申请号：US15933510

    申请日：2018-03-23

    Applicant: Intel Corporation

    Inventor： Rene Ranftl ,  Vladlen Koltun

    IPC: G06T15/10 ,  G06T3/00 ,  G06N3/04 ,  G06T7/20

    Abstract: Systems, apparatuses and methods may provide for technology that generates, by a first neural network, an initial set of model weights based on input data and iteratively generates, by a second neural network, an updated set of model weights based on residual data associated with the initial set of model weights and the input data. Additionally, the technology may output a geometric model of the input data based on the updated set of model weights. In one example, the first neural network and the second neural network reduce the dependence of the geometric model on the number of data points in the input data.

Patent Agency Ranking