知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

16 records (took 0.014 seconds)

    Graphics processing unit with a texture return buffer and a texture queue
    4.
    发明授权
    Graphics processing unit with a texture return buffer and a texture queue 有权
    具有纹理返回缓冲区和纹理队列的图形处理单元

    公开(公告)号：US09165396B2

    公开(公告)日：2015-10-20

    申请号：US13778031

    申请日：2013-02-26

    Applicant: NVIDIA Corporation

    Inventor： David Tarjan

    IPC: G06F13/00 ,  G06F13/28 ,  G06F9/34 ,  G06K9/36 ,  G06K9/54 ,  G06F15/80 ,  G06T15/00 ,  G09G5/00 ,  G06F12/02 ,  G09G5/36 ,  G06T15/04

    CPC classification number: G06T15/04 ,  G06T2210/52

    Abstract: A processor and a system are provided for performing texturing operations. The processor includes a texture return buffer having a plurality of slots for storing texture values and one or more texture units coupled to the texture return buffer. Each of the slots of the texture return buffer are addressable by a thread. Each texture unit is configured to allocate a slot of the texture return buffer when the texture unit generates a texture value.

    Abstract translation: 提供处理器和系统用于执行纹理化操作。 处理器包括纹理返回缓冲器，其具有用于存储纹理值的多个时隙和耦合到纹理返回缓冲器的一个或多个纹理单元。 纹理返回缓冲区的每个槽可以由线程寻址。 每个纹理单元被配置为当纹理单元生成纹理值时分配纹理返回缓冲器的时隙。

    VIDEO PREDICTION USING SPATIALLY DISPLACED CONVOLUTION
    8.
    发明申请
    VIDEO PREDICTION USING SPATIALLY DISPLACED CONVOLUTION 审中-公开

    公开(公告)号：US20190297326A1

    公开(公告)日：2019-09-26

    申请号：US16360853

    申请日：2019-03-21

    Applicant: NVIDIA Corporation

    Inventor： Fitsum A. Reda ,  Guilin Liu ,  Kevin Shih ,  Robert Kirby ,  Jonathan Barker ,  David Tarjan ,  Andrew Tao ,  Bryan Catanzaro

    IPC: H04N19/139 ,  G06N3/08 ,  G06N20/10 ,  G06N3/04 ,  G06N20/20 ,  H04N19/587 ,  H04N19/132 ,  H04N19/172

    Abstract: A neural network architecture is disclosed for performing video frame prediction using a sequence of video frames and corresponding pairwise optical flows. The neural network processes the sequence of video frames and optical flows utilizing three-dimensional convolution operations, where time (or multiple video frames in the sequence of video frames) provides the third dimension in addition to the two-dimensional pixel space of the video frames. The neural network generates a set of parameters used to predict a next video frame in the sequence of video frames by sampling a previous video frame utilizing spatially-displaced convolution operations. In one embodiment, the set of parameters includes a displacement vector and at least one convolution kernel per pixel. Generating a pixel value in the next video frame includes applying the convolution kernel to a corresponding patch of pixels in the previous video frame based on the displacement vector.

Patent Agency Ranking