利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

459 条记录 (耗时 0.038 秒)

    Scalable per-title encoding
    1.
    发明授权
    Scalable per-title encoding 有权

    公开(公告)号：US12108055B2

    公开(公告)日：2024-10-01

    申请号：US17965124

    申请日：2022-10-13

    申请人： BITMOVIN, INC.

    发明人： Hadi Amirpour ,  Christian Timmerer

    IPC分类号： H04N19/179 ,  H04N19/29

    CPC分类号： H04N19/179 ,  H04N19/29

    摘要： A scalable per-title encoding technique may include detecting scene cuts in an input video received by an encoding network or system, generating segments of the input video, performing per-title encoding of a segment of the input video, training a deep neural network (DNN) for each representation of the segment, thereby generating a trained DNN, compressing the trained DNN, thereby generating a compressed trained DNN, and generating an enhanced bitrate ladder including metadata comprising the compressed trained DNN. In some embodiments, the method also may include generating a base layer bitrate ladder for CPU devices, and providing the enhanced bitrate ladder for GPU-available devices.

    Non-entropy encoded representation format
    8.
    发明授权
    Non-entropy encoded representation format 有权
    非熵编码的表示格式

    公开(公告)号：US09467700B2

    公开(公告)日：2016-10-11

    申请号：US14247066

    申请日：2014-04-07

    申请人： QUALCOMM Incorporated

    发明人： Ye-Kui Wang ,  Ying Chen ,  Adarsh Krishnan Ramasubramonian

    IPC分类号： H04N19/91 ,  H04N19/597 ,  H04N19/70 ,  H04N19/46 ,  H04N19/513 ,  H04N19/30 ,  H04N19/44 ,  H04N19/29

    CPC分类号： H04N19/91 ,  H04N19/29 ,  H04N19/30 ,  H04N19/44 ,  H04N19/46 ,  H04N19/513 ,  H04N19/597 ,  H04N19/70

    摘要： Systems, methods, and devices for coding multilayer video data are disclosed that may include encoding, decoding, transmitting, or receiving multilayer video data. The systems, methods, and devices may receive or transmit a non-entropy coded representation format within a video parameter set (VPS). The systems, methods, and devices may code (encode or decode) video data based on the non-entropy coded representation format within the VPS, wherein the representation format includes one or more of chroma format, whether different color planes are separately coded, picture width, picture height, luma bit depth, and chroma bit depth.

    摘要翻译： 公开了用于编码多层视频数据的系统，方法和设备，其可以包括编码，解码，发送或接收多层视频数据。 系统，方法和设备可以在视频参数集（VPS）内接收或发送非熵编码的表示格式。 系统，方法和设备可以基于VPS内的非熵编码的表示格式对视频数据进行编码（编码或解码），其中表示格式包括色度格式中的一种或多种，​​不同的颜色平面是否被分别编码，图像 宽度，图片高度，亮度位深度和色度位深度。

    SYSTEM AND METHOD FOR VIDEO CONTEXT-BASED COMPOSITION AND COMPRESSION FROM NORMALIZED SPATIAL RESOLUTION OBJECTS
    9.
    发明申请
    SYSTEM AND METHOD FOR VIDEO CONTEXT-BASED COMPOSITION AND COMPRESSION FROM NORMALIZED SPATIAL RESOLUTION OBJECTS 有权
    基于视觉语境的组合系统与方法与正规化空间分辨率对象的压缩

    公开(公告)号：US20160275354A1

    公开(公告)日：2016-09-22

    申请号：US14663637

    申请日：2015-03-20

    申请人： SAMSUNG ELETRÔNICA DA AMAZÔNIA LTDA.

    发明人： FERNANDA A. ANDALÓ ,  OTÁVIO A.B. PENATTI ,  VANESSA TESTONI ,  FERNANDO KOCH

    IPC分类号： G06K9/00 ,  G06K9/62 ,  G06K9/46

    CPC分类号： H04N19/59 ,  G06K9/00228 ,  G06K9/4628 ,  H04N19/124 ,  H04N19/154 ,  H04N19/17 ,  H04N19/29

    摘要： The present invention relates to a system and method for efficiently generating images and videos as an array of objects of interest (e.g., faces and hands, plates, etc.) in a desired resolution to perform vision tasks, such as face recognition, facial expression analysis, detection of hand gestures, among others. The composition of such images and videos takes into account the similarity of objects in the same category to encode them more effectively, providing savings in terms of time transmission and storage. Transmission time is less advantage to such a system in terms of efficiency, while less low cost storage means for storing data.

    摘要翻译： 本发明涉及一种用于以期望的分辨率有效地生成图像和视频作为感兴趣对象的阵列（例如，面部和手，板等）以执行视觉任务的系统和方法，诸如面部识别，面部表情 分析，手势检测等。 这样的图像和视频的组合考虑了相同类别中的对象的相似性，以更有效地编码它们，从而在时间传输和存储方面节省了费用。 传输时间对于这种系统在效率方面较少的优点，而较少的低成本存储装置用于存储数据。

    Partial frame utilization in video codecs
    10.
    发明授权
    Partial frame utilization in video codecs 有权
    视频编解码器的部分帧利用率

    公开(公告)号：US09414086B2

    公开(公告)日：2016-08-09

    申请号：US13487498

    申请日：2012-06-04

    申请人： Feng Yi ,  David R. Conrad ,  Chris Y. Chung

    发明人： Feng Yi ,  David R. Conrad ,  Chris Y. Chung

    IPC分类号： H04N7/32 ,  H04N19/55 ,  H04N19/176 ,  H04N19/46 ,  H04N19/61 ,  H04N19/103 ,  H04N19/117 ,  H04N19/124 ,  H04N19/156 ,  H04N19/164 ,  H04N19/17 ,  H04N19/167 ,  H04N19/29 ,  H04N19/85

    CPC分类号： H04N19/55 ,  H04N19/103 ,  H04N19/117 ,  H04N19/124 ,  H04N19/156 ,  H04N19/164 ,  H04N19/167 ,  H04N19/17 ,  H04N19/176 ,  H04N19/29 ,  H04N19/46 ,  H04N19/61 ,  H04N19/85

    摘要： Embodiments of the present invention provide techniques for efficiently coding/decoding video data during circumstances where a decoder only requires or utilizes a portion of coded frames. A coder may exchange signaling with a decoder to identify unused areas of frames and prediction modes for the unused areas. An input frame may be parsed into a used area and an unused area based on the exchanged signaling. If motion vectors of the input frame are not limited to the used areas of the reference frames, the unused area of the input frame may be coded using low complexity. If the motion vectors of the input frame are limited to the used areas of the reference frames, the pixel blocks in the unused area of the input frame may not be coded, or the unused area of the input frame may be filled with gray, white, or black pixel blocks.

    摘要翻译： 本发明的实施例提供了在解码器仅需要或利用编码帧的一部分的情况下有效地对视频数据进行编码/解码的技术。 编码器可以与解码器交换信令以识别未使用区域的帧的未使用区域和预测模式。 可以基于所交换的信令将输入帧解析为使用区域和未使用区域。 如果输入帧的运动矢量不限于参考帧的使用区域，则可以使用低复杂度对输入帧的未使用区域进行编码。 如果输入帧的运动矢量被限制到参考帧的使用区域，则输入帧的未使用区域中的像素块可能不被编码，或者输入帧的未使用区域可以用灰色，白色 ，或黑色像素块。