中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

40 records (took 0.009 seconds)

    VIDEO INTER/INTRA COMPRESSION USING MIXTURE OF EXPERTS
    2.
    发明申请
    VIDEO INTER/INTRA COMPRESSION USING MIXTURE OF EXPERTS 审中-公开

    公开(公告)号：WO2022235270A1

    公开(公告)日：2022-11-10

    申请号：PCT/US2021/031218

    申请日：2021-05-07

    Applicant: GOOGLE LLC

    Inventor： MINNEN, David Charles ,  HWANG, Sung Jin ,  KARPILOVSKY, Elliott Michael ,  MUKHERJEE, Debargha

    IPC: H04N19/119 ,  H04N19/147 ,  H04N19/176 ,  H04N19/189 ,  G06T9/00

    Abstract: Methods, systems, and apparatus, including computer programs, for compression and decompression of video data using an ensemble of machine learning models. Methods can include defining for each frame in a video, a plurality of blocks in the frame. Methods can further include processing the frames of video in sequential sets, wherein each sequential set is at least a current frame (220) of video and a prior frame (240) of video in the ordered sequence. Each respective prediction of a block in the frame of the video includes providing, as input to a prediction model a first and the second border (235,230) of a current block (225) of the current frame, a first and a second border (250, 255) for a respective current block (245) of the prior frame and the respective current block (245) of the prior frame.

    PORTABLE TERMINAL
    3.
    发明申请
    PORTABLE TERMINAL 审中-公开
    便携式终端

    公开(公告)号：WO2006080261A2

    公开(公告)日：2006-08-03

    申请号：PCT/JP2006300912

    申请日：2006-01-16

    Applicant: MATSUSHITA ELECTRIC IND CO LTD ,  INOUE AKIHIKO

    Inventor： INOUE AKIHIKO

    IPC: H04N19/00 ,  H03M7/30 ,  H04N7/14 ,  H04N19/117 ,  H04N19/12 ,  H04N19/127 ,  H04N19/156 ,  H04N19/162 ,  H04N19/164 ,  H04N19/189 ,  H04N19/423 ,  H04N19/70 ,  H04N19/80

    CPC classification number: H04N7/147 ,  H04N19/117 ,  H04N19/12 ,  H04N19/154 ,  H04N19/156 ,  H04N19/162 ,  H04N2007/145

    Abstract: A portable terminal including an input unit (1001), through which images are entered, an encoding unit (1002) operable to encode the input images, thereby providing encoded data, a transmitting unit (1003) operable to transmit the encoded data to a communication counterpart, a receiving unit (1006) operable to receive communication counterpart-related information from the communication counterpart, and a mode-determining unit operable to determine an encoding method. The mode-determining unit receives the information on each of the self-terminal and the communication counterpart, thereby providing the determined encoding method. As a result, even when each of the self-terminal and the communication counterpart retains a sufficient level of remaining battery power, the encoding method is properly changed to suppress unwanted power consumption, whereby communication between the self-terminal and the communication counterpart can be made for a longer period of time.

    Abstract translation: 一种便携式终端，包括输入图像的输入单元（1001），可编码输入图像的编码单元（1002），从而提供编码数据;发送单元（1003），用于将编码数据发送到通信 对方，可操作以从通信对方接收通信对方相关信息的接收单元（1006）以及可操作以确定编码方法的模式确定单元。 模式确定单元接收关于每个自身终端和通信对方的信息，从而提供所确定的编码方法。 结果，即使当自身终端和通信对方中的每一个保持足够的剩余电池电量时，也适当地改变编码方法以抑制不需要的功耗，从而可以使自终端与通信对方之间的通信 制造了更长的一段时间。

    VIDEO CODING USING ADAPTATION PARAMETER SETS
    4.
    发明申请
    VIDEO CODING USING ADAPTATION PARAMETER SETS 审中-公开

    公开(公告)号：WO2021197407A1

    公开(公告)日：2021-10-07

    申请号：PCT/CN2021/084870

    申请日：2021-04-01

    Applicant: BEIJING BYTEDANCE NETWORK TECHNOLOGY CO., LTD. ,  BYTEDANCE INC.

    Inventor： WANG, Ye-Kui ,  ZHU, Weijia ,  ZHANG, Li ,  DENG, Zhipin

    IPC: H04N19/189

    Abstract: Methods and apparatus for video processing are disclosed. The processing may include video encoding, video decoding or video transcoding. One example method includes performing a conversion between a video comprising one or more video layers and a bitstream of the video according to a rule, the rule specifies use of multiple adaptation parameter set (APS) network abstraction layer (NAL) units for the video, each APS NAL unit has a corresponding adaptation parameter type value, each APS NAL unit is associated with a corresponding video layer identifier, each APS NAL unit is a prefix unit or a suffix unit, and the rule specifies that, responsive to the multiple APS NAL units sharing a same adaptation parameter type value, adaptation parameter set identifier values of the multiple APS NAL units belong to a same identifier space.

    METHOD AND APPARATUS FOR VIDEO CODING
    5.
    发明申请
    METHOD AND APPARATUS FOR VIDEO CODING 审中-公开

    公开(公告)号：WO2021141714A1

    公开(公告)日：2021-07-15

    申请号：PCT/US2020/064055

    申请日：2020-12-09

    Applicant: TENCENT AMERICA LLC

    Inventor： LI, Ling ,  LI, Xiang ,  LIU, Shan

    IPC: G06K9/36 ,  H04N19/117 ,  H04N19/186 ,  H04N19/189 ,  H04N19/30 ,  H04N19/44 ,  H04N19/46 ,  H04N19/70 ,  H04N19/82

    Abstract: Aspects of the disclosure provide a method and an apparatus including processing circuitry for video decoding. The processing circuitry decodes, from a coded video bitstream, a first syntax element indicating whether a first component in the coded video bitstream is coded based on a second component in the coded video bitstream. The processing circuitry determines whether to decode one or more second syntax elements for a chroma related coding tool based on the first syntax element. The chroma related coding tool is a luma mapping with chroma scaling coding tool or a cross-component adaptive loop filter. The one or more second syntax elements are decoded when the first syntax element indicates that the first component is coded based on the second component. The one or more second syntax elements are not decoded when the first syntax element indicates that the first component is not coded based on the second component.

    LOW-COMPLEXITY METHOD FOR GENERATING SYNTHETIC REFERENCE FRAMES IN VIDEO CODING
    6.
    发明申请
    LOW-COMPLEXITY METHOD FOR GENERATING SYNTHETIC REFERENCE FRAMES IN VIDEO CODING 审中-公开
    在视频编码中生成合成参考帧的低复杂度方法

    公开(公告)号：WO2017066235A1

    公开(公告)日：2017-04-20

    申请号：PCT/US2016/056516

    申请日：2016-10-12

    Applicant: CISCO TECHNOLOGY, INC.

    Inventor： DAVIES, Thomas

    IPC: H04N19/189

    CPC classification number: H04N19/513 ,  H04N19/189 ,  H04N19/577

    Abstract: Presented herein are techniques for a low-complexity process of generating an artificial frame that can be used for prediction. At least a first reference frame and a second reference frame of a video signal are obtained. A synthetic reference frame is generated from the first reference frame and the second reference frame. Reference blocks from each of the first reference frame and the second reference frame are combined to derive an interpolated block of the synthetic reference frame.

    Abstract translation: 这里呈现的是用于产生可用于预测的仿真帧的低复杂度过程的技术。 获得视频信号的至少第一参考帧和第二参考帧。 从第一参考帧和第二参考帧产生合成参考帧。 来自第一参考帧和第二参考帧中的每一个的参考块被组合以导出合成参考帧的内插块。

    RELATIONSHIP MODELING OF ENCODE QUALITY AND ENCODE PARAMETERS BASED ON SOURCE ATTRIBUTES
    9.
    发明申请
    RELATIONSHIP MODELING OF ENCODE QUALITY AND ENCODE PARAMETERS BASED ON SOURCE ATTRIBUTES 审中-公开

    公开(公告)号：WO2022018696A1

    公开(公告)日：2022-01-27

    申请号：PCT/IB2021/056675

    申请日：2021-07-23

    Applicant: SSIMWAVE INC.

    Inventor： OLEKAS, Christopher Vytautas ,  OLIJNYK, Peter ,  WANG, Jiheng ,  ZENG, Kai

    IPC: H04N19/149 ,  H04N19/115 ,  H04N19/147 ,  H04N19/154 ,  H04N19/186 ,  H04N19/189

    Abstract: A source quality of a source video and a source content complexity of the source video are identified. Parameter constraints with respect to parameters of an operation are received. The source video quality, source content complexity, and parameter constraints are applied to a deep neural network (DNN) producing DNN outputs. In an example, the DNN outputs are combined using domain knowledge to provide the filter parameters, as predicted, to a filter chain, such that applying the filter chain to the input source video results in an output video achieving the full reference video quality score. In another example, the DNN outputs are combined using domain knowledge to provide the filter parameters, as predicted, to a filter chain, such that applying the filter chain to the input source video results in an output video achieving the full reference video quality score.

    METHOD AND SYSTEM OF VIDEO ENCODING OPTIMIZATION
    10.
    发明申请
    METHOD AND SYSTEM OF VIDEO ENCODING OPTIMIZATION 审中-公开
    视频编码优化的方法和系统

    公开(公告)号：WO2017130183A1

    公开(公告)日：2017-08-03

    申请号：PCT/IL2017/050002

    申请日：2017-01-01

    Applicant: BEAMR IMAGING LTD.

    Inventor： CARMEL, Sharon ,  GILL, Dror ,  SHOHAM, Tamar ,  JULIUS, Dan ,  HACMON, Liad ,  MIZRAHI, Lior ,  SHROT, Udi Yehuda ,  LEIBMAN, Amir ,  BIRAN, Alon ,  ENAV, Eyal

    IPC: H04N19/189 ,  H04N19/152

    CPC classification number: H04N19/189 ,  H04N19/115 ,  H04N19/154 ,  H04N19/176 ,  H04N19/177 ,  H04N19/179 ,  H04N19/196 ,  H04N19/61 ,  H04N19/82 ,  H04N19/87

    Abstract: A computerized method and system of segment-based video encoding optimization, the method comprising obtaining a set of input segments constituting an input video stream; selecting one or more input segments in accordance with a selection criterion to be one or more representative segments; determining an encoding instruction and obtaining one or more encoded representative segments encoded from the representative segments in accordance with the encoding instruction and using a quality-driven video encoding scheme; determining, based on the encoded representative segments, an encoding configuration, and obtaining one or more encoded input segments encoded from at least a sub-set of the input segments using the encoding configuration; determining an evaluation instruction used to evaluate quality for each encoded input segment; and generating an output video stream, by selecting, for each input segment, a corresponding output segment from a group comprising at least one of the following candidate segments: the input segment, an encoded representative segment, and an encoded input segment.

    Abstract translation: 一种基于片段的视频编码优化的计算机化的方法和系统，所述方法包括：获得构成输入视频流的一组输入段; 根据选择标准选择一个或多个输入段作为一个或多个代表性段; 确定编码指令并根据编码指令并使用质量驱动的视频编码方案获得从代表段编码的一个或多个编码的代表性段; 基于编码的代表性段确定编码配置;以及使用编码配置获得从至少一个输入段的子集编码的一个或多个编码的输入段; 确定用于评估每个编码输入段的质量的评估指令; 以及通过为每个输入段选择来自包括以下候选段中的至少一个的组的相应输出段：输入段，编码的代表段和编码的输入段，来生成输出视频流。

Patent Agency Ranking