-
公开(公告)号：WO2023091290A1
公开(公告)日：2023-05-25
申请号：PCT/US2022/048415
申请日：2022-10-31
Applicant: TENCENT AMERICA LLC , PERINGASSERY KRISHNAN, Madhu , ZHAO, Xin
Inventor： ZHAO, Liang , LIU, Shan
IPC: H04N19/176 , H04N19/186 , H04N19/00 , H04N19/46 , H04N19/70
Abstract: This disclosure relates to adaptive loop filtering (ALE) for cross-component sample offset (CCSO), local sample offset (LSO), and generalized sample offset (GSO). ALE uses reconstructed samples of a first color component as input (e.g., Y or Cb or Cr). At least one of the GSO, LSO, or CCSO is determined to be enabled for a frame based on a syntax value in a coded video stream. The coded video stream is decoded by applying the at least one of the GSO, the LSO, or the CCSO at a block level.
-
公开(公告)号：WO2023088562A1
公开(公告)日：2023-05-25
申请号：PCT/EP2021/082306
申请日：2021-11-19
Applicant: TELEFONAKTIEBOLAGET LM ERICSSON (PUBL)
Inventor： LI, Yun
Abstract: A computer-implemented method of training an autoencoder for data compression is provided. The method comprises inputting training data into a neural network to generate a plurality of first latent variables, using a probability estimator to obtain probability mass functions for the plurality of latent variables, and determining a rate measure based on the probability mass functions and a plurality of coded latent variables. The plurality of coded latent variables is based on one-hot encoding of plurality of quantized latent variables obtained by quantizing the plurality of latent variables. A gradient of the rate measure is determined based on the probability mass functions and a plurality of approximately coded latent variables obtained by applying a differentiable function to the plurality of latent variables to approximate one-hot encoding. One or more parameters of the autoencoder is updated based on the rate measure and the gradient of the rate measure.
-
公开(公告)号：WO2023086956A1
公开(公告)日：2023-05-19
申请号：PCT/US2022/079744
申请日：2022-11-11
Applicant: INNOPEAK TECHNOLOGY, INC.
Inventor： YU, Yue , YU, Haoping
Abstract: In some embodiments, a video decoder decodes a video from a bitstream. The video decoder accesses a binary string representing a partition of the video and processes each coding tree unit (CTU) in the partition to generate decoded values in the CTU. The process includes initializing the context variables for context-adaptive binary arithmetic coding (CABAC), the Rice parameter variables, and palette predictor variables only when the CTU is the first CTU in a tile, or the CTU is the first CTU in a tile, or parallel coding is enabled and the CTU is the first CTU in a CTU row of a tile. No other initialization is performed for these variables. The video decoder decodes the CTU based on the initialized context variables, Rice parameter variables, and palette predictor variables.
-
公开(公告)号：WO2023044917A1
公开(公告)日：2023-03-30
申请号：PCT/CN2021/121045
申请日：2021-09-27
Applicant: OPPO广东移动通信有限公司
Inventor： 王凡
IPC: H04N19/00
Abstract: 本申请实施例提供了一种帧内预测的方法、编码器、解码器和编解码系统。在该方法中，在确定至少两个预测模式在当前块中的至少两个单元上的权重之后，可以进一步根据该至少两个单元的权重，确定某一方向(例如垂直方向或水平方向)上权重的变化率，根据该变化率，进而可以通过平滑过渡的方式确定该当前块上的其他单元上的权重，以确定当前块的帧内预测值。由于本申请实施例能够确定至少两个预测模式分别在当前块的不同单元上的权重，从而能够实现对当前块的不同的单元设置不同的权重，从而有助于更准确的确定当前块的帧内预测值，进而提高压缩效率。本申请实施例的方案能够适用于对纹理复杂的场景，例如有些扭曲的线条、表面不均匀的场景等。
-
公开(公告)号：WO2023044900A1
公开(公告)日：2023-03-30
申请号：PCT/CN2021/120913
申请日：2021-09-27
Applicant: OPPO广东移动通信有限公司
IPC: H04N19/00
Abstract: 本申请实施例公开了一种编解码方法、码流、编码器、解码器以及存储介质，该方法包括：解析码流，确定当前块的第一模式使用标识信息；若第一模式使用标识信息指示当前块使用第一帧内预测模式，则根据第一帧内预测模式对当前块进行预测，确定当前块的预测块；若第一模式使用标识信息指示当前块不使用第一帧内预测模式，则解析码流，确定当前块的第二模式使用标识信息；并根据第二模式使用标识信息确定当前块的目标预测模式，以及根据目标预测模式对当前块进行预测，确定当前块的预测块。这样，不仅能够提高压缩效率，同时还能够降低软硬件的能耗和开销，进而提升了编解码性能。
-
Patent Agency Ranking
公开(公告)号：WO2023030504A1
公开(公告)日：2023-03-09
申请号：PCT/CN2022/116861
申请日：2022-09-02
Inventor： DENG, Zhipin , ZHANG, Kai , ZHANG, Li
IPC: H04N19/00
Abstract: Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: determining, during a conversion between a video unit of a video and a bitstream of the video unit, multiple hypothesis information of the video unit, the video unit being a multiple hypothesis coded video unit; inserting the multiple hypothesis information into a history-based motion candidate table; and performing the conversion based on the history-based motion candidate table.
-
公开(公告)号：WO2023028555A1
公开(公告)日：2023-03-02
申请号：PCT/US2022/075453
申请日：2022-08-25
Applicant: INNOPEAK TECHNOLOGY, INC.
Inventor： YU, Yue , YU, Haoping
IPC: H04N19/122 , H04N19/124 , H04N19/61 , H04N19/96 , H04N19/00
Abstract: In some embodiments, a video decoder decodes a video from a bitstream of the video using a history-based rice parameter derivation. The video decoder accesses a binary string representing a partition of the video and processes each coding tree unit (CTU) in the partition to generate decoded coefficient values in the CTU. The process includes updating a replacement variable for a transform unit (TU) in the CTU for calculating rice parameters independently of the previous TU or CTU. The process further includes calculating the rice parameters for TU in the CTU based on the value of the replacement variable and decoding the binary string corresponding to the TU into coefficient values based on the calculated rice parameters. Pixel values of the TU can be determined from the decoded coefficient values for output.
-
公开(公告)号：WO2023003597A1
公开(公告)日：2023-01-26
申请号：PCT/US2022/014289
申请日：2022-01-28
Applicant: TENCENT AMERICA LLC
Inventor： ZHAO, Xin , PERINGASSERY KRISHNAN, Madhu , LIU, Shan
Abstract: Methods, apparatus, and computer readable storage medium for encoding/decoding video data in a decoder. The method includes receiving a first End of Block (BOB) flag associated with a first color component of a data block from the video data; deriving a context for entropy encoding the first BOB flag based on a second BOB flag associated with a second color component of the data block of the video data; and performing entropy decoding of the first BOB flag based on the derived context.
-
公开(公告)号：WO2023001042A1
公开(公告)日：2023-01-26
申请号：PCT/CN2022/105480
申请日：2022-07-13
Inventor： LIN, Chaoyi , LI, Yue , ZHANG, Kai , ZHANG, Li
IPC: H04N19/00
Abstract: A video processing method, comprising determining information included in a bitstream that indicates whether down-sampling is performed on a video unit, and performing a conversion between the video unit and the bitstream based on the bitstream.
-
公开(公告)号：WO2023285731A1
公开(公告)日：2023-01-19
申请号：PCT/FI2022/050439
申请日：2022-06-21
Applicant: AIFORIA TECHNOLOGIES OYJ
Inventor： REUNANEN, Juha
Abstract: A method of facilitating processing of pathology images involves receiving pathology image data representing a pathology image having a plurality of image regions, wherein the pathology image data includes, for each of the plurality of image regions, a respective plurality of representations of the image region including a first representation and a second representation, the second representation having a smaller data size than the first representation. The method involves, for each of the plurality of image regions: determining, based at least in part on the first representation of the image region, a first set of image properties, determining whether the first set of image properties meets first image property criteria, and, if the first set of image properties meets the first image property criteria, producing signals for causing the second representation to be used in place of the first representation. Other methods, systems, and computer-readable media are disclosed.
-
-
-
-
-
-
-
-
-
Search Results
670
records
(took 0.034 seconds)
