-
公开(公告)号：US20250168346A1
公开(公告)日：2025-05-22
申请号：US19031001
申请日：2025-01-17
Applicant: Douyin Vision Co., Ltd. , Bytedance Inc.
IPC: H04N19/13 , H04N19/159 , H04N19/176
Abstract: Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: determining, for a conversion between a current video block of a video and a bitstream of the video, at least one context model associated with the current video block based on initiation information of the at least one context model, the initiation information of the at least one context model being included in the bitstream; and performing the conversion based on the at least one context model.
-
公开(公告)号：US20250142093A1
公开(公告)日：2025-05-01
申请号：US19009881
申请日：2025-01-03
IPC: H04N19/176 , G06V10/74 , H04N19/139 , H04N19/52
Abstract: Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: determining, for a conversion between a current video block of a video and a bitstream of the video, a plurality of co-located frames of the current video block, the current video block being in a current frame co-located with the plurality of co-located frame; and performing the conversion based on the plurality of co-located frames.
-
公开(公告)号：US20250142081A1
公开(公告)日：2025-05-01
申请号：US19009847
申请日：2025-01-03
Applicant: Bytedance Inc.
Inventor： Bharath VISHWANATH , Kai ZHANG , Li ZHANG
IPC: H04N19/139 , H04N19/103 , H04N19/176 , H04N19/184 , H04N19/70
Abstract: Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: obtaining, for a conversion between a current video block of a video and a bitstream of the video, values for a set of adjusting parameters associated with values for a set of model parameters of a local illumination compensation (LIC) model for coding the current video block; updating the values for the set of model parameters based on the values for the set of adjusting parameters; and performing the conversion based on the updated values for the set of model parameters.
-
公开(公告)号：US20250063192A1
公开(公告)日：2025-02-20
申请号：US18913903
申请日：2024-10-11
Inventor： Na ZHANG , Jizheng XU , Kai ZHANG , Mehdi SALEHIFAR , Li ZHANG
IPC: H04N19/513 , H04N19/105 , H04N19/139 , H04N19/196 , H04N19/58
Abstract: Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: determining, for a conversion between a current video block of a video and a bitstream of the video, that a first prediction mode is applied to the current block, reordering, in the first prediction mode, at least a first set of block vector difference (BVD) candidates of multiple BVD candidates corresponding to a first base candidate according to at least one criterion; deriving, based on the reordered BVD candidates, a block vector for the current video block; and performing the conversion based on the motion information.
-
公开(公告)号：US20250056014A1
公开(公告)日：2025-02-13
申请号：US18927730
申请日：2024-10-25
Inventor： Zhipin DENG , Kai ZHANG , Li ZHANG
IPC: H04N19/167 , H04N19/119 , H04N19/132 , H04N19/176 , H04N19/567
Abstract: Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: obtaining, for a conversion between a current video block of a video and a bitstream of the video, a value for a metric of a blending region in a direction, the blending region being comprised in a target region associated with the current video block, the value being determined from a plurality of predetermined values for the metric, values for samples of the blending region being determined based on values for samples of a first part of the target region and values for samples of a second part of the target region; and performing the conversion based on the value for the metric.
-
Patent Agency Ranking
公开(公告)号：US20240430430A1
公开(公告)日：2024-12-26
申请号：US18823515
申请日：2024-09-03
Inventor： Semih ESENLIK , Zhaobin ZHANG , Yaojun WU , Kai ZHANG , Yue LI , Li ZHANG
IPC: H04N19/132 , H04N19/124
Abstract: Embodiments of the present disclosure provide a solution for visual data processing. A method for visual data processing is proposed. The method comprises: obtaining, for a conversion between visual data and a bitstream of the visual data, statistical information associated with a first representation of the visual data, the first representation being generated based on applying a first neural network to the visual data; determining at least one sample from a second representation of the visual data based on the statistical information, a value of the at least one sample being absent from the bitstream, the second representation being obtained by quantizing the first representation; and performing the conversion based on the determining.
-
公开(公告)号：US20240380904A1
公开(公告)日：2024-11-14
申请号：US18778813
申请日：2024-07-19
Inventor： Semih ESENLIK , Yaojun WU , Zhaobin ZHANG , Yue LI , Kai ZHANG , Li ZHANG
IPC: H04N19/189 , H04N19/119 , H04N19/124 , H04N19/132 , H04N19/436
Abstract: Embodiments of the present disclosure provide a solution for data processing. A method for data processing is proposed. The method comprises: processing, during a conversion between data and a bitstream of the data, a first set of samples of a reconstructed latent representation of the data and a second set of samples of the reconstructed latent representation by using a model, the first set of samples being associated with a first sample of the reconstructed latent representation and the second set of samples being associated with a second sample of the reconstructed latent representation; and performing the conversion based on a result of the processing.
-
公开(公告)号：US20240323353A1
公开(公告)日：2024-09-26
申请号：US18732479
申请日：2024-06-03
IPC: H04N19/105 , H04N19/176
CPC classification number: H04N19/105 , H04N19/176
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 target video block of a video and a bitstream of the video, a target maximum number from a first maximum number of motion candidates of a candidate type associated with a motion vector (MV) candidate list and a second maximum number of motion candidates of the candidate type associated with a block vector (BV) candidate list; determining a candidate list including motion candidates of the candidate type for the target video block based on the target maximum number; and performing the conversion based on the candidate list.
-
公开(公告)号：US20240276004A1
公开(公告)日：2024-08-15
申请号：US18568108
申请日：2022-06-13
Inventor： Zhipin DENG , Kai ZHANG , Li ZHANG
IPC: H04N19/50 , H04N19/105 , H04N19/176
CPC classification number: H04N19/50 , H04N19/105 , H04N19/176
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 target block of a video and a bitstream of the target block, whether to apply a first mode to generate a hypothesis of the target block, the target block being a multiple hypothesis prediction block coded with a second mode; and performing the conversion based on the determining. Compared with the conventional solution, the proposed method can advantageously improve the coding efficiency and performance.
-
公开(公告)号：US20240275944A1
公开(公告)日：2024-08-15
申请号：US18569561
申请日：2022-06-22
Inventor： Zhipin DENG , Li ZHANG , Kai ZHANG
IPC: H04N19/105 , H04N19/139 , H04N19/176 , H04N19/513 , H04N19/70
CPC classification number: H04N19/105 , H04N19/139 , H04N19/176 , H04N19/513 , H04N19/70
Abstract: Embodiments of the present disclosure provide a method for video processing. The method comprises: determining, during a conversion between a current video block of a video and a bitstream of the video, whether to insert a target motion candidate for the current video block into a prediction list for the current video block based on a comparison between the target motion candidate and at least one existing motion candidate in the prediction list; and performing the conversion based on the determination. The proposed method can advantageously fill the prediction list more efficiently.
-
-
-
-
-
-
-
-
-
Search Results
574
records
(took 0.022 seconds)
