-
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.
-
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.
-
Patent Agency Ranking
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.
-
公开(公告)号：US20240267533A1
公开(公告)日：2024-08-08
申请号：US18566956
申请日：2022-06-02
IPC: H04N19/156 , H04N19/154 , H04N19/176 , H04N19/184
CPC classification number: H04N19/156 , H04N19/154 , H04N19/176 , H04N19/184
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 current video block of a video and a bitstream of the video, a cost based on at least two error metrics associated with two target blocks of the video, the cost indicting a degree of distortion between the two target blocks; refining coding data of the current video block based on the cost and the two target blocks; and performing the conversion based on the refined coding data. Compare with the conventional solution, the proposed method can advantageously improve the coding quality and the coding efficiency.
-
-
-
-
-
-
-
-
-
Search Results
574
records
(took 0.03 seconds)
