-
公开(公告)号：US20240214561A1
公开(公告)日：2024-06-27
申请号：US18600563
申请日：2024-03-08
Inventor： Xiaoyu XIU , Hong-Jheng JHU , Yi-Wen CHEN , Wei CHEN , Che-Wei KUO , Ning YAN , Xianglin WANG , Bing YU
IPC: H04N19/11 , H04N19/184 , H04N19/196 , H04N19/593
CPC classification number: H04N19/11 , H04N19/184 , H04N19/196 , H04N19/593
Abstract: Methods, apparatuses, and non-transitory computer-readable storage mediums are provided for video decoding. In one method, a decoder identifies a floating-point division operation to be performed to derive parameters in decoder-side intra mode derivation (DIMD) mode or in template-based intra mode derivation (TIMD) mode; and the decoder obtains the parameters in the DIMD mode or the TIMD mode by replacing the floating-point division operation with integer additions and multiplications based on a look-up-table (LUT).
-
公开(公告)号：US20240205438A1
公开(公告)日：2024-06-20
申请号：US18435446
申请日：2024-02-07
Inventor： Che-Wei KUO , Xiaoyu XIU , Wei CHEN , Xianglin WANG , Yi-Wen CHEN , Hong-Jheng JHU , Ning YAN , Bing YU
IPC: H04N19/44 , H04N19/105 , H04N19/132 , H04N19/186
CPC classification number: H04N19/44 , H04N19/105 , H04N19/132 , H04N19/186
Abstract: An electronic apparatus performs a method of decoding video data, including: receiving, from the video signal, a picture frame that includes a first component, and a second component; determining a classifier for a respective sample of the second component using a set of weighted sample values from a first set of samples of the first component associated with the respective sample of the second component, and a second set of samples of the second component associated with the respective sample of the second component, wherein the first set of samples and the second set of samples are collocated, neighbouring, and current samples relative to the respective sample of the second component; determining a sample offset for the respective sample of the second component according to the classifier; and modifying the respective sample of the second component based on the determined sample offset.
-
公开(公告)号：US20240205436A1
公开(公告)日：2024-06-20
申请号：US18426274
申请日：2024-01-29
Inventor： Wei CHEN , Xiaoyu XIU , Yi-Wen CHEN , Hong-Jheng JHU , Che-Wei KUO , Xianglin WANG , Bing YU
IPC: H04N19/436 , G06N3/0895 , H04N19/124 , H04N19/136 , H04N19/176 , H04N19/463
CPC classification number: H04N19/436 , G06N3/0895 , H04N19/124 , H04N19/136 , H04N19/463 , H04N19/176
Abstract: A method and an apparatus for hybrid training of neural networks for video coding are provided. The method includes: obtaining, in an offline training stage, an offline trained network by training a neural network offline; and refining, in an online training stage, a plurality of neural network layers with constraint on a plurality of parameters of the plurality of neural network layers, where the plurality of neural network layers may include at least one neural network layer in the offline trained network or in a simple neural network connected to the offline trained network.
-
公开(公告)号：US20240179314A1
公开(公告)日：2024-05-30
申请号：US18384828
申请日：2023-10-27
Inventor： Hong-Jheng JHU , Xiaoyu XIU , Yi-Wen CHEN , Wei CHEN , Che-Wei KUO , Xianglin WANG , Bing YU
IPC: H04N19/12 , H04N19/174 , H04N19/18 , H04N19/70
CPC classification number: H04N19/12 , H04N19/174 , H04N19/18 , H04N19/70
Abstract: Methods, apparatuses, and non-transitory computer-readable storage mediums are provided for video coding. The method includes: in response to determining that transform skip is disabled, disabling, by a decoder, a presence of a rice parameter for transform skip residual coding. The method may further include adopting a flag of transform skip, sps_transform_skip_enabled_flag, to condition a presence of sps_ts_residual_coding_rice_present_in_sh_flag.
-
公开(公告)号：US20240107070A1
公开(公告)日：2024-03-28
申请号：US18518954
申请日：2023-11-25
Inventor： Hong-Jheng JHU , Xiaoyu XIU , Yi-Wen CHEN , Wei CHEN , Che-Wei KUO , Ning YAN , Xianglin WANG , Bing YU
Abstract: Methods, apparatuses, and non-transitory computer-readable storage mediums are provided for video decoding. In one method, a decoder receives a Sequence Parameter Set (SPS) rice extension flag that indicates whether an extension of rice parameter derivation for binarization of abs_remainder and dec_abs_level is enabled. In a second method, the decoder may receive a Sequence Parameter Set (SPS) rice adaption enabled flag that indicates whether rice parameter derivation for binarization of abs_remainder and dec_abs_level is used.
-
公开(公告)号：US20240098250A1
公开(公告)日：2024-03-21
申请号：US18513492
申请日：2023-11-17
Inventor： Xiaoyu XIU , Che-Wei KUO , Wei CHEN , Hong-Jheng JHU , Ning YAN , Yi-Wen CHEN , Xianglin WANG , Bing YU
IPC: H04N19/105 , H04N19/119 , H04N19/176 , H04N19/46
CPC classification number: H04N19/105 , H04N19/119 , H04N19/176 , H04N19/46
Abstract: Methods and devices are provided for decoding a video block in GPM. The method includes: partitioning the video block into a first geometric partition and a second geometric partition; receiving a first template matching (TM) enable flag for the first geometric partition a second TM enable flag for the second geometric partition, the first TM enable flag indicating whether a uni-directional motion of the first geometric partition is refined by TM, and the second TM enable flag indicating whether a uni-directional motion of the second partition is refined by the TM; receiving a first merge GPM index for the first geometric partition and a second merge GPM index for the second geometric partition; constructing a uni-directional motion victor (MV) candidate list of the GPM; and generating a first uni-directional MV for the first geometric partition and a second uni-directional MV for the second geometric partition.
-
公开(公告)号：US20240064296A1
公开(公告)日：2024-02-22
申请号：US18385888
申请日：2023-10-31
Inventor： Wei CHEN , Xiaoyu XIU , Yi-Wen CHEN , Hong-Jheng JHU , Che-Wei KUO , Xianglin WANG , Bing YU
IPC: H04N19/117 , G06V10/82 , H04N19/124 , H04N19/59 , H04N19/80
CPC classification number: H04N19/117 , G06V10/82 , H04N19/124 , H04N19/59 , H04N19/80
Abstract: A method and an apparatus for image filtering in video coding using a neural network are provided. The method includes: loading, a plurality of quantization parameter (QP) map (QpMap) values at a plurality of QpMap channels into the neural network; obtaining a QP scaling factor by adjusting a plurality of input QP values related to an input frame; and adjusting, according to a QP scaling factor, the plurality of QpMap values for the neural network to learn and filter the input frame to the neural network.
-
公开(公告)号：US20230388532A1
公开(公告)日：2023-11-30
申请号：US18447233
申请日：2023-08-09
Inventor： Che-Wei KUO , Xiaoyu XIU , Wei CHEN , Xianglin WANG , Yi-Wen CHEN , Tsung-Chuan MA , Hong-Jheng JHU , Bing YU
IPC: H04N19/44 , H04N19/132 , H04N19/105 , H04N19/172 , H04N19/169 , H04N19/186 , H04N19/70
CPC classification number: H04N19/44 , H04N19/132 , H04N19/105 , H04N19/172 , H04N19/1883 , H04N19/186 , H04N19/70
Abstract: An electronic apparatus performs a method of video encoding. The method comprises: obtaining a video picture that includes a first component and a second component; determining a plurality of offsets associated with the second component; utilizing a sample value of the first component to obtain a class index associated with the second component; selecting an offset from the plurality of offsets for the second component according to the class index; and obtaining a sample value of the second component based on the selected offset, wherein utilizing the sample value of the first component to obtain the class index associated with the second component comprises: utilizing a first sample value of the first component to obtain a first parameter; utilizing a second sample value of the first component to obtain a second parameter; and obtaining the class index according to the first parameter and the second parameter.
-
公开(公告)号：US20230254501A1
公开(公告)日：2023-08-10
申请号：US18135112
申请日：2023-04-14
Inventor： Xiaoyu XIU , Che-Wei KUO , Wei CHEN , Yi-Wen CHEN , Hong-Jheng JHU , Xianglin WANG , Bing YU
IPC: H04N19/513 , H04N19/176
CPC classification number: H04N19/513 , H04N19/176
Abstract: Methods, apparatuses, and non-transitory computer-readable storage mediums are provided for encoding video. An encoder may obtain a first motion vector (MV) associated with a video block obtained from the video. The encoder may obtain a first prediction signal of the video block using the first MV. The encoder may identify a target MV by applying a gradient-based motion refinement algorithm in a recursive manner using the first prediction signal and the first MV. The encoder may obtain a second prediction signal of the video block based on the target MV.
-
公开(公告)号：US20250039457A1
公开(公告)日：2025-01-30
申请号：US18801713
申请日：2024-08-12
Inventor： Han GAO , Xiaoyu XIU , Yi-Wen CHEN , Wei CHEN , Hong-Jheng JHU , Ning YAN , Che-Wei KUO , Xianglin WANG , Bing YU
IPC: H04N19/66 , H04N19/119 , H04N19/174 , H04N19/70
Abstract: Methods for video decoding and encoding, apparatuses and non-transitory storage media are provided. In one decoding method, the decoder obtains a geometric partition mode (GPM) blending area index at a certain level associated with a picture, where the GPM blending area index indicates a blending area width from a set of blending area widths. The decoder obtains one or more weighting values that are used to blend prediction samples of a GPM mode based on the blending area width indicated by the GPM blending area index. Furthermore, the decoder obtains a GPM predictor based on the one or more weighting values.
