-
公开(公告)号:US12137257B2
公开(公告)日:2024-11-05
申请号:US17389179
申请日:2021-07-29
Inventor: Kai Zhang , Li Zhang , Hongbin Liu , Jizheng Xu , Yue Wang
IPC: H04N19/96 , H04N19/119 , H04N19/12 , H04N19/122 , H04N19/13 , H04N19/132 , H04N19/136 , H04N19/157 , H04N19/172 , H04N19/176 , H04N19/184 , H04N19/186 , H04N19/46 , H04N19/70
Abstract: A method for processing a video includes determining a valid splitting type for a current video block; determining whether or how to signal a splitting type to be used for the current video block based on the determination of the valid splitting type; and performing a conversion between the current video block and a bitstream representation of the current video block in accordance with the determining results.
-
公开(公告)号:US12137252B2
公开(公告)日:2024-11-05
申请号:US18450647
申请日:2023-08-16
Inventor: Zhipin Deng , Li Zhang , Ye-Kui Wang , Kai Zhang , Jizheng Xu
IPC: H04N19/46 , H04N19/159 , H04N19/172 , H04N19/174 , H04N19/70
Abstract: Systems, methods, and apparatus for video processing are described. The video processing may include video encoding, video decoding or video transcoding. One example method of video processing includes performing a conversion between a video including one or more video regions and a bitstream of the video according to a format rule. The format rule specifies that a variable X indicates whether B slice is allowed or used in a video region. The format rule further specifies that the variable X is based on values of a reference picture list information present flag and/or a field indicating a number of entries in a reference picture list syntax structure.
-
公开(公告)号:US12136188B2
公开(公告)日:2024-11-05
申请号:US17453968
申请日:2021-11-08
Inventor: Meng Wang , Jizheng Xu , Li Zhang , Shiqi Wang
IPC: G06T3/4076 , G06T3/4046
Abstract: Embodiments of the present disclosure provide a solution for image/video super resolution. A method for image processing is proposed. The method comprises: receiving a first image with a first resolution and at least one reference image associated with the first image, the first image and the at least one reference image being associated with a same video; determining a difference between the first image and the at least one reference image; and generating a second image with a second resolution based on the difference, the first image and the at least one reference image, the second resolution being higher than the first resolution.
-
公开(公告)号:US20240364981A1
公开(公告)日:2024-10-31
申请号:US18770528
申请日:2024-07-11
Applicant: Bytedance Inc.
Inventor: Ye-Kui WANG
IPC: H04N21/854 , H04N21/845
CPC classification number: H04N21/85406 , H04N21/845
Abstract: Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: performing a conversion between a bitstream of a video and a media file of the video, wherein the media file comprises a group of labels comprising a first label, a first indication in a first data structure for the first label is coded with a single bit, and the first indication indicates whether the first label contains a summary label for the group of labels.
-
公开(公告)号:US12132884B2
公开(公告)日:2024-10-29
申请号:US17585704
申请日:2022-01-27
Inventor: Weijia Zhu , Li Zhang , Jizheng Xu , Kai Zhang , Hongbin Liu , Yue Wang
IPC: H04N19/105 , H04N19/132 , H04N19/159 , H04N19/176 , H04N19/186 , H04N19/70
CPC classification number: H04N19/105 , H04N19/132 , H04N19/159 , H04N19/176 , H04N19/186
Abstract: Devices, systems and methods for video processing are described. An example method for video processing includes determining, for a conversion between a current block of a video and a bitstream representation of the video, a number of intra-coded neighboring blocks of the current block for a combined inter and intra prediction mode according to a rule that specifies a manner of treating a block coded using a palette coding mode in counting the number of intra-coded neighboring blocks for the combined inter and intra prediction mode. The method also includes performing the conversion based on the determining.
-
公开(公告)号:US20240357174A1
公开(公告)日:2024-10-24
申请号:US18763998
申请日:2024-07-03
Inventor: Yingzhan Xu , Wenyi Wang , Kai Zhang , Li Zhang
IPC: H04N19/597 , H04N19/159 , H04N19/513
CPC classification number: H04N19/597 , H04N19/159 , H04N19/513
Abstract: Embodiments of the present disclosure provide a solution for point cloud coding. A method for point cloud coding is proposed. The method comprises: determining, based on a target motion information between a current frame of a point cloud sequence and a reference frame of the current frame during a conversion between the current frame and a bitstream of the point cloud sequence, whether an attribute inter prediction is performed on the current frame based on the reference frame, the target motion information being used for performing a motion compensation on the reference frame; and performing the conversion based on the determination.
-
公开(公告)号:US20240357157A1
公开(公告)日:2024-10-24
申请号:US18763028
申请日:2024-07-03
Inventor: Hongbin Liu , Li Zhang , Kai Zhang , Jizheng Xu , Yue Wang
IPC: H04N19/52 , H04N19/132 , H04N19/137 , H04N19/139 , H04N19/159 , H04N19/176 , H04N19/184 , H04N19/186 , H04N19/46 , H04N19/513 , H04N19/577
CPC classification number: H04N19/52 , H04N19/132 , H04N19/137 , H04N19/139 , H04N19/159 , H04N19/176 , H04N19/184 , H04N19/186 , H04N19/46 , H04N19/513 , H04N19/577
Abstract: One example method of video processing includes implementing, by a processor, a decoder-side motion vector derivation (DMVD) scheme for motion vector refinement during a conversion between a current video block and a bitstream representation of the current video block by deriving parameters based on a deriving rule. The conversion may include compressing the current video block into the bitstream representation or uncompressing the bitstream representation into pixel values of the current video block.
-
公开(公告)号:US20240348893A1
公开(公告)日:2024-10-17
申请号:US18623742
申请日:2024-04-01
Applicant: Bytedance Inc.
Inventor: Ye-Kui WANG
IPC: H04N21/845 , H04N21/84
CPC classification number: H04N21/845 , H04N21/84
Abstract: Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: receiving, at a first device, a metadata file from a second device; and determining a descriptor in a data set in the metadata file, a presence of the descriptor indicating that a representation in the data set is a main stream representation (MSR).
-
公开(公告)号:US20240348834A1
公开(公告)日:2024-10-17
申请号:US18749462
申请日:2024-06-20
Applicant: Bytedance Inc.
Inventor: Ye-Kui WANG
IPC: H04N19/70 , H04N19/172 , H04N19/174
CPC classification number: H04N19/70 , H04N19/172 , H04N19/174
Abstract: Embodiments of the present disclosure provide a solution for point cloud coding. A method for point cloud coding is proposed. The method comprises: performing a conversion between a point cloud sequence and a bitstream of the point cloud sequence based on a tile inventory, the tile inventory being valid starting from a first coded point cloud frame in the bitstream, the first coded point cloud frame immediately following a data unit for the tile inventory in a bitstream order, or the first coded point cloud frame following the data unit in the bitstream order and having a frame counter partially indicated in the data unit. Thereby, the proposed method can advantageously better support the application of the tile inventory.
-
公开(公告)号:US20240348772A1
公开(公告)日:2024-10-17
申请号:US18674691
申请日:2024-05-24
Inventor: Wenyi WANG , Yingzhan Xu , Kai Zhang , Li Zhang
IPC: H04N19/105 , H04N19/139 , H04N19/172 , H04N19/597
CPC classification number: H04N19/105 , H04N19/139 , H04N19/172 , H04N19/597
Abstract: Embodiments of the present disclosure provide a solution for point cloud coding. A method for point cloud coding is proposed. The method comprises: determining, during a conversion between a current frame of a point cloud sequence and a bitstream of the point cloud sequence, at least one neighbor list comprising a set of neighbor points of a current point of the current frame based on geometry information of the set of neighbor points; and performing the conversion based on the at least one neighbor list. Compared with the conventional solution, the proposed method can advantageously improve the point cloud coding efficiency and coding quality.
-
-
-
-
-
-
-
-
-