-
公开(公告)号：US11917180B2
公开(公告)日：2024-02-27
申请号：US18093562
申请日：2023-01-05
发明人： Je Won Kang , Sang Hyo Park , Seung Wook Park , Wha Pyeong Lim
IPC分类号： H04N19/44 , H04N19/105 , H04N19/132 , H04N19/159 , H04N19/176 , H04N19/70
CPC分类号： H04N19/44 , H04N19/105 , H04N19/132 , H04N19/159 , H04N19/176 , H04N19/70
摘要： A method and apparatus for intra-prediction coding of video data are provided. The apparatus includes a decoder that is configured to decode, from a bitstream, a syntax element indicating an intra-prediction type of a current block of the video data, and an intra-predictor that is configured to generate a prediction block for the current block by selectively performing matrix based intra-prediction or regular intra-prediction based on the intra-prediction type of the current block indicated by the syntax element.
-
62.发明公开公开(公告)号：US20240054686A1
公开(公告)日：2024-02-15
申请号：US18029022
申请日：2021-09-29
发明人： Je Won Kang , Chae Hwa Yoo , Seung Wook Park , Wha Pyeong Lim
CPC分类号： G06T9/002 , G06T3/4046 , G06V10/7715 , G06V10/82
摘要： A VCM coding apparatus and a VCM coding method, related to a deep learning-based feature map coding apparatus in a multitasking system for machine vision, are provided for performing default procedures of generating and compressing a common feature map related to multiple tasks implied by an original video. The VCM coding apparatus and the VCM coding method can further generate and compress a task-specific feature map whenever needed for higher performance than obtainable with the common feature map to ensure relatively acceptable performance for both machine vision and human vision.
-
公开(公告)号：US11849140B2
公开(公告)日：2023-12-19
申请号：US17868990
申请日：2022-07-20
发明人： Je Won Kang , Seung Wook Park , Wha Pyeong Lim
IPC分类号： H04N19/52 , H04N19/132 , H04N19/176 , H04N19/70
CPC分类号： H04N19/52 , H04N19/132 , H04N19/176 , H04N19/70
摘要： A video decoding apparatus is provided for decoding pictures using inter-prediction. The video decoding apparatus includes a predictor that generates affine prediction samples for respective subblocks in a target block in a current picture to be decoded by performing affine motion prediction on a subblock-by-subblock basis using control point motion vectors which respectively correspond to corners of the target block. The predictor also modifies sample values of the affine prediction samples by executing a first coding tool, the first coding tool compensating for motion according to sample positions in each of the subblocks using the control point motion vectors.
-
公开(公告)号：US20230353770A1
公开(公告)日：2023-11-02
申请号：US18021267
申请日：2021-08-24
发明人： Je Won Kang , Seung Wook Park , Young Bin Min
IPC分类号： H04N19/463 , H04N19/172 , H04N19/136 , H04N19/127 , H04N19/184 , H04N19/597
CPC分类号： H04N19/463 , H04N19/172 , H04N19/136 , H04N19/127 , H04N19/184 , H04N19/597
摘要： A frame packing method in an MPEG immersive video format is provided. A frame packing method in association with an immersive-video encoding and decoding method efficiently arranges, on a single screen, texture information and depth information of a basic view and an additional view to increase the coding efficiency.
-
公开(公告)号：US11800127B2
公开(公告)日：2023-10-24
申请号：US18093623
申请日：2023-01-05
发明人： Je Won Kang , Sang Hyo Park , Seung Wook Park , Wha Pyeong Lim
IPC分类号： H04N19/44 , H04N19/105 , H04N19/132 , H04N19/159 , H04N19/176 , H04N19/70
CPC分类号： H04N19/44 , H04N19/105 , H04N19/132 , H04N19/159 , H04N19/176 , H04N19/70
摘要： A method and apparatus for intra-prediction coding of video data are provided. The apparatus includes a decoder that is configured to decode, from a bitstream, a syntax element indicating an intra-prediction type of a current block of the video data, and an intra-predictor that is configured to generate a prediction block for the current block by selectively performing matrix based intra-prediction or regular intra-prediction based on the intra-prediction type of the current block indicated by the syntax element.
-
公开(公告)号：US11792418B2
公开(公告)日：2023-10-17
申请号：US18093665
申请日：2023-01-05
发明人： Je Won Kang , Sang Hyo Park , Seung Wook Park , Wha Pyeong Lim
IPC分类号： H04N9/44 , H04N19/105 , H04N19/132 , H04N19/159 , H04N19/176 , H04N19/70 , H04N19/44
CPC分类号： H04N19/44 , H04N19/105 , H04N19/132 , H04N19/159 , H04N19/176 , H04N19/70
摘要： A method and apparatus for intra-prediction coding of video data are provided. The apparatus includes a decoder that is configured to decode, from a bitstream, a syntax element indicating an intra-prediction type of a current block of the video data, and an intra-predictor that is configured to generate a prediction block for the current block by selectively performing matrix based intra-prediction or regular intra-prediction based on the intra-prediction type of the current block indicated by the syntax element.
-
公开(公告)号：US11785251B2
公开(公告)日：2023-10-10
申请号：US17874997
申请日：2022-07-27
发明人： Je Won Kang , Sang Hyo Park , Seung Wook Park , Wha Pyeong Lim
IPC分类号： H04N19/105 , H04N19/132 , H04N19/176 , H04N19/70 , H04N19/513 , H04N19/139 , H04N19/577
CPC分类号： H04N19/521 , H04N19/105 , H04N19/132 , H04N19/139 , H04N19/176 , H04N19/577 , H04N19/70
摘要： A coding tool is provided to improve the compression performance of inter prediction and is used at the encoder/decoder side to adjust the correction of a motion vector based on a high level syntax. In addition, a method is provided for simply performing an integer sample search step of searching for an integer offset and a fractional sample refinement step of searching for a sub-pixel offset in relation to motion vector refinement among coding tools.
-
公开(公告)号：US11778174B2
公开(公告)日：2023-10-03
申请号：US17520057
申请日：2021-11-05
发明人： Je Won Kang , Sang Hyo Park , Seung Wook Park , Wha Pyeong Lim
IPC分类号： H04N19/11 , H04N19/105 , H04N19/139 , H04N19/159 , H04N19/167 , H04N19/176 , H04N19/70
CPC分类号： H04N19/11 , H04N19/105 , H04N19/139 , H04N19/159 , H04N19/167 , H04N19/176 , H04N19/70
摘要： An apparatus for decoding video data includes a decoder configured to decode, from a bitstream, a syntax element indicating an intra-prediction type of a current block of the video data, and an intra-predictor configured to generate a prediction block for the current block by selectively performing matrix based intra-prediction (MIP) or regular intra-prediction based on the intra-prediction type of the current block indicated by the syntax element.
-
公开(公告)号：US11770533B2
公开(公告)日：2023-09-26
申请号：US17964386
申请日：2022-10-12
发明人： Je Won Kang , Sang Hyo Park , Seung Wook Park , Wha Pyeong Lim
IPC分类号： H04N19/127 , H04N19/103 , H04N19/13 , H04N19/132 , H04N19/136 , H04N19/184 , H04N19/186 , H04N19/187
CPC分类号： H04N19/127 , H04N19/103 , H04N19/13 , H04N19/132 , H04N19/136 , H04N19/184 , H04N19/186 , H04N19/187
摘要： A method and device for controlling coding tools are provided. The video decoding method includes decoding, from a high level of a bitstream, an enable flag indicating whether one or more coding tools are enabled. The coding tools includes a first coding tool that encodes sample values using luma component mapping based on a piecewise linear model. The method includes acquiring a value of an application flag depending on a value of the enable flag, by setting the application flag indicating whether to apply the coding tools to a predetermined value, or by decoding the application flag from a low level of the bitstream, the application flag including a first application flag indicating whether to apply the first coding tool. The coding tools are operated when the value of the application flag is a value indicating that the coding tools are applied.
-
公开(公告)号：US20230300347A1
公开(公告)日：2023-09-21
申请号：US18202772
申请日：2023-05-26
发明人： Je Won Kang , Seung Wook Park
IPC分类号： H04N19/176 , H04N19/44 , H04N19/136 , H04N19/192
CPC分类号： H04N19/176 , H04N19/44 , H04N19/136 , H04N19/192
摘要： A video codec uses a block-based deep learning model. The video codec, when processing video blocks by using a deep learning model, generates a super block by stacking or packing the respective ones of YUV video blocks and inputs the generated super block to the deep learning model. The video codec processes the inputs differently in the course of performing convolution within the deep learning model, according to the characteristics of the constituent YUV blocks of the super block
-
-
-
-
-
-
-
-
-
搜索结果
283 条记录 (耗时 0.043 秒)
