-
公开(公告)号:US20240333950A1
公开(公告)日:2024-10-03
申请号:US18616793
申请日:2024-03-26
申请人: TENCENT AMERICA LLC
发明人: Ding DING , Xiaozhong XU , Shan Liu
IPC分类号: H04N19/44 , H04N19/176 , H04N19/88
CPC分类号: H04N19/44 , H04N19/176 , H04N19/88
摘要: A method and apparatus comprising computer code configured to cause a processor or processors to receive a video bitstream comprising a current block in a current picture and reconstruct the current block by transforming the current block by a neural network comprising a plurality of upsample modules and activation modules, and at least one of the upsample modules includes a convolution layer and a pixel shuffle layer, and at least one of the activation modules includes a LeakyReLu function and a convolution function.
-
2.
公开(公告)号:US20240314341A1
公开(公告)日:2024-09-19
申请号:US18666025
申请日:2024-05-16
发明人: Robert SKUPIN , Yago SÁNCHEZ DE LA FUENTE , Thomas SCHIERL , Cornelius HELLGE , Karsten GRUENEBERG , Thomas WIEGAND
IPC分类号: H04N19/33 , H04N19/119 , H04N19/132 , H04N19/146 , H04N19/167 , H04N19/174 , H04N19/34 , H04N19/46 , H04N19/70 , H04N19/88
CPC分类号: H04N19/33 , H04N19/119 , H04N19/132 , H04N19/146 , H04N19/167 , H04N19/174 , H04N19/34 , H04N19/46 , H04N19/70 , H04N19/88
摘要: A video data stream is rendered reducible in a manner so that the reduction leads to a restriction of pictures of the reduced video data stream to merely a predetermined subarea of the pictures of the original video data stream and in a manner so that transcoding, such as re-quantization, may be avoided and a conformance of the reduced video data stream relative to the codec underlying the original video data stream be maintained. This is achieved by providing the video data stream with information including an indication of the predetermined subarea and replacement indices for redirecting the indices included by the payload portion so as to refer to, and/or replacement parameters for adjusting the first set of coding parameter settings so as to result in, a second set of coding parameter settings.
-
公开(公告)号:US20240305833A1
公开(公告)日:2024-09-12
申请号:US18669724
申请日:2024-05-21
发明人: Ning YAN , Yi-Wen CHEN , Xiaoyu XIU , Wei CHEN , Che-Wei KUO , Hong-Jheng JHU , Xianglin WANG , Bing YU
摘要: Implementations of the disclosure provide a video processing method for invertible filtering in video coding. The video processing method may include receiving, by a processor, an image derived from encoded video information stored in a bitstream. The video processing method may also include applying, by the processor, a forward filter to the image to generate an intermediate image and flipping the intermediate image. The video processing method may further include applying, by the processor, an inverse filter to the flipped intermediate image to generate a reconstructed image, and inversely flipping the reconstructed image to generate an invertible reconstructed image.
-
4.
公开(公告)号:US20240305798A1
公开(公告)日:2024-09-12
申请号:US18665493
申请日:2024-05-15
发明人: Robert SKUPIN , Yago SÁNCHEZ DE LA FUENTE , Thomas SCHIERL , Cornelius HELLGE , Karsten GRUENEBERG , Thomas WIEGAND
IPC分类号: H04N19/33 , H04N19/119 , H04N19/132 , H04N19/146 , H04N19/167 , H04N19/174 , H04N19/34 , H04N19/46 , H04N19/70 , H04N19/88
CPC分类号: H04N19/33 , H04N19/119 , H04N19/132 , H04N19/146 , H04N19/167 , H04N19/174 , H04N19/34 , H04N19/46 , H04N19/70 , H04N19/88
摘要: A video data stream is rendered reducible in a manner so that the reduction leads to a restriction of pictures of the reduced video data stream to merely a predetermined subarea of the pictures of the original video data stream and in a manner so that transcoding, such as re-quantization, may be avoided and a conformance of the reduced video data stream relative to the codec underlying the original video data stream be maintained. This is achieved by providing the video data stream with information including an indication of the predetermined subarea and replacement indices for redirecting the indices included by the payload portion so as to refer to, and/or replacement parameters for adjusting the first set of coding parameter settings so as to result in, a second set of coding parameter settings.
-
公开(公告)号:US12081792B2
公开(公告)日:2024-09-03
申请号:US17941432
申请日:2022-09-09
申请人: TENCENT AMERICA LLC
发明人: Han Gao , Liang Zhao , Xin Zhao , Shan Liu
IPC分类号: H04N19/139 , H04N19/105 , H04N19/176 , H04N19/52 , H04N19/593 , H04N19/88
CPC分类号: H04N19/52 , H04N19/105 , H04N19/139 , H04N19/176 , H04N19/593 , H04N19/88
摘要: Method, device, and non-transitory storage medium for interleaved motion vector prediction (MVP) for video coding are provided. A MVP candidate list for a current block may be generated based on spatial motion vectors associated with neighboring blocks and non-neighboring blocks. A first spatial motion vector predictor (SMVP) associated with an adjacent neighboring block to the left of the current block may be inserted into the MVP candidate list, and a second SMVP associated with an adjacent neighboring block to the top of the current block may be inserted into the MVP candidate list. One or more candidates in the MVP candidate list may be pruned based on determining that the one or more candidates have a same SMVP.
-
公开(公告)号:US20240276017A1
公开(公告)日:2024-08-15
申请号:US18443492
申请日:2024-02-16
发明人: Gary J. Sullivan , Sandeep Kanumuri
IPC分类号: H04N19/65 , H04N19/15 , H04N19/172 , H04N19/184 , H04N19/573 , H04N19/70 , H04N19/88
CPC分类号: H04N19/65 , H04N19/15 , H04N19/573 , H04N19/70 , H04N19/88 , H04N19/172 , H04N19/184
摘要: Disclosed herein are innovations for bitstreams having clean random access (CRA) pictures and/or other types of random access point (RAP) pictures. New type definitions and strategic constraints on types of RAP pictures can simplify mapping of units of elementary video stream data to a container format. Such innovations can help improve the ability for video coding systems to more flexibly perform adaptive video delivery, production editing, commercial insertion, and the like.
-
公开(公告)号:US20240267512A1
公开(公告)日:2024-08-08
申请号:US18636039
申请日:2024-04-15
IPC分类号: H04N19/105 , H04N19/137 , H04N19/176 , H04N19/88
CPC分类号: H04N19/105 , H04N19/137 , H04N19/176 , H04N19/88
摘要: Embodiments of the present disclosure provide a solution for video processing. A method for video processing is proposed. The method comprises: obtaining, during a conversion between a target block of a video and a bitstream of the video, a list of adaptive decoder side motion vector refinement (ADMVR) merge candidates for the target block in an ADMVR merge mode; reordering the list of ADMVR merge candidates; and performing the conversion based on the reordered list of ADMVR merge candidates. Compared with the conventional solution, the proposed method can advantageously improve the coding effectiveness and coding efficiency.
-
8.
公开(公告)号:US12003772B2
公开(公告)日:2024-06-04
申请号:US17970214
申请日:2022-10-20
申请人: KT CORPORATION
发明人: Bae Keun Lee
IPC分类号: H04N11/02 , H04N19/132 , H04N19/176 , H04N19/60 , H04N19/88
CPC分类号: H04N19/60 , H04N19/132 , H04N19/176 , H04N19/88
摘要: An image decoding method according to the present invention can comprise the steps of: acquiring residual coefficients of a current block; dequantizing the residual coefficients; performing secondary inverse transformation on the dequantized residual coefficients; and performing primary inverse transformation on the performance result of the secondary inverse transformation. The secondary inverse transformation can be performed for a partial region of the current block.
-
公开(公告)号:US20240127490A1
公开(公告)日:2024-04-18
申请号:US18312722
申请日:2023-05-05
申请人: Tencent America LLC
发明人: Thuong NGUYEN CANH , Xiaozhong XU , Joel JUNG , Shan LIU
IPC分类号: G06T9/00 , G06T9/20 , H04N19/119 , H04N19/167 , H04N19/50 , H04N19/88
CPC分类号: G06T9/001 , G06T9/20 , H04N19/119 , H04N19/167 , H04N19/50 , H04N19/88
摘要: A method of encoding includes receiving a polygon mesh comprising a plurality of faces and a plurality vertices; separating the polygon mesh into a left side half mesh and a right side half mesh by a plane; extracting the left side half mesh comprising a first plurality of vertices in-plane and on a left side of the polygon mesh; remapping the plurality of faces to represent a new vertices order in order to generate a plurality of remapped faces; extracting the plurality of remapped faces; compressing the left side half mesh by a codec; predicting a location of a second plurality of vertices on the right side half mesh using a symmetry based prediction on the compressed left side half mesh; and connecting the left side half mesh and the right side half mesh.
-
公开(公告)号:US11936869B2
公开(公告)日:2024-03-19
申请号:US18246470
申请日:2021-07-30
发明人: Yuan Ge , Hongzhi Shi , Jian Zhao
IPC分类号: G06K9/36 , H04N19/119 , H04N19/126 , H04N19/132 , H04N19/176 , H04N19/88 , H04N19/895
CPC分类号: H04N19/126 , H04N19/119 , H04N19/132 , H04N19/176 , H04N19/88 , H04N19/895
摘要: An image compression sampling method and assembly are provided. The method includes: performing sparse representation on a target image by using an initial sparse matrix, quantifying an initial sparse representation result to obtain an optimized sparse representation result, and obtaining an optimized sparse matrix; constructing a product matrix by using the optimized sparse matrix and an initial measurement matrix, and adjusting absolute values of off-diagonal elements in the product matrix to be less than a correlation threshold; performing singular value decomposition on the product matrix to obtain a diagonal matrix and a left singular matrix, and updating the diagonal matrix according to a quantity of samplings of the initial measurement matrix; and optimizing the initial measurement matrix by using the left singular matrix and the updated diagonal matrix to obtain an optimized measurement matrix, and collecting image data by using the optimized sparse matrix and the optimized measurement matrix.
-
-
-
-
-
-
-
-
-