-
公开(公告)号：US11816868B2
公开(公告)日：2023-11-14
申请号：US17332213
申请日：2021-05-27
申请人： TENCENT AMERICA LLC
发明人： Xiang Zhang , Wen Gao , Shan Liu
摘要： A method, computer program, and computer system is provided for point cloud coding. The method includes receiving, from a bitstream, data corresponding to a point cloud; obtaining from the data a first prediction residual of a first component from among a plurality of components of an attribute associated with the point cloud; reconstructing the first prediction residual; determining a predicted second prediction residual based on the reconstructed first prediction residual and at least one model parameter; obtaining a second prediction residual of a second component from among the plurality of components based on the predicted second prediction residual; reconstructing the second prediction residual; and decoding the data corresponding to the point cloud based on the reconstructed first prediction residual and the reconstructed second prediction residual.
-
公开(公告)号：US11783512B2
公开(公告)日：2023-10-10
申请号：US17859811
申请日：2022-07-07
申请人： Tencent America LLC
发明人： Xiang Zhang , Wen Gao , Shan Liu
IPC分类号： G06T9/40
CPC分类号： G06T9/40
摘要： Aspects of the disclosure provide methods and apparatuses for point cloud compression. In some examples, an apparatus for point cloud compression includes processing circuitry. The processing circuitry determines a plurality of original points in a point cloud that is quantized to a reconstructed position. The processing circuitry determines an attribute value of the reconstructed position based on attribute information of the plurality of original points. Further, the processing circuitry encodes the point cloud based on the determined attribute value of the reconstructed position.
-
公开(公告)号：US20230143700A1
公开(公告)日：2023-05-11
申请号：US18153413
申请日：2023-01-12
申请人： TENCENT AMERICA LLC
发明人： Xiang Zhang , Wen Gao , Shan Liu
摘要： A method, computer program, and computer system is provided for decoding point cloud data. Data corresponding to a point cloud is received. A number of contexts associated with the received data is reduced based on occupancy data corresponding to one or more parent nodes and one or more child nodes within the received data. The data corresponding to the point cloud is decoded based on the reduced number of contexts.
-
公开(公告)号：US11606556B2
公开(公告)日：2023-03-14
申请号：US17502605
申请日：2021-10-15
申请人： TENCENT AMERICA LLC
发明人： Wen Gao , Xiang Zhang , Shan Liu
IPC分类号： H04N19/119 , H04N19/46 , H04N19/117 , H04N19/80
摘要： Methods and apparatuses of encoding a video stream using video point cloud coding include determining a projection plane for each point in the point cloud; creating a list of raw points included in the point cloud; generating a list of connected components; determining whether a number of connected components is greater than a first threshold; based on determining that the number of the connected components is greater than the first threshold, processing the connected components and generating one or more patches based on the processed connected components; and generating an encoded video stream based on the generated one or more patches, wherein the list of raw points is updated based on at least one from among a result of the generating of the list of connected components, and a result of the processing of the connected components.
-
公开(公告)号：US20230040484A1
公开(公告)日：2023-02-09
申请号：US17502605
申请日：2021-10-15
申请人： TENCENT AMERICA LLC
发明人： Wen Gao , Xiang Zhang , Shan Liu
IPC分类号： H04N19/119 , H04N19/80 , H04N19/117 , H04N19/46
摘要： Methods and apparatuses of encoding a video stream using video point cloud coding include determining a projection plane for each point in the point cloud; creating a list of raw points included in the point cloud; generating a list of connected components; determining whether a number of connected components is greater than a first threshold; based on determining that the number of the connected components is greater than the first threshold, processing the connected components and generating one or more patches based on the processed connected components; and generating an encoded video stream based on the generated one or more patches, wherein the list of raw points is updated based on at least one from among a result of the generating of the list of connected components, and a result of the processing of the connected components.
-
公开(公告)号：US20220394295A1
公开(公告)日：2022-12-08
申请号：US17500345
申请日：2021-10-13
申请人： TENCENT AMERICA LLC
发明人： Xiang Zhang , Wen Gao , Shan Liu , Weiwei Feng , Bing Jian
IPC分类号： H04N19/597 , H04N19/186
摘要： Methods and apparatuses of encoding a video stream using video point cloud coding include obtaining a source point cloud; obtaining a geometry-reconstructed point cloud, wherein the geometry-reconstructed point cloud is reconstructed using lossy coding; obtaining a target point included in the geometry-reconstructed point cloud; performing at least one of a forward K-dimensional (KD)-tree search to determine a first plurality of points of the source point cloud which are nearest neighbors to the target point, and a backward KD-tree search to determine a second plurality of points of the source point cloud for which the target point is a nearest neighbor; determining an average color value based on at least one of a first average color value of the first plurality of points and a second average color value of the second plurality of points; selecting a color value for the target point based on the average color value; and generating an encoded video stream based on the selected color value.
-
公开(公告)号：US20220394293A1
公开(公告)日：2022-12-08
申请号：US17495301
申请日：2021-10-06
申请人： TENCENT AMERICA LLC
发明人： Xiang Zhang , Wen Gao , Shan Liu , Weiwei Feng , Bing Jian
IPC分类号： H04N19/597 , H04N19/184 , G06T15/04
摘要： Methods and apparatuses of encoding a video stream using video point cloud coding include obtaining a source point cloud; generating a geometry map and a texture map based on the source point cloud; generating a reconstructed geometry map and a reconstructed texture map using lossy coding without using recoloring, wherein a resolution of the reconstructed geometry map is same as a resolution of the reconstructed texture map; obtaining a point of the source point cloud corresponding to a geometry pixel of the geometry map and a texture pixel of the texture map; selecting a color of the texture pixel based on a color of the obtained point; and generating an encoded video stream based on the selected color, the geometry map, and the texture map.
-
公开(公告)号：US11469771B2
公开(公告)日：2022-10-11
申请号：US16916944
申请日：2020-06-30
申请人： TENCENT AMERICA LLC
发明人： Xiang Zhang , Wen Gao , Shan Liu
摘要： Aspects of the disclosure provide methods, apparatuses, and a non-transitory computer-readable medium for point cloud compression and decompression. In a method, syntax information of a point cloud in a quantized space is decoded from a coded bitstream. The syntax information includes dividing information and adaptive geometry quantization information for a bounding box of the point cloud. The bounding box of the point cloud is divided into a plurality of parts based on the dividing information. Quantization parameters for the parts in the bounding box are determined based on the adaptive geometry quantization information. Points in each of the parts in the bounding box of the point cloud are reconstructed based on the quantization parameter for the respective part in the bounding box.
-
公开(公告)号：US11438628B2
公开(公告)日：2022-09-06
申请号：US17314843
申请日：2021-05-07
申请人： TENCENT AMERICA LLC
发明人： Xiang Zhang , Wen Gao , Shan Liu
IPC分类号： H04N19/62 , H04N19/64 , H04N19/179 , H04N19/119 , H04N19/597 , H04N19/70
摘要： A method, computer program, and computer system is provided for decoding point cloud data. Data corresponding to a point cloud is received. Hash elements corresponding to one or more neighboring nodes associated with a current node are identified. A size of a hash table is decreased based on deleting one or more of the hash elements corresponding to non-border regions of the one or more neighboring nodes. The data corresponding to the point cloud is decoded based on the hash table having the decreased size.
-
公开(公告)号：US20220058837A1
公开(公告)日：2022-02-24
申请号：US17324627
申请日：2021-05-19
申请人： TENCENT AMERICA LLC
发明人： Wen Gao , Xiang Zhang , Shan Liu
摘要： A method, computer program, and computer system is provided for decoding point cloud data. Data corresponding to a point cloud is received. A number of contexts associated with the received data is reduced based on reducing a size of an array corresponding to syntax elements for predictive tree-based coding of the point cloud. The data corresponding to the point cloud is decoded based on the reduced number of contexts.
-
-
-
-
-
-
-
-
-
搜索结果
81 条记录 (耗时 0.029 秒)
