公开(公告)号：US20210112276A1

公开(公告)日：2021-04-15

申请号：US17034896

申请日：2020-09-28

Applicant: TENCENT AMERICA LLC

Inventor： Sehoon YEA ,  Stephan WENGER ,  Shan LIU

IPC: H04N19/597 ,  H04N19/192 ,  H04N19/61 ,  H04N19/46 ,  H04N19/186

Abstract: A method of point cloud attribute coding performed by at least one processor, including obtaining an encoded bitstream corresponding to a point cloud; determining whether the encoded bitstream was encoded using an inter-channel tool for inter-channel decorrelation; based on determining that the encoded bitstream was encoded using the inter-channel tool, decoding the encoded bitstream using the inter-channel tool to reconstruct an attribute signal corresponding to the point cloud; and reconstructing the point cloud using the reconstructed attribute signal.

公开(公告)号：US20210006840A1

公开(公告)日：2021-01-07

申请号：US16915385

申请日：2020-06-29

Applicant: TENCENT AMERICA LLC

Inventor： Arash VOSOUGHI ,  Sehoon YEA ,  Stephan WENGER ,  Shan LIU

IPC: H04N19/96 ,  H04N19/70 ,  G06T9/40 ,  H04N19/176

Abstract: A method and apparatus for encoding/decoding a video stream using video point cloud coding, the encoding/decoding including obtaining an input point cloud, generating patches based on points of the point cloud, packing the patches into an image, generating the video stream based on the image, and smoothing the image using Morton codes.

公开(公告)号：US20210006837A1

公开(公告)日：2021-01-07

申请号：US16919996

申请日：2020-07-02

Applicant: TENCENT AMERICA LLC

Inventor： Sehoon YEA ,  Arash Vosoughi ,  Shan Liu

IPC: H04N19/62 ,  H04N19/64 ,  H04N19/96

Abstract: A method of encoding video data corresponding to a point cloud by at least one processor, the method including obtaining a plurality of transform coefficients corresponding to attributes of the point cloud; and encoding the plurality of transform coefficients to generate an embedded bitstream, the encoding including iterating over a plurality of bit-planes of the plurality of transform coefficients to process all points in the point cloud.

公开(公告)号：US20210006766A1

公开(公告)日：2021-01-07

申请号：US16917116

申请日：2020-06-30

Applicant: TENCENT AMERICA LLC

Inventor： Sehoon YEA ,  Arash VOSOUGHI ,  Stephan WENGER ,  Shan LIU

IPC: H04N13/161 ,  H04N19/597 ,  G06T9/00 ,  H04N19/85 ,  H04N19/176

Abstract: Systems and methods for decoding a video stream by at least one processor, a method includes receiving the video stream, the video stream including at least one cell; and reconstructing a cell from among the at least one cell. The reconstructing includes: obtaining a maximum difference value for each of at least one set of attribute values of the cell; and determining whether to apply a filter to the cell based on the maximum difference value of a set of attribute values of the at least one set of attribute values.

公开(公告)号：US20200380731A1

公开(公告)日：2020-12-03

申请号：US16887928

申请日：2020-05-29

Applicant: TENCENT AMERICA LLC

Inventor： Arash VOSOUGHI ,  Sehoon YEA ,  Shan LIU

IPC: G06T9/00

Abstract: According to some aspects of the disclosure, processing circuitry for point cloud decompression can decode prediction information of an image from a coded bitstream corresponding to a point cloud. The prediction information indicates that the image includes a first portion corresponding to patches in the point cloud, and a second portion corresponding to missed points by the patches from the point cloud. The processing circuitry can scan the second portion of the image according to a non-jumpy scan to obtain the missed points in a sequence, and reconstruct the point cloud based on reconstructed patches corresponding to the patches and reconstructed missed points based on the sequence of the missed points.

公开(公告)号：US20200311984A1

公开(公告)日：2020-10-01

申请号：US16823563

申请日：2020-03-19

Applicant: TENCENT AMERICA LLC

Inventor： Sehoon YEA ,  Arash VOSOUGHI ,  Shan LIU

IPC: G06T9/40

Abstract: A method of adaptive point cloud attribute coding includes obtaining an attribute of a current point included in point cloud data, and obtaining candidate predicted values of the obtained attribute, the candidate predicted values including any one or any combination of a weighted average value of a plurality of distances from the current point respectively to other points included in the point cloud data, a first predicted value of a first distance from the current point to a first nearest point among the other points and a second predicted value of a second distance from the current point to a second nearest point after the first nearest point among the other points. The method further includes selecting, for the obtained attribute, one among the obtained candidate predicted values, using rate-distortion optimization, and setting, for a decoder, a flag indicating whether the obtained candidate predicted values includes the weighted average value.

公开(公告)号：US20200304865A1

公开(公告)日：2020-09-24

申请号：US16823797

申请日：2020-03-19

Applicant: TENCENT AMERICA LLC

Inventor： Sehoon YEA ,  Arash Vosoughi ,  Shan Liu

IPC: H04N21/4402 ,  H04N21/435 ,  H04N19/196 ,  H04N19/105 ,  H04N19/132 ,  H04L29/06

Abstract: A method of predicting point cloud attribute coding includes receiving point cloud data comprising one or more candidate points and extracting one or more candidate attribute values for the one or more candidate points from the received point cloud data. The method further includes calculating a weighted median from the one or more extracted candidate attribute values and a weight factor, whereby the weight factor corresponds to a relative importance factor of a candidate vector associated with the extracted candidate attribute values. The method further includes assign one or more prediction indices corresponding to attribute data for video encoding to the candidate points in response to the calculation of the weighted median, wherein the prediction indices and processing the media content to encode the attribute data associated with the candidate points having the lowest prediction indices.

公开(公告)号：US20200304829A1

公开(公告)日：2020-09-24

申请号：US16825051

申请日：2020-03-20

Applicant: TENCENT AMERICA LLC

Inventor： Sehoon YEA ,  Arash VOSOUGHI ,  Shan LIU

IPC: H04N19/513 ,  H04N19/547 ,  H04N19/172 ,  H04N19/132 ,  H04N19/186

Abstract: A method of interframe point cloud attribute coding is performed by at least one processor and includes obtaining, as a motion estimation unreliability measure of motion estimation of a target frame, a value inversely proportional to a ratio of a number of first point cloud samples of the target frame respectively with second point cloud samples of an interframe reference frame, to a number of point cloud samples in the target frame. The method further includes identifying whether the obtained motion estimation unreliability measure is greater than a predetermined threshold, based on the obtained motion estimation unreliability measure being identified to be greater than the predetermined threshold, skipping motion compensation of the target frame, and based on the obtained motion estimation unreliability measure being identified to be less than or equal to the predetermined threshold, performing the motion compensation of the target frame.

公开(公告)号：US20200304813A1

公开(公告)日：2020-09-24

申请号：US16808009

申请日：2020-03-03

Applicant: TENCENT AMERICA LLC

Inventor： Byeongdoo CHOI ,  Shan LIU ,  Arash VOSOUGHI ,  Sehoon YEA

IPC: H04N19/20 ,  H04N19/37 ,  H04N19/159 ,  H04N19/70

Abstract: A method and apparatus for referencing a parameter set to permit decoding of a coded point cloud sequence includes parsing a parameter set associated with the coded point cloud sequence. A dependent parameter set is identified based on parsing the parameter set. It is identified whether the dependent parameter set is a patch-level parameter set. The patch-level parameter set is referenced based on identifying that the dependent parameter set is the patch-level parameter set to permit the decoding of the coded point cloud sequence. A frame-level parameter set is referenced based on identifying that the dependent parameter set is not the patch-level parameter set to permit the decoding of the coded point cloud sequence.

公开(公告)号：US20200221133A1

公开(公告)日：2020-07-09

申请号：US16731448

申请日：2019-12-31

Applicant: TENCENT AMERICA LLC

Inventor： Arash VOSOUGHI ,  Sehoon YEA ,  Shan LIU

IPC: H04N19/85 ,  H04N21/434 ,  H04N21/4402 ,  H04N19/80

Abstract: Methods and apparatuses of decoding a video stream encoded using video point cloud coding include obtaining a geometry-reconstructed point cloud; dividing the geometry-reconstructed point cloud into a plurality of cells; obtaining a first reference point including a centroid of a first plurality of points; generating a second plurality of points by applying a first filter to the first plurality of points based on the first reference point; obtaining a second reference point including a centroid of the second plurality of points; generating a third plurality of points by applying a second filter to the second plurality of points based on the second reference point, wherein a strength of the first filter is higher than a strength of the second filter; obtaining a smoothed geometry-reconstructed point cloud based on the third plurality of points; and reconstructing a dynamic point cloud using the smoothed geometry-reconstructed point cloud.