公开(公告)号：US20240314353A1

公开(公告)日：2024-09-19

申请号：US18602832

申请日：2024-03-12

Applicant: TENCENT AMERICA LLC

Inventor： Jun TIAN ,  Shan Liu ,  Xiaozhong Xu

IPC: H04N19/54 ,  H04N19/105 ,  H04N19/159 ,  H04N19/172

CPC classification number: H04N19/54 ,  H04N19/105 ,  H04N19/159 ,  H04N19/172

Abstract: A method of decoding a dynamic mesh sequence, the method includes: receiving a coded bitstream comprising the dynamic mesh sequence in a first frame and a second frame that occurs later than the first frame; reconstructing the dynamic mesh in the first frame; determining whether a duplicate vertex removal mode is enabled in which a motion vector of a vertex in the dynamic mesh second that is a duplicate of a vertex in the dynamic mesh sequence in the first frame; based on determining that the duplicate vertex removal mode is enabled, decoding a motion vector for each vertex in the second frame that is not a duplicate of a vertex in the reconstructed first frame; and reconstruct the dynamic mesh sequence in the second frame using the reconstructed dynamic mesh in the first frame and each decoded motion vector.

公开(公告)号：US20240242389A1

公开(公告)日：2024-07-18

申请号：US18463538

申请日：2023-09-08

Applicant: Tencent America LLC

Inventor： Jun TIAN ,  Xiaozhong XU ,  Shan LIU

IPC: G06T9/00

CPC classification number: G06T9/001

Abstract: A method and apparatus comprising computer code configured to cause a processor or processors to obtain a mesh, the mesh comprising a frame of a sequence corresponding to three-dimensional (3D) volumetric data, the frame including a plurality of vertices of the mesh, use 4:2:0 sampling to sample the mesh, determine a coefficient of a displacement vector of at least one vertex of the sampled mesh, and decode the mesh based on the coefficient and the sampled mesh.

公开(公告)号：US20230388543A1

公开(公告)日：2023-11-30

申请号：US18127487

申请日：2023-03-28

Applicant: Tencent America LLC

Inventor： Jun TIAN ,  Chao HUANG ,  Xiang ZHANG ,  Xiaozhong XU ,  Shan LIU

IPC: H04N19/597 ,  H04N19/105 ,  H04N19/154 ,  H04N19/172 ,  H04N19/46

CPC classification number: H04N19/597 ,  H04N19/105 ,  H04N19/154 ,  H04N19/172 ,  H04N19/46

Abstract: A plurality of neighboring vertices of a current vertex in a current frame of a mesh is determined. The current frame corresponds to the mesh at a first time instance. Each of the plurality of neighboring vertices is connected to the current vertex through a respective edge in the mesh. A plurality of neighboring estimation errors of the plurality of neighboring vertices is determined. Each of the plurality of neighboring estimation errors indicates a difference between a reference vertex of a corresponding one of the plurality of neighboring vertices in a reference frame and the corresponding one of the plurality of neighboring vertices in the current frame. The reference frame corresponds to the mesh at a second time instance. A prediction residue of the current vertex is determined based on the plurality of neighboring estimation errors. Prediction information of the current vertex is generated based on the determined prediction residue.

公开(公告)号：US20230222697A1

公开(公告)日：2023-07-13

申请号：US17969570

申请日：2022-10-19

Applicant: Tencent America LLC

Inventor： Chao HUANG ,  Xiang ZHANG ,  Jun TIAN ,  Xiaozhong XU ,  Shan LIU

IPC: G06T9/00 ,  G06V10/44 ,  G06V10/24

CPC classification number: G06T9/001 ,  G06V10/24 ,  G06V10/457

Abstract: Aspects of the disclosure provide methods and apparatuses for mesh coding (encoding and/or decoding). In some examples, an apparatus for coding mesh includes processing circuitry. The processing circuitry decodes, three dimensional (3D) coordinates of vertices in a first 3D mesh frame and connectivity information of the vertices from a bitstream that carries the first 3D mesh frame. The first 3D mesh frame represents a surface of an object with polygons. The processing circuitry deduces texture coordinates associated with the vertices, and decodes a texture map for the first 3D mesh frame from the bitstream. The texture map includes first one or more 2D charts with 2D vertices having the texture coordinates. The processing circuitry reconstructs the first 3D mesh frame based on the 3D coordinates of the vertices, the connectivity information of the vertices, the texture map and the texture coordinates.

公开(公告)号：US20230057207A1

公开(公告)日：2023-02-23

申请号：US17892976

申请日：2022-08-22

Applicant: Tencent America LLC

Inventor： Jun TIAN ,  Xiaozhong XU ,  Shan LIU

IPC: H04S7/00

Abstract: Aspects of the disclosure provide methods and apparatuses for audio processing. In some examples, an apparatus for media processing includes processing circuitry. The processing circuitry receives first six degrees of freedom (6 DoF) information associated with a media content for a scene in a media application. The first 6 DoF information includes a first spatial location and a first rotation orientation for rotation about a center at the first spatial location. The processing circuitry determines that a rendering platform for rendering the media content is a three degrees of freedom (3 DoF) platform; and calculates, a revolution orientation of the media content on a sphere centered other than the first spatial location, according to at least the first spatial location. The revolution orientation is 3 DoF information associated with the media content for rendering on the 3 DoF platform.

公开(公告)号：US20250063193A1

公开(公告)日：2025-02-20

申请号：US18799578

申请日：2024-08-09

Applicant: TENCENT AMERICA LLC

Inventor： Thuong NGUYEN CANH ,  Xiaozhong XU ,  Chao HUANG ,  Shan LIU ,  Jun TIAN

IPC: H04N19/597 ,  H04N19/126 ,  H04N19/17

Abstract: A method performed includes encoding a first vertex, a second vertex, and a third vertex of a first face of a polygon mesh; determining a set of adaptive weights that comprise a first weight, a second weight, and a third weight; and performing parallelogram prediction to predict a fourth vertex in a second face of the polygon mesh by applying the first weight to the first vertex, the second weight to the second vertex, and the third weigh to the third vertex, in which the first weight is less than 0.8 and greater than 0, in which the second weight is greater than −0.8 and less than 0, and in which the third weight is less than 0.9 and greater than 0.

公开(公告)号：US20250030889A1

公开(公告)日：2025-01-23

申请号：US18777254

申请日：2024-07-18

Applicant: Tencent America LLC

Inventor： Jun TIAN ,  Xiaozhong XU ,  Shan LIU

IPC: H04N19/597 ,  H04N19/17

Abstract: In a method of mesh decoding, a bitstream that includes prediction information of a plurality of vertices in a mesh frame is received. A prediction value of a current vertex of the plurality of vertices is determined based on (i) a value of the current vertex received in the bitstream and (ii) each distance between the current vertex and one or more neighboring vertices of the current vertex in the mesh frame. The current vertex is reconstructed based on the prediction value of the current vertex.

公开(公告)号：US20240357164A1

公开(公告)日：2024-10-24

申请号：US18644014

申请日：2024-04-23

Applicant: Tencent America LLC

Inventor： Jun TIAN ,  Xiaozhong XU ,  Shan LIU

IPC: H04N19/597 ,  G06T17/20 ,  H04N19/159 ,  H04N19/63

CPC classification number: H04N19/597 ,  G06T17/20 ,  H04N19/159 ,  H04N19/63

Abstract: An apparatus includes processing circuitry. The processing circuitry is configured to receive a bitstream that includes displacement information and base mesh information of a mesh in a current mesh frame. The processing circuitry is configured to determine a plurality of wavelet coefficients packed in a plurality of two-dimensional (2D) blocks of a 2D image based on the displacement information. The processing circuitry is configured to unpack the plurality of wavelet coefficients packed from the plurality of 2D blocks based on levels of detail of the plurality of wavelet coefficients. The processing circuitry is configured to determine a plurality of displacements of the mesh in the current mesh frame based on the unpacked plurality of wavelet coefficients. The plurality of displacements is associated with a base mesh and the mesh in the current mesh frame, and the base mesh includes a subset of a plurality of vertices of the mesh.

公开(公告)号：US20240348826A1

公开(公告)日：2024-10-17

申请号：US18632467

申请日：2024-04-11

Applicant: TENCENT AMERICA LLC

Inventor： Jun TIAN ,  Xiaozhong XU ,  Shan LIU

IPC: H04N19/597 ,  H04N19/14 ,  H04N19/63

CPC classification number: H04N19/597 ,  H04N19/14 ,  H04N19/63

Abstract: A method and apparatus comprising computer code configured to cause a processor or processors to obtain, from a bitstream, a mesh representing an encoded volumetric data of at least one three-dimensional (3D) visual content, partition a plurality of vertices of the mesh into a plurality of groups, and decode the encoded volumetric data by predicting the vertices in each group of the plurality of groups.

公开(公告)号：US20240292028A1

公开(公告)日：2024-08-29

申请号：US18587404

申请日：2024-02-26

Applicant: TENCENT AMERICA LLC

Inventor： Jun TIAN ,  Xiaozhong XU ,  Shan LIU

IPC: H04N19/597 ,  H04N19/70

CPC classification number: H04N19/597 ,  H04N19/70

Abstract: Method, apparatus, and system for video encoding are provided. The process may include receiving volumetric data of at least one three-dimensional (3D) content. The process may also include determining a first collection of one or more duplicate vertices in a first frame of the volumetric data using a mapping function and then determining a second collection one or more non-skippable duplicate vertices among the first collection. In some embodiments, the one or more duplicate vertices comprises vertex indices of vertices in the first frame may have same mapping as respective vertices in a reference frame. In some embodiments, the second collection may include indices of the one or more non-skippable duplicate vertices with respect to positions of the respective vertices in the first collection. The process may include signaling the second collection and a number of vertices in the second collection.