IP Library Granted Patent US 12671838
Granted Patent B2
US 12671838 · App. 18/632,467 · Granted Jun 30, 2026

Adaptive wavelet transform

Inventors: Jun Tian (Palo Alto, CA); Xiaozhong Xu (Palo Alto, CA); Shan Liu (Palo Alto, CA)
Assignee: TENCENT AMERICA LLC
H04N19/597H04N19/14H04N19/63
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12671838
App. No.
18/632,467
Granted
Jun 30, 2026
Kind
B2
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.

Claims (29)

1 . A method for video decoding, the method performed by at least one processor and comprising:

obtaining, from a bitstream, a mesh representing an encoded volumetric data of at least one three-dimensional (3D) visual content;

partitioning a plurality of vertices of the mesh into a plurality of groups; and

decoding the encoded volumetric data by predicting the vertices in each group of the plurality of groups based on an adaptive wavelet transform, the adaptive wavelet transform comprises a prediction process and an update process, the prediction process is dependent on geometry attribute signals at a set of ones of the plurality of vertices, at least one vertex of the set being indicated by the prediction process as a middle between at least two other vertices of the set, and the update process is dependent on neighboring vertices, including the at least two other vertices, of the set.

2 . The method according to claim 1 , wherein the prediction process comprises selecting the at least two other vertices of the first set as endpoints of an edge of the mesh.

3 . The method according to claim 1 , wherein the update process is dependent on a number of neighboring vertices, including the at least two other vertices.

4 . The method according to claim 1 , wherein the update process is dependent on a scalar value.

5 . The method according to claim 4 , wherein the prediction process is also dependent on the scalar value.

6 . The method according to claim 1 , wherein decoding the encoded volumetric data comprises applying the adaptive wavelet transform to an enhancement layer of a mesh frame of the mesh.

7 . The method according to claim 1 , wherein decoding the encoded volumetric data comprises applying the adaptive wavelet transform to a mesh frame of a mesh sequence of the mesh.

8 . The method according to claim 7 , wherein decoding the encoded volumetric data comprises selecting a region of the mesh frame and applying the adaptive wavelet transform to the selected region of the mesh frame.

9 . The method according to claim 1 , wherein decoding the encoded volumetric data comprises applying the adaptive wavelet transform to a base layer of a mesh frame of the mesh.

10 . The method according to claim 1 , wherein decoding the encoded volumetric data comprises applying the adaptive wavelet transform to a frequency band of a mesh frame of the mesh.

11 . A method for video encoding, the method performed by at least one processor and comprising:

obtaining a mesh representing an volumetric data of at least one three-dimensional (3D) visual content;

partitioning a plurality of vertices of the mesh into a plurality of groups; and

encoding the volumetric data based on a prediction of the vertices in each group of the plurality of groups and an adaptive wavelet transform, the adaptive wavelet transform comprises a prediction process and an update process, the prediction process is dependent on geometry attribute signals at a set of ones of the plurality of vertices, at least one vertex of the set being indicated by the prediction process as a middle between at least two other vertices of the set, and the update process is dependent on neighboring vertices, including the at least two other vertices, of the set.

12 . The method according to claim 11 , wherein the prediction process comprises selecting the at least two other vertices of the first set as endpoints of an edge of the mesh.

13 . The method according to claim 11 , wherein the update process is dependent on a number of neighboring vertices, including the at least two other vertices.

14 . The method according to claim 11 , wherein the update process is dependent on a scalar value.

15 . The method according to claim 11 , wherein the prediction process is dependent on the scalar value.

16 . A method of encoding visual media data, the method comprising:

obtaining a mesh representing an volumetric data of at least one three-dimensional (3D) visual content;

partitioning a plurality of vertices of the mesh into a plurality of groups; and

encoding and transmitting a bitstream including the volumetric data and encoded based on a prediction of the vertices in each group of the plurality of groups and an adaptive wavelet transform, the adaptive wavelet transform comprises a prediction process and an update process, the prediction process is dependent on geometry attribute signals at a set of ones of the plurality of vertices, at least one vertex of the set being indicated by the prediction process as a middle between at least two other vertices of the set, and the update process is dependent on neighboring vertices, including the at least two other vertices, of the set.

17 . The method according to claim 16 , wherein the prediction process comprises selecting the at least two other vertices of the first set as endpoints of an edge of the mesh.

18 . The method according to claim 16 , wherein the update process is dependent on a number of neighboring vertices, including the at least two other vertices.

19 . The method according to claim 16 , wherein the update process is dependent on a scalar value.

20 . The method according to claim 19 , wherein the prediction process is dependent on the scalar value.