IP Library › Granted Patent US 12,652,395
Granted Patent B2
US 12,652,395 · App. 18/820,800 · Granted Jun 9, 2026

Face count reduction for lossy mesh compression

Inventors: Thuong Nguyen Canh (Palo Alto, CA); Xiaozhong Xu (State College, PA); Shan Liu (San Jose, CA)
Assignee: TENCENT AMERICA LLC
H04N19/14H04N19/119H04N19/1883H04N19/70
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 12,652,395
App. No.
18/820,800
Granted
Jun 9, 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 by determining a face normal for each face in the mesh, classifying the groups based on their orientation to the face normal, and merging adjacent faces that share an edge between the plurality of groups, and decode the encoded volumetric data based on the plurality of groups.

Claims (28)

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 by determining a face normal for each face in the mesh, classifying the groups based on their orientation to the face normal, and merging adjacent faces that share an edge between the plurality of groups; and

decoding the encoded volumetric data based on the plurality of groups, and decoding the encoded volumetric data based on the plurality of groups further comprises splitting the merged adjacent faces into a target m-polygonal face.

2 . The method according to claim 1 , wherein partitioning the plurality of vertices of the mesh into the plurality of groups is further based on identifying the faces that share the edge, and merging the faces that share the edge into a larger polygonal face than before merging the face.

3 . The method according to claim 1 , wherein the target m-polygonal face is a triangular face.

4 . The method according to claim 1 , wherein splitting the merged adjacent faces into the target m-polygonal face is based on decoded displacements.

5 . The method according to claim 4 , wherein at least one of the decoded displacements is based on a non-zero displacement syntax indicating a sum of values.

6 . The method according to claim 4 , wherein splitting the merged adjacent faces into the target m-polygonal face is further based on an nzFlag syntax.

7 . An apparatus for video decoding, the apparatus comprising:

at least one memory configured to store computer program code;

at least one processor configured to access the computer program code and operate as instructed by the computer program code, the computer program code including:

obtaining code configured to cause the at least one processor to obtain, from a bitstream, a mesh representing an encoded volumetric data of at least one three-dimensional (3D) visual content;

partitioning code configured to cause the at least one processor to partition a plurality of vertices of the mesh into a plurality of groups by determining a face normal for each face in the mesh, classifying the groups based on their orientation to the face normal, and merging adjacent faces that share an edge between the plurality of groups; and

decoding code configured to cause the at least one processor to decode the encoded volumetric data based on the plurality of groups, and decoding the encoded volumetric data based on the plurality of groups further comprises splitting the merged adjacent faces into a target m-polygonal face.

8 . The apparatus according to claim 7 , wherein partitioning the plurality of vertices of the mesh into the plurality of groups is further based on identifying the faces that share the edge, and merging the faces that share the edge into a larger polygonal face than before merging the face.

9 . The apparatus according to claim 7 , wherein the target m-polygonal face is a triangular face.

10 . The apparatus according to claim 7 , wherein splitting the merged adjacent faces into the target m-polygonal face is based on decoded displacements.

11 . The apparatus according to claim 10 , wherein at least one of the decoded displacements is based on a non-zero displacement syntax indicating a sum of values.

12 . The apparatus according to claim 10 , wherein splitting the merged adjacent faces into the target m-polygonal face is further based on an nzFlag syntax.

13 . A non-transitory computer readable medium storing a program causing a computer 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 by determining a face normal for each face in the mesh, classifying the groups based on their orientation to the face normal, and merging adjacent faces that share an edge between the plurality of groups; and

decode the encoded volumetric data based on the plurality of groups, and decoding the encoded volumetric data based on the plurality of groups further comprises splitting the merged adjacent faces into a target m-polygonal face.

14 . The method according to claim 13 , wherein partitioning the plurality of vertices of the mesh into the plurality of groups is further based on identifying the faces that share the edge, and merging the faces that share the edge into a larger polygonal face than before merging the face.

15 . The method according to claim 13 , wherein the target m-polygonal face is a triangular face.

16 . The method according to claim 13 , wherein splitting the merged adjacent faces into the target m-polygonal face is based on decoded displacements.

17 . The method according to claim 13 , wherein at least one of the decoded displacements is based on a non-zero displacement syntax indicating a sum of values.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 18, 2026
From: NGUYEN CANH, THUONG; XU, XIAOZHONG; LIU, SHAN
To: TENCENT AMERICA LLC
Reel/Frame 074923/0456 →
Continuity (2)
Provisional Application 63603020 · Nov 27, 2023
Related Publication 20250175617A1 · May 29, 2025
References Cited (6)
US 5793429A · Kim · 1998 [cited by examiner]
US 6256039B1 · Krishnamurthy · 2001 [cited by examiner]
US 6476804B1 · Costabel · 2002 [cited by examiner]
US 11627294B2 · Thompson · 2023 [cited by examiner]
US 20070291029A1 · Konev · 2007 [cited by examiner]
US 20240022765A1 · Tourapis · 2024 [cited by examiner]