Distortion information for each iteration of vertices reconstruction

Patent metadata

Field	Value
Publication number	US-12561845-B2
Application number	US-202418627336-A
Country	US
Kind code	B2
Filing date	Apr 4, 2024
Priority date	Apr 18, 2023
Publication date	Feb 24, 2026
Grant date	Feb 24, 2026

Abstract

An apparatus includes a communication interface configured to receive a compressed bitstream including a base mesh sub-bitstream and a processor operably coupled to the communication interface. The processor is configured to decode a plurality of submeshes from the base mesh sub-bitstream. The processor is also configured to subdivide a submesh of the plurality of submeshes according to a subdivision iteration count to generate at least one subdivided submesh, including determine a number of vertex positions for the at least one subdivided submesh by use of a number of vertices associated with an original submesh and by use of distortion information between the original submesh and a base mesh at each subdivision iteration associated with the subdivision iteration count. The processor is also configured to reconstruct at least a portion of a mesh-frame using the vertex positions corresponding to the at least one subdivided submesh.

First claim

What is claimed is:

1 . An apparatus comprising:
a communication interface configured to receive a compressed bitstream including a base mesh sub-bitstream; and a processor operably coupled to the communication interface, the processor configured to:
decode a plurality of submeshes from the base mesh sub-bitstream;
subdivide a submesh of the plurality of submeshes according to a subdivision iteration count to generate at least one subdivided submesh, including determine a number of vertex positions for the at least one subdivided submesh by use of a number of vertices associated with an original submesh and by use of distortion information between the original submesh and a base mesh at each subdivision iteration associated with the subdivision iteration count; and
reconstruct at least a portion of a mesh-frame using the vertex positions corresponding to the at least one subdivided submesh.

2 . The apparatus of claim 1 , wherein the number of vertices associated with the original submesh and the distortion information are included as signaling elements in association with the compressed bitstream.

3 . The apparatus of claim 2 , wherein the signaling elements also include one or more of:
the subdivision iteration count; a submesh identifier; and a number of distortions associated with the submesh.

4 . The apparatus of claim 3 , wherein the signaling elements are signaled as part of a Supplemental Enhancement Information (SEI) message.

5 . The apparatus of claim 1 , wherein the distortion information includes a distortion metric type.

6 . The apparatus of claim 5 , wherein the distortion metric type includes at least one of:
a point cloud based point-to-point (D1) metric; a point cloud based point-to-plane (D2) metric; a point cloud based peak signal-to-noise ratio (PSNR) metric; a rendered image based PSNR metric; and a perceptual based distortion metric.

7 . The apparatus of claim 1 , wherein the processor is further configured to halt the reconstruction of the mesh-frame at a particular iteration of the subdivision iteration count based on the distortion information indicating a reconstruction quality is above a threshold.

8 . The apparatus of claim 1 , wherein the number of vertices is determined based on a difference between a number of vertices associated with a next iteration of the subdivision iteration count and a current iteration of the subdivision iteration count.

9 . A method comprising:
receiving a compressed bitstream including a base mesh sub-bitstream; decoding a plurality of submeshes from the base mesh sub-bitstream; subdividing a submesh of the plurality of submeshes according to a subdivision iteration count to generate at least one subdivided submesh, including determining a number of vertex positions for the at least one subdivided submesh by using a number of vertices associated with an original submesh and by using distortion information between the original submesh and a base mesh at each subdivision iteration associated with the subdivision iteration count; and reconstructing at least a portion of a mesh-frame using the vertex positions corresponding to the at least one subdivided submesh.

10 . The method of claim 9 , wherein the number of vertices associated with the original submesh and the distortion information are included as signaling elements in association with the compressed bitstream.

11 . The method of claim 10 , wherein the signaling elements also include one or more of:
the subdivision iteration count; a submesh identifier; and a number of distortions associated with the submesh.

12 . The method of claim 11 , wherein the signaling elements are signaled as part of a Supplemental Enhancement Information (SEI) message.

13 . The method of claim 9 , wherein the distortion information includes a distortion metric type.

14 . The method of claim 13 , wherein the distortion metric type includes at least one of:
a point cloud based point-to-point (D1) metric; a point cloud based point-to-plane (D2) metric; a point cloud based peak signal-to-noise ratio (PSNR) metric; a rendered image based PSNR metric; and a perceptual based distortion metric.

15 . The method of claim 9 , further comprising halting the reconstruction of the mesh-frame at a particular iteration of the subdivision iteration count based on the distortion information indicating a reconstruction quality is above a threshold.

16 . The method of claim 9 , wherein the number of vertices is determined based on a difference between a number of vertices associated with a next iteration of the subdivision iteration count and a current iteration of the subdivision iteration count.

17 . An apparatus comprising:
a communication interface; and a processor operably coupled to the communication interface, the processor configured to:
subdivide a submesh according to a subdivision iteration count to generate at least one subdivided submesh having vertex positions;
determine a number of vertices associated with the submesh to be used to simplify the vertex positions;
determine distortion information between the submesh and a base mesh at each subdivision iteration associated with the subdivision iteration count;
reconstruct at least a portion of a mesh-frame using the vertex positions of the at least one subdivided submesh; and
create a compressed bitstream including information on the submesh, the subdivision iteration count, the number of vertices associated with the submesh, and the distortion information.

18 . The apparatus of claim 17 , wherein the processor is further configured to signal the number of vertices associated with the submesh and the distortion information as signaling elements.

19 . The apparatus of claim 18 , wherein the signaling elements are signaled as part of a Supplemental Enhancement Information (SEI) message.

20 . The apparatus of claim 17 , wherein the distortion information includes a distortion metric type including at least one of:
a point cloud based point-to-point (D1) metric; a point cloud based point-to-plane (D2) metric; a point cloud based peak signal-to-noise ratio (PSNR) metric; a rendered image based PSNR metric; and a perceptual based distortion metric.

Assignees

• Samsung Electronics Co Ltd

Inventors

• Lim Youngkwon
• Joshi Rajan Laxman
• Budagavi Madhukar

Classifications

• H04N19/184

  the unit being bits, e.g. of the compressed video stream · CPC title

• G06T17/205

  Re-meshing · CPC title

• G06T17/20

  Finite element generation, e.g. wire-frame surface description, {tesselation} · CPC title

• G06T9/001 Primary

  Model-based coding, e.g. wire frame · CPC title