Granted Patent B2

US 12,530,813 · App. 18/725,355 · Granted Jan 20, 2026

Inventors: Vladyslav Zakharchenko (Palo Alto, CA); Yue Yu (Palo Alto, CA); Haoping Yu (Palo Alto, CA)

Assignee: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS CORP., LTD.

G06T9/001G06T9/20G06T17/20G06T17/205G06T2210/36G06T2210/56

Abstract

Claims (66)

1 . A computer-implemented method for decoding a coded mesh bitstream of a dynamic mesh representing three-dimensional (3D) content, the method comprising:

reconstructing geometry information of the dynamic mesh from a geometry component bitstream in the coded mesh bitstream, the reconstructed geometry information comprising data specifying a plurality of vertices of the dynamic mesh;

reconstructing connectivity information of the dynamic mesh from a connectivity component bitstream in the coded mesh bitstream, the reconstructed connectivity information comprising data specifying a plurality of faces of the dynamic mesh;

refining the reconstructed connectivity information based on the reconstructed geometry information to generate refined connectivity information;

reconstructing an attribute image of the dynamic mesh from an attribute component bitstream in the coded mesh bitstream, the reconstructed attribute image comprising image content to be applied to faces of the dynamic mesh;

refining the reconstructed attribute image based on the reconstructed geometry information to generate refined attribute image;

reconstructing the dynamic mesh based, at least in part, upon the reconstructed geometry information, the refined connectivity information, and the refined attribute image; and

causing the reconstructed dynamic mesh to be rendered for display,

wherein refining the reconstructed connectivity information based on the reconstructed geometry information to generate refined connectivity information comprises dividing a face out of the plurality of faces specified by the reconstructed connectivity information into two faces based on a vertex of the plurality of vertices specified in the reconstructed geometry information.

2 . The computer-implemented method of claim 1 , wherein refining the reconstructed connectivity information based on the reconstructed geometry information comprises:

identifying a vertex of the plurality of vertices that is located inside a face of the plurality of faces;

determining a projected vertex of the vertex on an edge of the face; and

dividing the face into two refined faces, each refined face has the projected vertex as one vertex.

3 . The computer-implemented method of claim 2 , wherein refining the reconstructed attribute image based on the reconstructed geometry information to generate refined attribute image comprises:

determining a transformation based on the vertex and the projected vertex; and

applying an inverse of the transformation to a face in the reconstructed attribute image that corresponds to the face.

4 . The computer-implemented method of claim 3 , wherein the transformation is one of an affine transformation or an interpolation transformation.

5 . The computer-implemented method of claim 4 , wherein parameters of the interpolation transformation are signaled in the coded mesh bitstream.

6 . The computer-implemented method of claim 4 , wherein parameters of the affine transformation are determined based on the vertex and the projected vertex.

7 . The computer-implemented method of claim 1 , further comprising:

reconstructing mapping information of the dynamic mesh from a mapping component bitstream in the coded mesh bitstream, the reconstructed mapping information comprising data specifying a list of vertex attribute coordinates in the attribute image; and

refining the reconstructed mapping information based on the reconstructed geometry information to generate refined mapping information, wherein reconstructing the dynamic mesh is further based on the refined mapping information.

8 . A system comprising:

a processor; and

a non-transitory computer-readable medium communicatively coupled to the processor, wherein the processor is configured to execute program code stored in the non-transitory computer-readable medium and thereby perform operations comprising:

reconstructing geometry information of a dynamic mesh from a geometry component bitstream in a coded mesh bitstream of the dynamic mesh, the reconstructed geometry information comprising data specifying a plurality of vertices of the dynamic mesh;

reconstructing connectivity information of the dynamic mesh from a connectivity component bitstream in the coded mesh bitstream, the reconstructed connectivity information comprising data specifying a plurality of faces of the dynamic mesh;

refining the reconstructed connectivity information based on the reconstructed geometry information to generate refined connectivity information;

reconstructing an attribute image of the dynamic mesh from an attribute component bitstream in the coded mesh bitstream, the reconstructed attribute image comprising image content to be applied to faces of the dynamic mesh;

refining the reconstructed attribute image based on the reconstructed geometry information to generate refined attribute image;

reconstructing the dynamic mesh based, at least in part, upon the reconstructed geometry information, the refined connectivity information, and the refined attribute image; and

causing the reconstructed dynamic mesh to be rendered for display,

wherein refining the reconstructed connectivity information based on the reconstructed geometry information to generate refined connectivity information comprises dividing a face out of the plurality of faces specified by the reconstructed connectivity information into two faces based on a vertex of the plurality of vertices specified in the reconstructed geometry information.

9 . The system of claim 8 , wherein refining the reconstructed connectivity information based on the reconstructed geometry information comprises:

identifying a vertex of the plurality of vertices that is located inside a face of the plurality of faces;

determining a projected vertex of the vertex on an edge of the face; and

dividing the face into two refined faces, each refined face has the projected vertex as one vertex.

10 . The system of claim 9 , wherein refining the reconstructed attribute image based on the reconstructed geometry information to generate refined attribute image comprises:

determining a transformation based on the vertex and the projected vertex; and

applying an inverse of the transformation to a face in the reconstructed attribute image that corresponds to the face.

11 . A computer-implemented method for encoding three-dimensional (3D) content represented by a dynamic mesh, the method comprising:

converting geometry information from a list of vertices of the dynamic mesh to a sequence of geometry component images;

encoding the sequence of geometry component images of the dynamic mesh using a video encoder to generate a geometry component bitstream;

decoding the geometry component bitstream to generate reconstructed geometry component images;

determining a face to be removed from connectivity component images of the dynamic mesh, the face containing a vertex in the reconstructed geometry component images;

updating the connectivity component images of the dynamic mesh by removing the face from the connectivity component images;

encoding the updated connectivity component images to generate a connectivity component bitstream;

updating, based on updating the connectivity component images, mapping component images of the dynamic mesh;

encoding the updated mapping component images to generate a mapping component bitstream; and

generating a coded mesh bitstream by including at least the geometry component bitstream, the connectivity component bitstream, and the mapping component bitstream,

wherein determining the face to be removed from connectivity component images of the dynamic mesh comprises:

accessing four vertices of two neighboring faces of the dynamic mesh described by the reconstructed geometry component images;

identifying a first vertex of the four vertices based on a distance of the first vertex to an edge formed by a second vertex and a third vertex of the four vertices;

determining that a first orientation of a first face of the two neighboring faces is the same as a second orientation of a second face of the two neighboring faces; and

in response to determining that the first orientation is the same as the second orientation, determining that the first face and the second face containing the first vertex are to be removed from the connectivity component images.

12 . The computer-implemented method of claim 11 , wherein updating the connectivity component images of the dynamic mesh further comprises merging the two neighboring faces into one face specified by the second vertex, the third vertex and a fourth vertex of the four vertices.

13 . The computer-implemented method of claim 12 , wherein updating the mapping component images comprises:

identifying a mapping sample of the mapping component images associated with the first vertex;

determining a transformation filter based on the first vertex and a vertex in the list of vertices that corresponds to the first vertex; and

applying the transformation filter to a first mapping sample and the mapping sample associated with the first vertex.

14 . The computer-implemented method of claim 11 , wherein:

encoding the geometry component images is performed via lossy video encoding.

15 . The computer-implemented method of claim 11 , wherein:

encoding the updated connectivity component images is performed via lossless video encoding.

16 . The computer-implemented method of claim 11 , wherein:

encoding the updated mapping component images is performed via lossless video encoding.

Assignments (1)

Continuity (4)

References Cited (28)

Cited By (1)

US 12,718,418