Granted Patent B2

US 12,423,874 · App. 17/944,994 · Granted Sep 23, 2025

Inventors: Xiang Zhang (Sunnyvale, CA); Shan Liu (San Jose, CA); Xiaozhong Xu (State College, PA); Chao Huang (Palo Alto, CA); Jun Tian (Belle Mead, NJ)

Assignee: Tencent America LLC

G06T9/001

Abstract

Claims (60)

1. A method for encoding mesh compression, comprising:

receiving a data structure for a mesh frame with polygons representing a surface of an object, the data structure for the mesh frame comprising a UV atlas that associates vertices of the mesh frame to UV coordinates in the UV atlas;

determining respective sampling rates for regions of the mesh frame according to respective characteristics of the regions of the mesh frame;

applying, on the UV atlas, the respective sampling rates for the regions of the mesh frame to determine sampling positions on the UV atlas;

generating one or more sampled two dimensional (2D) maps for the mesh frame according to the sampling positions on the UV atlas;

making a decision to signal a first sampling rate associated with a first region or to predict the first sampling rate; and

when the decision is to predict the first sampling rate,

encoding a first syntax, a second syntax, and the one or more sampled 2D maps into a bitstream, the first syntax indicating the decision and the second syntax indicating a predictor to use for predicting the first sampling rate.

2. The method of claim 1 , wherein the determining the respective sampling rates for the regions of the mesh frame comprises:

determining the first sampling rate for the first region of the mesh frame according to a requirement that limits a first number of sampling positions in the first region.

3. The method of claim 2 , wherein the determining the first sampling rate for the first region of the mesh frame comprises:

determining the first sampling rate to achieve an oversampling ratio (OR) that is closest to a target value, the OR being a ratio between the first number of sampling positions to a number of vertices originally in the first region of the mesh frame.

4. The method of claim 2 , wherein the determining the first sampling rate for the first region of the mesh frame comprises:

adjusting the first sampling rate until an oversampling ratio (OR) is smaller than a first threshold, the OR being a ratio between the first number of sampling positions to a number of vertices originally in the first region of the mesh frame.

5. The method of claim 2 , wherein the determining the first sampling rate for the first region of the mesh frame comprises:

adjusting the first sampling rate until an oversampling ratio (OR) is smaller than a first threshold and larger than a second threshold, the OR being a ratio between the first number of sampling positions to a number of vertices originally in the first region of the mesh frame.

6. The method of claim 1 , wherein a sampled 2D map of the one or more sampled 2D map comprises sampled regions with sampled points corresponding to the sampling positions on the UV atlas, and the method further comprises:

determining that a sampling position is occupied when the sampling position is in a polygon; and

determining an attribute of a sampled point in the sampled 2D map corresponding to the sampling position according to attributes of vertices of the polygon.

7. The method of claim 1 , wherein the generating the one or more sampled 2D maps further comprises:

forming sampled regions corresponding to the regions of the mesh based on the respective sampling rates of the regions of the mesh; and

placing the sampling regions in a non-overlapping configuration to form a sampled map.

8. The method of claim 7 , wherein the placing the sampling regions in the non-overlapping configuration further comprises:

after a subset of the sampled regions are placed in the non-overlapping configuration,

determining, for a current sampled region, an initial placement position according to a sampling rate of the current sampled region; and

determining, whether the current sampled region at the initial placement position overlaps with the subset of the sampled regions.

9. The method of claim 8 , further comprising:

determining an offset to the initial placement position when the current sampled region at the initial placement position overlaps with the subset of the sampled regions, the offset allowing the current sampled region to be non-overlapped with the subset of the sampled regions.

10. The method of claim 7 , wherein the non-overlapping configuration comprises a minimum distance requirement between the sampled regions.

11. The method of claim 1 , further comprising at least one of:

encoding a value of the first sampling rate for the first region directly into the bitstream;

encoding a first index into the bitstream, the first index indicating a selection of the first sampling rate from a set of sampling rates;

encoding the second syntax indicating the predictor for predicting the first sampling rate from a pre-established set of sampling rates;

encoding the second syntax indicating the predictor for predicting the first sampling rate from a previously used sampling rate for an encoded region of the mesh frame; and

encoding the second syntax indicating the predictor for predicting the first sampling rate from a previously used sampling rate for an encoded region in another mesh frame encoded prior to the mesh frame.

12. The method of claim 1 , wherein when the decision is to signal the first sampling rate, the method comprises at least one of:

encoding a value of the first sampling rate directly into the bitstream; and

encoding a third index into the bitstream, the third index indicating a selection of the first sampling rate from a set of sampling rates.

13. The method of claim 1 , further comprising:

encoding a prediction residual into the bitstream, the prediction residual being a difference between the first sampling rate and a sampling rate of the predictor.

14. The method of claim 1 , further comprising:

encoding a base sampling rate into the bitstream.

15. The method of claim 1 , further comprising:

encoding a control flag that indicates an enable/disable of an adaptive 2D atlas sampling.

16. The method of claim 1 , further comprising:

determining, at least a first UV offset associated with the first region of the mesh frame, the first UV offset being applied to a first sampled region corresponding to the first region to avoid overlapping with other sampled regions; and

encoding a third syntax indicating the first UV offset into the bitstream.

17. The method of claim 16 , wherein the encoding the third syntax further comprises at least one of:

encoding the third syntax having a value of the first UV offset into the bitstream;

encoding the third syntax indicating a predictor for predicting the first UV offset based on a pre-established set of UV offsets;

encoding the third syntax indicating a predictor for predicting the first UV offset based on a previously used UV offset for an encoded region of the mesh frame; and

encoding the third syntax indicting a predictor for predicting the first UV offset based on a previously used UV offset for an encoded region in another mesh frame encoded prior to the mesh frame.

18. An apparatus for encoding mesh compression, comprising processing circuitry configured to:

receive a data structure for a mesh frame with polygons representing a surface of an object, the data structure for the mesh frame comprising a UV atlas that associates vertices of the mesh frame to UV coordinates in the UV atlas;

determine respective sampling rates for regions of the mesh frame according to respective characteristics of the regions of the mesh frame;

apply, on the UV atlas, the respective sampling rates for the regions of the mesh frame to determine sampling positions on the UV atlas;

generate one or more sampled two dimensional (2D) maps for the mesh frame according to the sampling positions on the UV atlas;

make a decision to signal a first sampling rate associated with a first region or to predict the first sampling rate; and

when the decision is to predict the first sampling rate,

encode a first syntax, a second syntax, and the one or more sampled 2D maps into a bitstream, the first syntax indicating the decision and the second syntax indicating a predictor to use for predicting the first sampling rate.

Assignments (1)

Continuity (3)

References Cited (18)