Method and apparatus for point cloud compression

1. A method for point cloud encoding, comprising:

determining, from a point cloud, at least a first set of candidate source points that are associated with a target point in a geometry image reconstructed from a compressed geometry image for the point cloud;

weighting a color of a candidate source point in the first set based on a combination of a location difference between the candidate source point and the target point, and a color difference between the color of the candidate source point and an aggregate color of the first set of candidate source points;

determining a color of the target point based on a first weighted color average of the first set of candidate source points; and

encoding texture of the point cloud with the target point having the determined color.

2. The method of claim 1 , further comprising:

determining, from the point cloud, a second set of candidate source points that are associated with the target point;

weighting a color of a candidate source point in the second set based on a combination of a location difference between the candidate source point in the second set and the target point, and a color difference between the color of the candidate source point in the second set and an aggregate color of the second set of candidate source points;

determining the color of the target point based on the first weighted color average of the first set of candidate source points and a second weighed color average of the second set of candidate points.

3. The method of claim 2 , further comprising:

determining, from the point cloud, the first set of candidate source points that are nearest neighbors to the target point; and

determining, from the point cloud, the second set of candidate source points with the target point being one of the nearest neighbors to each of the candidate source points in the second set.

4. The method of claim 1 , further comprising:

calculating an Euclidean distance between the color of the candidate source point and the aggregate color of the first set of candidate source points in a color space as the color difference.

5. The method of claim 1 , further comprising:

weighting the color of the candidate source point in the first set based on an inverse of the location difference between the candidate source point in the first set and the target point, and an inverse of the color difference between the color of the candidate source point in the first set and the aggregate color of the first set of candidate source points.

6. The method of claim 5 , further comprising:

weighting the color of the candidate source point in the first set with a weight that is proportion to an inverse of an ascending function of the color difference between the color of the candidate source point in the first set and the aggregate color of the first set of candidate source points.

7. The method of claim 1 , further comprising:

determining the first set of candidate source points with a color variation smaller than a threshold.

8. The method of claim 7 , further comprising:

removing one or more candidate source points that are with a largest distance to the target point from the first set in response to a color deviation is larger than the threshold.

9. The method of claim 8 , further comprising:

removing the one or more candidate source points from the first set in response to the color deviation being larger than the threshold and based on a number of the candidate source points in the first set being larger than a specific limit.

10. The method of claim 8 , further comprising:

selecting one of the candidate source points in the first set with a closest distance to the target point in response to the color deviation being larger than the threshold and based on a number of the candidate source points in the first set being smaller than a specific limit.

11. An apparatus for point cloud encoding, comprising:

processing circuitry configured to:

determine, from a point cloud, at least a first set of candidate source points that are associated with a target point in a geometry image reconstructed from a compressed geometry image for the point cloud;

weight a color of a candidate source point in the first set based on a combination of a location difference between the candidate source point and the target point, and a color difference between the color of the candidate source point and an aggregate color of the first set of candidate source points;

determine a color of the target point based on a first weighted color average of the first set of candidate source points; and

encode texture of the point cloud with the target point having the determined color.

12. The apparatus of claim 11 , wherein the processing circuitry is configured to:

determine, from the point cloud, a second set of candidate source points that are associated with the target point;

weight a color of a candidate source point in the second set based on a combination of a location difference between the candidate source point in the second set and the target point, and a color difference between the color of the candidate source point in the second set and an aggregate color of the second set of candidate source points;

determine the color of the target point based on the first weighted color average of the first set of candidate source points and a second weighed color average of the second set of candidate points.

13. The apparatus of claim 12 , wherein the processing circuitry is configured to:

determine, from the point cloud, the first set of candidate source points that are nearest neighbors to the target point; and

determine, from the point cloud, the second set of candidate source points with the target point being one of the nearest neighbors to each of the candidate source points in the second set.

14. The apparatus of claim 11 , wherein the processing circuitry is configured to:

calculate an Euclidean distance between the color of the candidate source point and the aggregate color of the first set of candidate source points in a color space as the color difference.

15. The apparatus of claim 11 , wherein the processing circuitry is configured to:

weight the color of the candidate source point in the first set based on an inverse of the location difference between the candidate source point in the first set and the target point, and an inverse of the color difference between the color of the candidate source point in the first set and the aggregate color of the first set of candidate source points.

16. The apparatus of claim 15 , wherein the processing circuitry is configured to:

weight the color of the candidate source point in the first set with a weight that is proportion to an inverse of an ascending function of the color difference between the color of the candidate source point in the first set and the aggregate color of the first set of candidate source points.

17. The apparatus of claim 11 , wherein the processing circuitry is configured to:

determine the first set of candidate source points with a color variation smaller than a threshold.

18. The apparatus of claim 17 , wherein the processing circuitry is configured to:

remove one or more candidate source points that are with a largest distance to the target point from the first set in response to a color deviation is larger than the threshold.

19. The apparatus of claim 18 , wherein the processing circuitry is configured to:

remove the one or more candidate source points from the first set in response to the color deviation being larger than the threshold and based on a number of the candidate source points in the first set being larger than a specific limit.

20. The apparatus of claim 18 , wherein the processing circuitry is configured to:

select one of the candidate source points in the first set with a closest distance to the target point in response to the color deviation being larger than the threshold and based on a number of the candidate source points in the first set being smaller than a specific limit.