Techniques and apparatus for interframe point cloud attribute coding

1. A method of point cloud attribute coding, the method being performed by at least one processor, comprising:

calculating a motion-estimating uncertainty value based on geometry data associated with a point cloud;

identifying one or more inter-frame nearest neighbor point cloud samples corresponding to the point cloud in response to a determination that the motion-estimating uncertainty value is less than a threshold value;

ranking one or more temporal candidate points associated with the one or more identified inter-frame nearest neighbor point cloud samples based on the motion-estimation uncertainty value; and

extracting one or more sample attribute values from the one or more temporal candidate points, wherein the one or more sample attribute values correspond to the geometry data.

2. The method of claim 1 , further comprising:

disabling identification of one or more inter-frame nearest neighbor point cloud samples based on a determination that the motion-estimating uncertainty value exceeds the threshold value.

3. The method of claim 1 , wherein the identifying the one or more inter-frame nearest neighbor point cloud samples comprises:

determining that one or more candidate nearest neighbor point cloud samples are inter-frame samples;

determining a maximum allowable number of frames corresponding to an offset between the point cloud and the candidate nearest neighbor point cloud samples;

calculating a degree of change between the point cloud and the candidate nearest neighbor point cloud samples; and

selecting one or more of the candidate inter-frame nearest neighbor point cloud samples having a lowest offset and a lowest degree of change.

4. The method of claim 3 , wherein the identifying the one or more inter-frame nearest neighbor point cloud samples further comprises reordering the selected nearest neighbor point cloud samples based on the motion-estimating uncertainty value.

5. The method of claim 1 , wherein the temporal candidate point having a shortest temporal distance from the point cloud is ranked highest.

6. The method of claim 1 , wherein based on a determination that the motion-estimation uncertainty value is higher than the threshold value, the inter-frame point cloud sample is excluded from the weighted average.

7. The method of claim 1 , further comprising calculating a distance-weighted average of an attribute value associated with the first point cloud, the one or more inter-frame nearest neighbor point cloud samples, and one or more intra-frame nearest neighbor sample values.

8. An apparatus for point cloud attribute coding, the apparatus comprising:

at least one memory configured to store computer program code; and

at least one processor configured to access the at least one memory and operate according to the computer program code, the computer program code comprising:

calculating code configured to cause the at least one processor to calculate a motion-estimating uncertainty value based on geometry data associated with a point cloud;

identifying code configured to cause the at least one processor to identify one or more inter-frame nearest neighbor point cloud samples corresponding to the point cloud in response to a determination that the motion-estimating uncertainty value is less than a threshold value;

ranking code configured to cause the at least one processor to rank one or more temporal candidate points associated with the one or more identified inter-frame nearest neighbor point cloud samples based on the motion-estimation uncertainty value; and

extracting code configured to cause the at least one processor to extract one or more sample attribute values from the one or more temporal candidate points, wherein the one or more sample attribute values correspond to the geometry data.

9. The apparatus of claim 8 , further comprising:

disabling code configured to cause the at least one processor to disable identification of one or more inter-frame nearest neighbor point cloud samples based on a determination that the motion-estimating uncertainty value exceeds the threshold value.

10. The apparatus of claim 8 , wherein the identifying code comprises:

first determining code configured to cause the at least one processor to determine that one or more candidate nearest neighbor point cloud samples are inter-frame samples;

second determining code configured to cause the at least one processor to determine a maximum allowable number of frames corresponding to an offset between the point cloud and the candidate nearest neighbor point cloud samples;

calculating code configured to cause the at least one processor to calculate a degree of change between the point cloud and the candidate nearest neighbor point cloud samples; and

selecting code configured to cause the at least one processor to select one or more of the candidate inter-frame nearest neighbor point cloud samples having a lowest offset and a lowest degree of change.

11. The apparatus of claim 10 , wherein the identifying code further comprises:

reordering code configured to cause the at least one processor to reorder the selected nearest neighbor point cloud samples based on the motion-estimating uncertainty value.

12. The apparatus of claim 8 , wherein the temporal candidate point having a shortest temporal distance from the point cloud is ranked highest.

13. The apparatus of claim 8 , wherein based on a determination that the motion-estimation uncertainty value is higher than the threshold value, the inter-frame point cloud sample is excluded from the weighted average.

14. The apparatus of claim 8 , further comprising:

calculating code configured to cause the at least one processor to calculate a distance-weighted average of an attribute value associated with the first point cloud, the one or more inter-frame nearest neighbor point clouds, and one or more intra-frame nearest neighbor sample values.

15. A non-transitory computer-readable storage medium storing instructions that cause at least one processor to:

calculate a motion-estimating uncertainty value based on geometry data associated with a point cloud;

identify one or more inter-frame nearest neighbor point clouds corresponding to the point cloud in response to a determination that the motion-estimating uncertainty value is less than a threshold value;

rank one or more temporal candidate points associated with the one or more identified inter-frame nearest neighbor point clouds; and

extract one or more sample attribute values from the one or more temporal candidate points, wherein the one or more sample attribute values correspond to the geometry data.

16. The computer-readable storage medium of claim 15 , wherein the instructions further cause the at least one processor to:

disable identification of one or more inter-frame nearest neighbor point cloud samples based on a determination that the motion-estimating uncertainty value exceeds the threshold value.

17. The computer-readable storage medium of claim 15 , wherein the instructions that cause the at least one processor to identify the one or more inter-frame nearest neighbor point cloud samples comprises instructions that cause at least one processor to:

determine that one or more candidate nearest neighbor point cloud samples are inter-frame samples;

determine a maximum allowable number of frames corresponding to an offset between the point cloud and the candidate nearest neighbor point cloud samples;

calculate a degree of change between the point cloud and the candidate nearest neighbor point cloud samples; and

select one or more of the candidate inter-frame nearest neighbor point cloud samples having a lowest offset and a lowest degree of change.

18. The computer-readable storage medium of claim 17 , wherein the instructions that cause the at least one processor to identify the one or more inter-frame nearest neighbor point cloud samples further comprises instructions that cause the at least one processor to reorder the selected nearest neighbor point cloud samples based on the motion-estimating uncertainty value.

19. The computer-readable storage medium of claim 15 , wherein the temporal candidate point having a shortest temporal distance from the point cloud is ranked highest.

20. The computer-readable storage medium of claim 15 , wherein based on a determination that the motion-estimation uncertainty value is higher than the threshold value, the inter-frame point cloud sample is excluded from the weighted average.