Hash-based attribute prediction for point cloud coding

1. A method of point cloud coding, executable by a processor, comprising:

receiving data corresponding to a point cloud;

reconstructing hash elements corresponding to attribute values associated with the received data, wherein the reconstruction is based on hash elements corresponding to attribute values at an octree partition level; and

decoding the data corresponding to the point cloud based on the reconstructed hash elements.

2. The method of claim 1 , further comprising decreasing a size of a hash table based on deleting one or more of the hash elements corresponding to non-border regions associated with the attribute values.

3. The method of claim 2 , wherein a maximum size of the hash table is defined for the data corresponding to the point cloud.

4. The method of claim 3 , wherein the maximum size is signaled in a sequence parameter set, a geometry parameter set, or a slice header.

5. The method of claim 3 , wherein the hash table is decreased by removing partial elements from the hash table based on the hash table reaching the maximum size.

6. The method of claim 2 , wherein the hash table is decreased based on a Morton order associated with the hash elements.

7. The method of claim 2 , wherein a boundary size associated with the one or more neighboring nodes is signaled in a sequence parameter set, a geometry parameter set, or a slice header.

8. A computer system for point cloud coding, the computer system comprising:

one or more computer-readable non-transitory storage media configured to store computer program code; and

one or more computer processors configured to access said computer program code and operate as instructed by said computer program code, said computer program code including:

receiving code configured to cause the one or more computer processors to receive data corresponding to a point cloud;

reconstructing code configured to cause the one or more computer processors to reconstruct hash elements corresponding to attribute values associated with the received data, wherein the reconstruction is based on hash elements corresponding to attribute values at an octree partition level; and

decoding code configured to cause the one or more computer processors to decode the data corresponding to the point cloud based on the reconstructed hash elements.

9. The computer system of claim 8 , further comprising decreasing code configured to cause the one or more computer processors to decrease a size of a hash table based on deleting one or more of the hash elements corresponding to non-border regions associated with the attribute values.

10. The computer system of claim 9 , wherein a maximum size of the hash table is defined for the data corresponding to the point cloud.

11. The computer system of claim 10 , wherein the maximum size is signaled in a sequence parameter set, a geometry parameter set, or a slice header.

12. The computer system of claim 10 , wherein the hash table is decreased by removing partial elements from the hash table based on the hash table reaching the maximum size.

13. The computer system of claim 9 , wherein the hash table is decreased based on a Morton order associated with the hash elements.

14. The computer system of claim 8 , wherein a boundary size associated with the one or more neighboring nodes is signaled in a sequence parameter set, a geometry parameter set, or a slice header.

15. A non-transitory computer readable medium having stored thereon a computer program for point cloud coding, the computer program configured to cause one or more computer processors to:

receive data corresponding to a point cloud;

reconstruct hash elements corresponding to attribute values associated with the received data, wherein the reconstruction is based on hash elements corresponding to attribute values at an octree partition level; and

decode the data corresponding to the point cloud based on the reconstructed hash elements.

16. The computer readable medium of claim 15 , wherein the computer program is further configured to cause one or more computer processors to decrease a size of a hash table based on deleting one or more of the hash elements corresponding to non-border regions associated with the attribute values.

17. The computer readable medium of claim 16 , wherein a maximum size of the hash table is defined for the data corresponding to the point cloud.

18. The computer readable medium of claim 17 , wherein the maximum size is signaled in a sequence parameter set, a geometry parameter set, or a slice header.

19. The computer readable medium of claim 17 , wherein the hash table is decreased by removing partial elements from the hash table based on the hash table reaching the maximum size.

20. The computer readable medium of claim 16 , wherein the hash table is decreased based on a Morton order associated with the hash elements.