Context modeling of occupancy coding for point cloud coding

1. A method for coding information of a point cloud, the method performed by at least one processor and comprising:

obtaining the point cloud including a set of points in a three-dimensional space;

partitioning the point cloud into a plurality of objects using hybrid partitioning schemes and generating occupancy information for each of the plurality of objects; and

encoding the occupancy information of a current object by taking into account a distance between a plurality of neighboring objects, the plurality of the neighboring objects being of a same size as the current object, wherein the occupancy information of the current object is encoded using a context index based on a number of occupied objects and a number of classifications of the plurality of the neighboring objects of the plurality of objects.

2. The method of claim 1 , wherein the encoding of the occupancy information is performed on an object-by-object basis such that a next piece of occupancy information to be encoded is encoded based on a classification of the plurality of the neighboring objects of the plurality of objects, which are classified based on the distance between the plurality of objects.

3. The method of claim 1 , wherein the occupancy information is encoded using a context index defined by a look-up-table using a formula: LUT {ctxIdx} {ctxIdxChild}, wherein LUT is the look-up-table, ctxIdx is a node of the plurality of objects, and ctxIdxChild is a sub-node of the plurality of objects.

4. The method of claim 1 , wherein, based on a depth-first traversal being applied, the occupancy information of the current object is based on a partial context index, wherein the partial context index is based on the occupancy information of a subset of the plurality of the neighboring objects that are encoded prior to the current object.

5. The method of claim 4 , wherein the plurality of objects includes objects of different sizes.

6. The method of claim 1 , wherein the distance between the plurality of the neighboring objects is measured using a different traversal order.

7. The method of claim 5 , wherein the encoding of the occupancy information takes into account different sizes of the plurality of objects.

8. The method of claim 1 , wherein the encoding of the occupancy information is performed on an object-by-object basis such that a next piece of occupancy information to be encoded is encoded based on a classification of surrounding objects, of the plurality of objects, which are already encoded, and which are classified based on the distance between the plurality of objects.

9. The method of claim 1 , wherein, based on a breadth-first traversal being applied, a coding order for the encoded occupancy information is specified at the beginning of a partition depth.

10. An apparatus for coding information of a point cloud, the apparatus comprising:

at least one memory configured to store program code; and

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

obtaining code configured to obtain the point cloud including a set of points in a three-dimensional space;

partitioning code configured to partition the point cloud into a plurality of objects using hybrid partitioning schemes and generate occupancy information for each of the plurality of objects; and

encoding code configured to encode the occupancy information of a current object by taking into account a distance between a plurality of neighboring objects, the plurality of the neighboring objects being of a same size as the current object, wherein the occupancy information of the current object is encoded using a context index based on a number of occupied objects and a number of classifications of the plurality of the neighboring objects of the plurality of objects.

11. The apparatus of claim 10 , wherein the encoding code is configured to encode the occupancy information on an object-by-object basis such that a next piece of occupancy information to be encoded is encoded based on a classification of the plurality of the neighboring objects of the plurality of objects, which are classified based on the distance between the plurality of objects.

12. The apparatus of claim 10 , wherein the encoding code is configured to encode the occupancy information using a context index defined by a look-up-table using a formula: LUT{ctxIdx} {ctxIdxChild}, wherein LUT is the look-up-table, ctxIdx is a node of the plurality of objects, and ctxIdxChild is a sub-node of the plurality of objects.

13. The apparatus of claim 10 , wherein, based on a depth-first traversal being applied, the occupancy information of the current object is based on a partial context index, wherein the partial context index is based on the occupancy information of a subset of the plurality of the neighboring objects that are encoded prior to the current object.

14. The apparatus of claim 13 , wherein the plurality of objects includes objects of different sizes.

15. The apparatus of claim 10 , wherein the distance between the plurality of the neighboring objects is measured using a different traversal order.

16. The apparatus of claim 14 , wherein the encoding code is configured to encode the occupancy information by taking into account different sizes of the plurality of objects.

17. The apparatus of claim 10 , wherein the encoding code is configured to encode the occupancy information on an object-by-object basis such that a next piece of occupancy information to be encoded is encoded based on a classification of surrounding objects, of the plurality of objects, which are already encoded, and which are classified based on the distance between the plurality of objects.

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

obtain a point cloud including a set of points in a three-dimensional space;

partition the point cloud into a plurality of objects using hybrid partitioning schemes and generating occupancy information for each of the plurality of objects; and

encode the occupancy information of a current object by taking into account a distance between a plurality of neighboring objects, the plurality of the neighboring objects being of a same size as the current object, wherein the occupancy information of the current object is encoded using a context index based on a number of occupied objects and a number of classifications of the plurality of the neighboring objects of the plurality of objects.