# US 12,646,222 B2 · State summarization for binary voxel grid coding

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 12,646,222 B2
- Document ID: US12646222B2
- Status: Granted
- Kind: B2
- Application number: 18/706,208
- Filed: 2022-10-18
- Published: 2025-01-09
- Granted: 2026-06-02
- Earliest claimed: 2021-11-04
- Assignees: InterDigital Patent Holdings, Inc.
- Applicants: InterDigital Patent Holdings, Inc.
- Inventors: Maurice Quach; Jiahao Pang; Muhammad Asad Lodhi; Dong Tian; Giuseppe Valenzise; Frederic Dufaux
- Web page: https://patentgrep.com/patent/US12646222B2

## CPC

- G06T 9/001: {Model-based coding, e.g. wire frame}
- G06T 9/002: {using neural networks}
- G06T 9/005: {Statistical coding, e.g. Huffman, run length coding}
- G06T 9/40: Tree coding, e.g. quadtree, octree
- H04N 19/91: Entropy coding, e.g. variable length coding [VLC] or arithmetic coding
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

In one implementation, we improve the binary voxel-based octree coding method, via a proposed state summarization module for context modeling. Given a current voxel to be encoded or decoded, instead of directly estimating its occupancy probability based on the associated binary occupancy context, a proposed state summarization module is applied to convert the original binary context to a summarized representation. Under the summarized representation, the estimation of the occupancy probability becomes more affordable and effective. In particular, density-based state summarization, pattern-based, learning-based state summarization, and learning-based state summarization methods are provided.

## Claims

### Claim 1

An apparatus for encoding point cloud data, comprising:
at least one processor configured for
determining a first set of a first number of states associated with an occupancy state for each of a plurality of encoded voxels neighboring a current voxel, wherein the current voxel and the plurality of neighboring encoded voxels are in a point cloud represented by the point cloud data;
determining a density of occupied voxels in the plurality of neighboring encoded voxels;
processing the first set of states to obtain a second set of a second number of states, based on the density of occupied voxels in the plurality of neighboring encoded voxels;
predicting, based on the second set of states, a probability for an occupancy state for the current voxel; and
encoding the occupancy state for the current voxel, based on said predicted probability for the occupancy state for the current voxel.

### Claim 2 (depends on 1)

The apparatus of claim 1, wherein processing the first set of states comprises converting the first set of states to a summarized state space having the second number of states.

### Claim 3 (depends on 1)

The apparatus of claim 1, wherein determining the density of occupied voxels comprises:
classifying the voxels neighboring the current voxel into one or more classes of neighboring voxels based on a distance from each neighboring voxel to the current voxel; and
determining a number of occupied neighboring voxels included in each of the one or more classes of neighboring voxels.

### Claim 4 (depends on 2)

The apparatus of claim 2, wherein converting the first set of states to the summarized state space comprises determining that one or more of a set of patterns exists in a voxel neighborhood comprising the plurality of neighboring voxels.

### Claim 5 (depends on 1)

The apparatus of claim 1, wherein processing the first set of states comprises applying a neural network including a plurality of point-based MLP layers.

### Claim 6 (depends on 1)

The apparatus of claim 1, wherein processing the first set of states comprises applying a first neural network including a plurality of convolutional layers and a second neural network including a plurality of point-based MLP layers, wherein outputs from said first and second neural networks are concatenated.

### Claim 7

A method for encoding point cloud data, comprising:
determining a first set of a first number of states associated with an occupancy state for each of a plurality of encoded voxels neighboring a current voxel, wherein the current voxel and the plurality of encoded neighboring voxels are in a point cloud represented by point cloud data;
determining a density of occupied voxels in the plurality of neighboring encoded voxels;
processing the first set of states to obtain a second set of a second number of states, based on the density of occupied voxels in the plurality of neighboring encoded voxels;
predicting, based on the second set of states, a probability for an occupancy state for the current voxel; and
encoding the occupancy state for the current voxel, based on said predicted probability for the occupancy state for the current voxel.

### Claim 8 (depends on 7)

The method of claim 7, wherein determining the density of occupied voxels comprises:
classifying the voxels neighboring the current voxel into one or more classes of neighboring voxels based on a distance from each neighboring voxel to the current voxel; and
determining a number of occupied neighboring voxels included in each of the one or more classes of neighboring voxels.

### Claim 9 (depends on 7)

The method of claim 7, wherein processing the first set of states comprises converting the first set of states to a summarized state space having the second number of states.

### Claim 10 (depends on 9)

The method of claim 9, wherein converting the first set of states to the summarized state space comprises determining that one or more of a set of patterns exists in a voxel neighborhood comprising the plurality of neighboring voxels.

### Claim 11 (depends on 7)

The method of claim 7, wherein processing the first set of states comprises applying a neural network including a plurality of point-based MLP layers.

### Claim 12 (depends on 7)

The method of claim 7, wherein processing the first set of states comprises applying a first neural network including a plurality of convolutional layers and a second neural network including a plurality of point-based MLP layers, wherein outputs from said first and second neural networks are concatenated.

### Claim 13

An apparatus for decoding point cloud data, comprising:
at least one processor configured for
determining a first set of a first number of states associated with an occupancy state for each of a plurality of decoded voxels neighboring a current voxel, wherein the current voxel and the plurality of neighboring decoded voxels are in a point cloud represented by the point cloud data;
determining a density of occupied voxels in the plurality of neighboring encoded voxels;
processing the first set of states to obtain a second set of a second number of states, based on the density of occupied voxels in the plurality of neighboring encoded voxels;
predicting, based on the second set of states, a probability for an occupancy state for the current voxel; and
decoding the occupancy state for the current voxel, based on said predicted probability for the occupancy state for the current voxel.

### Claim 14 (depends on 13)

The apparatus of claim 13, wherein processing the first set of states comprises converting the first set of states to a summarized state space having the second number of states.

### Claim 15 (depends on 14)

The apparatus of claim 14, wherein converting the first set of states to the summarized state space comprises determining that one or more of a set of patterns exists in a voxel neighborhood comprising the plurality of neighboring voxels.

### Claim 16 (depends on 13)

The apparatus of claim 13, wherein processing the first set of states comprises applying a neural network including a plurality of point-based MLP layers.

### Claim 17

A method for decoding point cloud data, comprising:
determining a first set of a first number of states associated with an occupancy state for each of a plurality of decoded voxels neighboring a current voxel, wherein the current voxel and the plurality of decoded neighboring voxels are in a point cloud represented by the point cloud data;
determining a density of occupied voxels in the plurality of neighboring encoded voxels;
processing the first set of states to obtain a second set of a second number of states, based on the density of occupied voxels in the plurality of neighboring encoded voxels;
predicting, based on the second set of states, a probability for an occupancy state for the current voxel; and
decoding the occupancy state for the current voxel, based on said predicted probability for the occupancy state for the current voxel.

### Claim 18 (depends on 17)

The method of claim 17, wherein processing the first set of states comprises converting the first set of states to a summarized state space having the second number of states.

### Claim 19 (depends on 18)

The method of claim 18, wherein converting the first set of states to the summarized state space comprises determining that one or more of a set of patterns exists in a voxel neighborhood comprising the plurality of neighboring voxels.

### Claim 20 (depends on 17)

The method of claim 17, wherein processing the first set of states comprises applying a neural network including a plurality of point-based MLP layers.