# US 2026/0075245 A1 · Point cloud attribute compression with point cloud geometry decoupling

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

- Number: US 2026/0075245 A1
- Document ID: US20260075245A1
- Status: Published application
- Kind: A1
- Application number: 18/829,967
- Filed: 2024-09-10
- Published: 2026-03-12
- Earliest claimed: 2024-09-10
- Assignees: InterDigital VC Holdings, Inc.
- Applicants: InterDigital VC Holdings, Inc.
- Inventors: Yuning Huang; Jiahao Pang; Muhammad Asad Lodhi; Junghyun Ahn; Dong Tian
- Web page: https://patentgrep.com/patent/US20260075245A1

## CPC

- G06T 9/40: Tree coding, e.g. quadtree, octree
- H04N 19/597: specially adapted for multi-view video sequence encoding
- G06T 9/002: {using neural networks}
- G06T 9/005: {Statistical coding, e.g. Huffman, run length coding}
- H04N 19/136: Incoming video signal characteristics or properties
- H04N 19/169: characterised by the coding unit, i.e. the structural portion or semantic portion of the video signal being the object or the subject of the adaptive coding
- H04N 19/91: Entropy coding, e.g. variable length coding [VLC] or arithmetic coding
- H04N 19/96: Tree coding, e.g. quad-tree coding
- G06T 9/004: {Predictors, e.g. intraframe, interframe coding}
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

In one implementation, a method for reconstructing attributes of a point cloud is provided wherein a geometry feature map representative of a geometry of the point cloud is obtained, an attribute feature map is decoded from a bitstream, the attribute feature map being representative of attributes of points of the point cloud, and the decoded attribute feature map is updated with the geometry feature map. Attributes of points of the point cloud are reconstructed based on the updated decoded attribute feature map.

## Claims

### Claim 1

A method for reconstructing attributes of a point cloud, the method comprising:
obtaining a geometry feature map representative of a geometry of the point cloud,
decoding an attribute feature map from a bitstream, the attribute feature map being representative of attributes of points of the point cloud,
updating the decoded attribute feature map with the geometry feature map by providing the geometry feature map and the decoded attribute map to a neural network-based conditional feature decoder, and
reconstructing attributes of points of the point cloud based on the updated decoded attribute feature map.

### Claim 2 (depends on 1)

The method of claim 1, wherein the point cloud is represented with an octree structure, and wherein the attribute feature map represents voxel attributes at a current level in the octree structure of the point cloud.

### Claim 3 (depends on 2)

The method of claim 2, wherein a feature in the attribute feature map for a current voxel is representative of at least a set of voxels that are still to be reconstructed.

### Claim 4 (depends on 2)

The method of claim 2, wherein reconstructing attributes of points reconstructs voxel attributes at the current level in the octree structure and comprises:
determining an attribute probability of a current voxel based on the updated decoded attribute feature map, and
decoding attribute information for the current voxel based on the attribute probability determined for the current voxel.

### Claim 5 (depends on 2)

The method of claim 2, wherein reconstructing attributes of points reconstructs voxel attributes at the current level in the octree structure and comprises:
obtaining an attribute prediction for a current voxel from reconstructed voxel attributes at a previous level of the octree structure, and
reconstructing the attribute value for the current voxel based on the attribute prediction obtained for the current voxel and the updated decoded attribute feature map.

### Claim 6

(canceled)

### Claim 7 (depends on 1)

The method of claim 1, wherein the neural network-based conditional feature decoder comprises a concatenation layer that concatenates the decoded attribute feature map with the geometry feature map providing a concatenated feature map, and one or more convolutional layers that mix features of the concatenated feature map to output an updated decoded attribute feature map.

### Claim 8 (depends on 1)

The method of claim 1, wherein the decoded attribute feature map is updated with the geometry feature map and a predicted feature map obtained from a reference point cloud frame.

### Claim 9 (depends on 1)

The method of claim 1, wherein the geometry feature map is obtained as an output of a feature aggregator neural network that processes a decoded point cloud without attributes.

### Claim 10

An apparatus comprising one or more processors, coupled to a memory, the apparatus being configured to:
obtain a geometry feature map representative of a geometry of the point cloud,
decode an attribute feature map from a bitstream, the attribute feature map being representative of attributes of points of the point cloud,
update the decoded attribute feature map with the geometry feature map by providing the geometry feature map and the decoded attribute map to a neural network-based conditional feature decoder, and
reconstruct attributes of points of the point cloud based on the updated decoded attribute feature map.

### Claim 11

A method for encoding attributes of a current point cloud, the method comprising:
obtaining a geometry feature map representative of a geometry of the point cloud,
obtaining an attribute feature map, the attribute feature map being representative of attributes of points of the point cloud,
refining the attribute feature map with the geometry feature map by providing the geometry feature map and the attribute feature map to a neural network-based conditional feature encoder, and
encoding the refined attribute feature map.

### Claim 12 (depends on 11)

The method of claim 11, further comprising obtaining an updated attribute feature map from a decoded version of the refined attribute feature map and the geometry feature map, and encoding attributes of points of the point cloud based on the updated attribute feature map.

### Claim 13 (depends on 12)

The method of claim 12, wherein the point cloud is represented with an octree structure, and wherein the attribute feature map represents voxel attributes at a current level in the octree structure of the point cloud.

### Claim 14 (depends on 13)

The method of claim 13, wherein a feature in the attribute feature map for a current voxel is representative of at least a set of voxels that are still to be reconstructed.

### Claim 15 (depends on 13)

The method of claim 13, wherein encoding attributes of points of the point cloud encodes voxel attributes at the current level in the octree structure and comprises:
determining an attribute probability of a current voxel based on the updated attribute feature map, and
encoding attribute information for the current voxel based on the attribute probability determined for the current voxel.

### Claim 16

An apparatus comprising one or more processors, coupled to a memory, the apparatus being configured to:
obtain a geometry feature map representative of a geometry of a point cloud,
obtain an attribute feature map, the attribute feature map being representative of attributes of points of the point cloud,
refine the attribute feature map with the geometry feature map by providing the geometry feature map and the attribute feature map to a neural network-based conditional feature encoder, and
encode the refined attribute feature map.

### Claim 17 (depends on 10)

The apparatus of claim 10, wherein the neural-network-based conditional feature decoder comprises:
a concatenation layer that concatenates the decoded attribute feature map with the geometry feature map providing a concatenated feature map, and
one or more convolutional layers that mix features of the concatenated feature map to output an updated decoded attribute feature map.

### Claim 18 (depends on 10)

The apparatus of claim 10, wherein the geometry feature map is obtained as an output of a feature aggregator neural network that processes a decoded point cloud without attributes.

### Claim 19 (depends on 16)

The apparatus of claim 16, wherein the one or more processors are further configured to:
obtain an updated attribute feature map from a decoded version of the refined attribute feature map and the geometry feature map, and
encode attributes of points of the point cloud based on the updated attribute feature map.

### Claim 20 (depends on 19)

The apparatus of claim 19,
wherein the point cloud is represented with an octree structure, and
wherein the attribute feature map represents voxel attributes at a current level in the octree structure of the point cloud.
