# US 2026/0065596 A1 · Extracting connected object components for deduplication in three dimensional content creation and scene rendering

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

- Number: US 2026/0065596 A1
- Document ID: US20260065596A1
- Status: Published application
- Kind: A1
- Application number: 18/821,549
- Filed: 2024-08-30
- Published: 2026-03-05
- Earliest claimed: 2024-08-30
- Assignees: NVIDIA Corporation
- Applicants: Nvidia Corporation
- Inventors: Pascal Gautron
- Web page: https://patentgrep.com/patent/US20260065596A1

## CPC

- G06T 17/205: {Re-meshing}
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

Approaches presented herein provide systems and methods to identify connected components within an object using an assigned label. The assigned label may be propagated through a number of connected components to identify a number of components having the same assigned label. Index values for the assigned labels may also be identified within a memory buffer to determine a range within the buffer for the connected component and to group and store each of the individual component within a contiguous sequence.

## Claims

### Claim 1

A computer-implemented method, comprising:
replacing one or more first vertex values of a first set of vertex values with a primary vertex value, the first set of vertex values corresponding to a first primitive of a representation of an object;
determining that one or more second vertex values of a second set of vertex values are different from the primary vertex value, the second set of vertex values corresponding to a second forming the object and sharing at least one vertex with the first component, that one or more second vertex values for the second set of vertex values are different from the primary vertex value;
replacing the one or more second vertex values with the primary vertex value; and
grouping the first component and second component as a common component for use in rendering a representation of the object.

### Claim 2 (depends on 1)

The computer-implemented method of claim 1, further comprising:
increasing a change counter after replacing the one or more first vertex values for the first set of vertex values.

### Claim 3 (depends on 2)

The computer-implemented method of claim 2, further comprising:
determining the change counter has a non-zero value;
resetting the change counter to zero; and
replacing one or more third vertex values for a third set of vertex values with the primary vertex value, the third set of vertex values corresponding to a third primitive of the representation of the object.

### Claim 4 (depends on 1)

The computer-implemented method of claim 1, further comprising:
determining a first index value for the first primitive;
determining a second index value for the second primitive; and
generating a continuous range within an index buffer for the first primitive and the second primitive.

### Claim 5 (depends on 1)

The computer-implemented method of claim 1, further comprising:
extracting the representation of the object from a mesh that represents a plurality of objects.

### Claim 6 (depends on 1)

The computer-implemented method of claim 1, wherein the representation of the object comprises a triangular mesh.

### Claim 7 (depends on 1)

The computer-implemented method of claim 1, further comprising:
receiving the representation of the object; and
assigning a unique location for at least one vertex location within a buffer.

### Claim 8 (depends on 7)

The computer-implemented method of claim 7, wherein the one or more first vertex values are labels that are disconnected from underlying geometric properties of the respective vertices.

### Claim 9

A processor, comprising:
one or more circuits to:
assign a selected value to a first set of vertex values for each vertex in a first set of vertices corresponding to a first primitive of an object;
determine a second set of vertices corresponding to a second primitive of the object including at least one common vertex with the first set of vertices;
assign the selected value to each vertex value in the second set of vertices; and
store the first primitive and the second primitive in a buffer with a common index label.

### Claim 10 (depends on 9)

The processor of claim 9, wherein the selected value is determined based at least on one or more metrics associated with a label value assigned to the first set of vertex values.

### Claim 11 (depends on 10)

The processor of claim 10, wherein the one or more metrics are associated with at least one of a highest label value or a lowest label value.

### Claim 12 (depends on 9)

The processor of claim 9, wherein the one or more circuits are further to:
determine a first index range for the first primitive within the buffer;
determine a second index range for the second primitive within the buffer; and
assign the first index range and the second index range to be contiguous within the buffer.

### Claim 13 (depends on 9)

The processor of claim 9, wherein the one or more circuits are further to:
increase a change counter after assigning the selected value to each vertex in the second set of vertices.

### Claim 14 (depends on 9)

The processor of claim 9, wherein the processor is comprised in at least one of:
a system for performing simulation operations;
a system for performing simulation operations to test or validate autonomous machine applications;
a system for performing digital twin operations;
a system for performing light transport simulation;
a system for rendering graphical output;
a system for performing deep learning operations;
a system implemented using an edge device;
a system for generating or presenting virtual reality (VR) content;
a system for generating or presenting augmented reality (AR) content;
a system for generating or presenting mixed reality (MR) content;
a system incorporating one or more Virtual Machines (VMs);
a system for performing operations for a conversational AI application;
a system for performing operations for a generative AI application;
a system for performing operations using a language model;
a system for performing one or more generative operations using a large language model (LLM);
a system for performing one or more generative operations using a vision language model (VLM);
a system implemented at least partially in a data center;
a system for performing hardware testing using simulation;
a system for performing one or more generative content operations using a language model;
a system for synthetic data generation;
a collaborative content creation platform for 3D assets; or
a system implemented at least partially using cloud computing resources.

### Claim 15

A system, comprising:
processing circuitry to determine a plurality of connected portions of a component sharing at least one vertex, and to update one or more vertex values for each connected portion of the plurality of the connected portions until a number of changes associated with updating the vertex values for the component is zero.

### Claim 16 (depends on 15)

The system of claim 15, wherein the number of changes is reset to zero for each pass through the plurality of connected portions of the component.

### Claim 17 (depends on 15)

The system of claim 15, wherein the vertex values are associated with an assigned label for each vertex value.

### Claim 18 (depends on 17)

The system of claim 17, wherein changes to the assigned label are not applied to geometric properties of the plurality of connected portions.

### Claim 19 (depends on 15)

The system of claim 15, wherein the one or more processing units are further to determine a first set of connected portions of the component and a second set of connected portions of the component, and to assign a first index range for the first set and a second index range for a second set contiguously in a buffer.

### Claim 20 (depends on 15)

The system of claim 15, wherein the system is one of:
a system for performing simulation operations;
a system for performing simulation operations to test or validate autonomous machine applications;
a system for performing digital twin operations;
a system for performing light transport simulation;
a system for rendering graphical output;
a system for performing deep learning operations;
a system implemented using an edge device;
a system for generating or presenting virtual reality (VR) content;
a system for generating or presenting augmented reality (AR) content;
a system for generating or presenting mixed reality (MR) content;
a system incorporating one or more Virtual Machines (VMs);
a system for performing operations for a conversational AI application;
a system for performing operations for a generative AI application;
a system for performing operations using a language model;
a system for performing one or more generative content operations using a large language model (LLM);
a system for performing one or more generative operations using a vision language model (VLM);
a system implemented at least partially in a data center;
a system for performing hardware testing using simulation;
a system for performing one or more generative content operations using a language model;
a system for synthetic data generation;
a collaborative content creation platform for 3D assets; or
a system implemented at least partially using cloud computing resources.
