# US 2025/0157154 A1 · Method and apparatus of patterns for clothing simulation using neural network model

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

- Number: US 2025/0157154 A1
- Document ID: US20250157154A1
- Status: Published application
- Kind: A1
- Application number: 19/020,237
- Filed: 2025-01-14
- Published: 2025-05-15
- Earliest claimed: 2023-08-22
- Assignees: Clo Virtual Fashion Inc.
- Applicants: CLO Virtual Fashion Inc.
- Inventors: Dong Sig KANG; Eun Jung JU
- Web page: https://patentgrep.com/patent/US20250157154A1

## CPC

- G06F 30/27: using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
- G06T 19/00: Manipulating three-dimensional [3D] models or images for computer graphics
- D05B 19/10: Arrangements for selecting combinations of stitch or pattern data from memory {; Handling data in order to control stitch format, e.g. size, direction, mirror image}
- G06N 3/02: Neural networks
- G06N 3/045: Combinations of networks
- A41H 3/00: Patterns for cutting-out; Methods of drafting or marking-out such patterns, e.g. on the cloth
- G06F 2111/18: using virtual or augmented reality
- G06F 2113/12: Cloth
- G06F 2119/18: Manufacturability analysis or optimisation for manufacturability
- G06T 2210/16: Cloth
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- D05B: SEWING (appliances for the tailoring trade A41H; sewing tables A47B29/00; sewing in bookbinding B42B2/00; sewing machines modified for knitting D04B39/08)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- A41H: APPLIANCES OR METHODS FOR MAKING CLOTHES, e.g. FOR DRESS-MAKING OR FOR TAILORING, NOT OTHERWISE PROVIDED FOR

## Abstract

A clothing simulation method and apparatus are provided. The clothing simulation method includes obtaining pattern information for each of patterns of a garment, the pattern information including information about sample points extracted from each of the patterns, based on an embedding vector for each of the patterns obtained by applying the pattern information to a pattern embedding model trained to estimate a correlation between input pattern information, predicting sewing information about the patterns, and based on the sewing information, generating a simulation result of the garment.

## Claims

### Claim 1

A clothing simulation method, comprising:
obtaining pattern information for each of patterns of a garment, the pattern information including information about sample points extracted from each of the patterns;
predicting sewing information about the patterns based on an embedding vector for each of the patterns obtained by applying the pattern information to a pattern embedding model trained to estimate a correlation between input pattern information; and
based on the sewing information, generating a simulation result of the garment.

### Claim 2 (depends on 1)

The clothing simulation method of claim 1, further comprising:
extracting a predetermined number of sample points from each of the patterns of the garment; and
based on a position of a predetermined type of a point included in each of the patterns, adjusting positions of the sample points.

### Claim 3 (depends on 1)

The clothing simulation method of claim 1, wherein the obtaining of the pattern information for each of the patterns comprises obtaining information about sample points of a target pattern, based on a length of an outline from a reference point of the target pattern among the patterns of the garment to each sample point extracted from the target pattern.

### Claim 4 (depends on 1)

The clothing simulation method of claim 1, wherein:
the pattern embedding model comprises a transformer encoder, and
the predicting of the sewing information comprises obtaining information indicating a sewing line of a pattern pair extracted from the patterns by applying, to a transformer decoder, an embedding vector pair corresponding to the pattern pair.

### Claim 5 (depends on 1)

The clothing simulation method of claim 1, wherein the pattern embedding model comprises:
a first transformer encoder trained to estimate a correlation between sample points extracted from a same pattern from the input pattern information; and
a second transformer encoder trained to estimate a correlation between patterns from encoding data for each of the patterns obtained from embedding vectors of sample points output from the first transformer encoder.

### Claim 6 (depends on 5)

The clothing simulation method of claim 5, wherein the predicting of the sewing information comprises:
obtaining encoding data of a first pattern including an embedding vector for each sample point corresponding to the first pattern by applying pattern information of the first pattern to the first transformer encoder;
obtaining encoding data of a second pattern including an embedding vector for each sample point corresponding to the second pattern by applying pattern information of the second pattern to the first transformer encoder;
obtaining an embedding vector of the first pattern and an embedding vector of the second pattern by applying the encoding data of the first pattern and the encoding data of the second pattern to the second transformer encoder; and
predicting sewing information about a pattern pair of the first pattern and the second pattern by applying the embedding vector of the first pattern and the embedding vector of the second pattern to a transformer decoder.

### Claim 7 (depends on 1)

The clothing simulation method of claim 1, wherein the sewing information comprises a pair of lines sewn together within the patterns.

### Claim 8 (depends on 7)

The clothing simulation method of claim 7, wherein the sewing information further includes information indicating a sewing direction of the lines.

### Claim 9 (depends on 4)

The clothing simulation method of claim 4, wherein the information indicating the sewing line of the pattern pair comprises:
information about sample points that are extracted from a first pattern of the pattern pair and correspond to a starting point and an end point of the sewing line included in the first pattern; and
information about sample points that are extracted from a second pattern of the pattern pair and correspond to a starting point and an end point of the sewing line included in the second pattern.

### Claim 10 (depends on 1)

The clothing simulation method of claim 1, wherein the pattern embedding model is trained based on a loss about a difference between the predicted sewing information and ground truth.

### Claim 11 (depends on 1)

The clothing simulation method of claim 1, wherein:
the predicting of the sewing information about the patterns comprises predicting arrangement information about the patterns and the sewing information, based on an embedding vector for each of the patterns, and
the generating of the simulation result of the garment comprises generating the simulation result of the garment, based on the sewing information and the arrangement information.

### Claim 12 (depends on 11)

The clothing simulation method of claim 11, wherein the pattern embedding model is trained based on a loss about a difference between the predicted sewing information and ground truth, and a loss about a difference between the predicted arrangement information and ground truth.

### Claim 13 (depends on 1)

The clothing simulation method of claim 1, wherein the information about the sample points comprises at least one of:
information indicating positions of the sample points within a pattern of the garment;
information indicating positions of the sample points within the garment;
information indicating a positional relationship between adjacent ones of the sample points; and
information indicating a type of the sample points.

### Claim 14

A non-transitory computer-readable storage medium storing instructions that, the instructions when executed by one or more processors, cause the one or more processors to:
obtain pattern information for each of patterns of a garment, the pattern information including information about sample points extracted from each of the patterns;
predict sewing information about the patterns based on an embedding vector for each of the patterns obtained by applying the pattern information to a pattern embedding model trained to estimate a correlation between input pattern information; and
based on the sewing information, generate a simulation result of the garment.

### Claim 15

A clothing simulation apparatus comprising:
one or more processors; and
memory storing instructions thereon, the instructions when executed by the one or more processors cause the one or more processors to:
obtain pattern information for each of patterns of a garment, the pattern information including information about sample points extracted from each of the patterns;
predict sewing information about the patterns based on an embedding vector for each of the patterns obtained by applying the pattern information to a pattern embedding model trained to estimate a correlation between input pattern information; and
based on the sewing information, generate a simulation result of the garment.
