# US 2021/0343083 A1 · Computer implemented methods for generating 3d garment models

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

- Number: US 2021/0343083 A1
- Document ID: US20210343083A1
- Status: Published application
- Kind: A1
- Application number: 16/863,773
- Filed: 2020-04-30
- Published: 2021-11-04
- Earliest claimed: 2020-04-30
- Assignees: Clothing Tech LLC
- Applicants: Clothing Tech LLC
- Inventors: William WILCOX
- Web page: https://patentgrep.com/patent/US20210343083A1

## CPC

- G06T 17/00: Three-dimensional [3D] modelling for computer graphics
- G06T 19/00: Manipulating three-dimensional [3D] models or images for computer graphics
- A41H 1/00: Measuring aids or methods
- G06F 30/10: Geometric CAD
- G06N 5/04: Inference or reasoning models
- G06N 20/00: Machine learning
- G06Q 10/10: Office automation; Time management
- G06Q 30/0203: Market surveys; Market polls
- G06Q 30/0643: {graphically representing goods, e.g. 3D product representation}
- G06T 19/20: Editing of three-dimensional [3D] images, e.g. changing shapes or colours, aligning objects or positioning parts
- G06T 2210/16: Cloth
- G06T 2219/2004: Aligning objects, relative positioning of parts
- G06T 2219/2021: Shape modification
- G06V 20/647: {by matching two-dimensional images to three-dimensional objects}
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- A41H: APPLIANCES OR METHODS FOR MAKING CLOTHES, e.g. FOR DRESS-MAKING OR FOR TAILORING, NOT OTHERWISE PROVIDED FOR
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

The invention relates to a first computer implemented method for automatically generating a first 3D garment model representing a first garment to be fabricated from first garment panels, a second computer implemented method for virtually finishing a second 3D garment model representing a second garment to be fabricated without finishes or with default finishes, and a third computer implemented method for automatically generating a plurality of third 3D garment models in a batch process, each third 3D garment model representing a third garment to be fabricated from third garment panels.

## Claims

### Claim 1

A computer implemented method, with program code being stored on a machine readable medium or embodied as an electromagnetic wave, for automatically generating a first 3D garment model representing a first garment to be fabricated from first garment panels, the computer implemented method comprising:
providing one or more first documents comprising a plurality of first 2D pattern pieces representing the first garment panels,
determining with a pattern recognition algorithm
a garment type indicator for at least one of the first 2D pattern pieces, the garment type indicator representing a type of a garment that the respective first garment panel belongs to and being one of a plurality of garment type indicators stored on the machine readable medium, and
a panel pose indicator for each of the first 2D pattern pieces, the panel pose indicator representing an estimated position and an estimated orientation of the respective garment panel within the first garment, and
generating the first 3D garment model based on the first 2D pattern pieces, the at least one garment type indicator, and the panel pose indicators.

### Claim 2 (depends on 1)

The computer implemented method according to claim 1, further comprising adding default finishes to the first 3D garment model based on at least one of the at least one garment type indicator and the panel pose indicators.

### Claim 3 (depends on 1)

The computer implemented method according to claim 1, further comprising generating a first 2D panel model for each of the first 2D pattern pieces, wherein generating the first 3D garment model is based on draping a reference object with the first 2D panel models.

### Claim 4 (depends on 3)

The computer implemented method according to claim 3, further comprising:
positioning and orienting the first 2D panel models based on the panel pose indicators,
while, before, or after positioning and orienting the 2D panel models, shaping each of the first 2D panel models into first 3D panel models so as they adapt to a shape of the reference object based on the at least one garment type indicator, and the panel pose indicators, and
generating the first 3D garment model by virtually assembling the first 3D panel models along their respective edges.

### Claim 5 (depends on 1)

The computer implemented method according to claim 1, wherein for determining a garment type indicator and the panel pose indicator, the pattern recognition algorithm is configured for analyzing at least one of
a shape of the 2D pattern piece,
a proportion of the 2D pattern piece relative to the other 2D pattern pieces,
textual information associated with the 2D pattern piece in the respective first document,
whether the 2D pattern piece is at least in part symmetrical or not, and
an amount of provided 2D pattern pieces.

### Claim 6

A computer implemented method, with program code being stored on a machine readable medium or embodied as an electromagnetic wave, for virtually finishing a second 3D garment model representing a second garment to be fabricated without finishes or with default finishes, the computer implemented method comprising:
providing the second 3D garment model,
providing one or more second documents comprising human-readable garment finishing instructions for finishing the second garment,
determining with an extraction algorithm at least one garment finish feature from the one or more second documents, the garment finish feature corresponding to an additional garment component or a garment property and being indicative for a position and an orientation of the respective additional garment component or garment property within the second garment, and
virtually finishing the second 3D garment model based on the determined at least one garment finish feature.

### Claim 7 (depends on 6)

The computer implemented method according to claim 6, wherein virtually finishing the second 3D garment model comprises modifying at least a part of the second 3D garment model.

### Claim 8 (depends on 7)

The computer implemented method according to claim 7, the garment finish feature corresponding to a fabric type of at least part of the second 3D garment model, wherein modifying the at least a part of the second 3D garment model comprises attributing at least one of a texture and a color to at least part of the second 3D garment model based on the garment finish feature.

### Claim 9 (depends on 7)

The computer implemented method according to claim 7, the garment finish feature corresponding to seams of the second garment, wherein modifying at least a part of the second 3D garment model comprises attributing at least one of a thread color, a thread type, and a stitch pattern to seams of the second garment.

### Claim 10 (depends on 6)

The computer implemented method according to claim 6, wherein virtually finishing the second 3D garment model comprises adding at least one garment finish model to the second 3D garment model.

### Claim 11 (depends on 10)

The computer implemented method according to claim 10, the garment finish feature corresponding to seams of the second garment, wherein the at least one garment finish model represents stitches to be placed at dedicated locations within the second garment.

### Claim 12 (depends on 10)

The computer implemented method according to claim 10, the garment finish feature corresponding to bindings of the second garment, wherein the at least one garment finish model represents hems to be placed at openings of the second garment.

### Claim 13 (depends on 10)

The computer implemented method according to claim 10, the garment finish feature corresponding to a closure of the garment, wherein the at least one garment finish model represents at least one of
a button,
a buttonhook,
a snap fastener,
a zipper,
a touch fastener,
a magnetic fastener,
a hook,
a loop for a hook or a button,
a cord fastener, and
laces.

### Claim 14 (depends on 6)

The computer implemented method according to claim 6, wherein for determining the at least one garment finish feature, the extraction algorithm is configured for analyzing the one or more second documents with respect to at least one of:
textual information,
image data,
arrows,
size data,
color swatches,
color indicators,
stitch types, and
stitch designations.

### Claim 15

A computer implemented method, with program code being stored on a machine readable medium or embodied as an electromagnetic wave, for automatically generating a plurality of third 3D garment models in a batch process, each third 3D garment model representing a third garment to be fabricated from third garment panels, the computer implemented method comprising:
for each third 3D garment model to be generated:
providing one or more third documents comprising
a plurality of third 2D pattern pieces representing the third garment panels and
human-readable garment finishing instructions for finishing the third garment,
recognizing patterns of the third 2D pattern pieces,
generating a fourth 3D garment model based on the recognized patterns of third 2D pattern pieces,
extracting at least one garment finish feature from the human-readable garment finishing instructions,
generating a third 3D garment model by virtually finishing each of the fourth 3D garment models based on the extracted at least one garment finish feature; and
for the batch-processed plurality of third 3D garment models, generating a report comprising statistics about at least one of:
whether a fourth 3D garment model could be generated for each of the third 3D garment models to be generated,
which of the fourth 3D garment models could be generated,
for each of the fourth 3D garment models that could be generated, a level of confidence that it was generated correctly,
which of the fourth 3D garment models could not be generated,
which of the fourth 3D garment models could be generated only in part and to what extent,
whether a third 3D garment model could be generated from each of the fourth 3D garment models,
which of the third 3D garment models could be generated,
for each of the third 3D garment models that could be generated, a level of confidence that it was generated correctly,
which of the third 3D garment models could not be generated, and
which of the third 3D garment model could be generated only in part and to what extent.

### Claim 16 (depends on 15)

The computer implemented method according to claim 15, wherein recognizing patterns of the third 2D pattern pieces is based on determining with a pattern recognition algorithm
a garment type indicator for at least one of the third 2D pattern pieces, the garment type indicator representing a type of a garment that the respective third garment panel belongs to and being one of a plurality of garment type indicators stored on the machine readable medium, and
a panel pose indicator for each of the third 2D pattern pieces, the panel pose indicator representing an estimated position and an estimated orientation of the respective garment panel within the third garment,
wherein generating the fourth 3D garment model is further based on the garment type indicator and the panel pose indicator.

### Claim 17 (depends on 16)

The computer implemented method according to claim 16, wherein the pattern recognition algorithm is trainable based on at least one of the generated report and user feedback.

### Claim 18 (depends on 15)

The computer implemented method according to claim 15, wherein extracting at least one garment finish feature is based on determining with an extraction algorithm the at least one garment finish feature from the one or more third documents, the garment finish feature corresponding to an additional garment component or a garment property and being indicative for a position and an orientation of the respective additional garment component or garment property within the third garment.

### Claim 19 (depends on 18)

The computer implemented method according to claim 18, wherein for determining the at least one garment finish feature, the extraction algorithm is configured for analyzing the one or more third documents with respect to at least one of:
textual information,
image data,
arrows,
size data,
color swatches,
color indicators,
stitch types, and
stitch designations.

### Claim 20 (depends on 18)

The computer implemented method according to claim 18, wherein the extraction algorithm is trainable based on at least one of the generated report and user feedback.
