# US 2021/0342926 A1 · Visualization of garments on a body model of a human

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

- Number: US 2021/0342926 A1
- Document ID: US20210342926A1
- Status: Published application
- Kind: A1
- Application number: 16/863,802
- 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/US20210342926A1

## CPC

- G06T 13/40: of characters, e.g. humans, animals or virtual beings
- A61B 5/0064: {Body surface scanning}
- A61B 5/1079: {using optical or photographic means}
- A61B 5/744: {Displaying an avatar, e.g. an animated cartoon character}
- G06Q 10/40: Business processes related to social networking or social networking services
- G06Q 30/0643: {graphically representing goods, e.g. 3D product representation}
- G06T 7/74: {involving reference images or patches}
- G06T 7/75: {involving models}
- G06T 17/00: Three-dimensional [3D] modelling for computer graphics
- G06T 19/00: Manipulating three-dimensional [3D] models or images for computer graphics
- G06T 19/006: {Mixed reality (object pose determination, tracking or camera calibration for mixed reality G06T7/00)}
- G06T 19/20: Editing of three-dimensional [3D] images, e.g. changing shapes or colours, aligning objects or positioning parts
- G06T 2200/04: involving 3D image data
- G06T 2207/10028: Range image; Depth image; 3D point clouds
- G06T 2207/30196: Human being; Person
- G06T 2210/16: Cloth
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- 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

## Abstract

The invention relates to three computer implemented methods providing virtual fitting room functionality to a human. The three computer implemented methods allow for a simple and efficient garment selection process by the human.

## Claims

### Claim 1

Computer implemented method, with program code being stored on a machine readable medium or embodied as an electromagnetic wave, for generating a fully animatable body model of a human for garment fitting purposes, the computer implemented method comprising:
providing a pose instruction to the human, the pose instruction instructing the human to pose in at least a first and a second nominal body pose;
receiving at least:
a plurality of first 3D points, the first 3D points being based on first scan data representing a surface of the human while in a first actual body pose; and
a plurality of second 3D points, the second 3D points being based on second scan data representing a surface of the human while in a second actual body pose, the first and second actual body pose respectively corresponding to the first and second nominal body pose;
determining at least a first and a second kinematic tree from respectively the at least first and second scan data, the at least first and second kinematic tree respectively corresponding to the at least first and second actual body pose;
establishing a one-to-one correspondence between at least a part of the first 3D points and at least a part of the second 3D points;
determining an interpolating model between the at least first and second actual body pose, wherein the interpolating model takes at least a third kinematic tree as input, wherein the interpolating model is constrained by the one-to-one correspondence; and
providing the interpolating model as the fully animatable body model to a computer program configured to provide virtual fitting room services.

### Claim 2 (depends on 1)

Computer implemented method according to claim 1, wherein the at least first and second scan data are provided by marker-free scanning.

### Claim 3 (depends on 1)

Computer implemented method according to claim 1, wherein the determination of the at least first and second kinematic tree is done using a neural network, wherein the neural network is trained for extracting a kinematic tree from a scan data.

### Claim 4 (depends on 1)

Computer implemented method according to claim 1, wherein the pose instruction instructs the human to pose in at least a first and a second nominal body pose corresponding to common body poses of the human, wherein the human is free to choose the at least first and second nominal body pose.

### Claim 5 (depends on 1)

Computer implemented method according to claim 1, wherein the at least first and second scan data capture the human in a dressed state, wherein the human is allowed to freely choose a worn dress.

### Claim 6

Computer implemented method, with program code being stored on a machine readable medium or embodied as an electromagnetic wave, for determining a best fitting garment for a human, the computer implemented method comprising:
establishing access to a stored garment catalogue comprising a plurality of 3D garment digital twins (GDT), each GDT associated to at least one of a plurality of garment types;
receiving a body model of the human;
receiving a garment instruction from the human about a chosen garment type via a graphical user interface, the chosen garment type being one of the plurality of garment types;
determining a best fitting garment according to a best fitting criterion based on the GDTs associated to the chosen garment type and the body model of the human;
providing the human with information about the best fitting garment via the graphical user interface; and
visualizing the best fitting garment on the body model in a virtual 3D environment.

### Claim 7 (depends on 6)

Computer implemented method according to claim 6, wherein the best fitting criterion comprises at least two sub-criteria, wherein each sub-criterion uses a measured model property of the body model and a corresponding measured garment property of at least one of the GDTs associated to the chosen garment type, and each sub-criterion comprises a metric for comparing the measured model property with the measured garment property, the metric providing a discrepancy, wherein the best fitting garment according to the best fitting criterion is determined to be the garment that minimizes a combination of discrepancies provided by the sub-criteria.

### Claim 8 (depends on 6)

Computer implemented method according to claim 6, wherein the best fitting criterion is provided by the human via the graphical user interface.

### Claim 9 (depends on 6)

Computer implemented method according to claim 6, wherein the visualization of the best fitting garment on the body model comprises vanity visualization functionality, wherein a horizontal extent of the body model and of the best fitting garment is changed by the vanity visualization functionality.

### Claim 10 (depends on 6)

Computer implemented method according to claim 6, further providing the human with the option to choose a next larger or a next smaller garment compared to the best fitting garment, wherein the next larger or the next smaller garment is visualized on the body model in the virtual 3D environment.

### Claim 11 (depends on 6)

Computer implemented method according to claim 6, wherein the body model is provided as a fully animatable body model with program code being stored on a machine readable medium or embodied as an electromagnetic wave, for generating a fully animatable body model of a human for garment fitting purposes, the computer implemented method further comprising:
providing a pose instruction to the human, the pose instruction instructing the human to pose in at least a first and a second nominal body pose;
receiving at least:
a plurality of first 3D points, the first 3D points being based on first scan data representing a surface of the human while in a first actual body pose; and
plurality of second 3D points, the second 3D points being based on second scan data representing a surface of the human while in a second actual body pose, the first and second actual body pose respectively corresponding to the first and second nominal body pose;
determining at least a first and a second kinematic tree from respectively the at least first and second scan data, the at least first and second kinematic tree respectively corresponding to the at least first and second actual body pose;
establishing a one-to-one correspondence between at least a part of the first 3D points and at least a part of the second 3D points;
determining an interpolating model between the at least first and second actual body pose, wherein the interpolating model takes at least a third kinematic tree as input, wherein the interpolating model is constrained by the one-to-one correspondence; and
providing the interpolating model as the fully animatable body model to a computer program configured to provide virtual fitting room services.

### Claim 12

Computer implemented method, with program code being stored on a machine readable medium or embodied as an electromagnetic wave, for visualizing at least one garment on a fully animatable body model of a human, the computer implemented method comprising:
receiving the fully animatable body model of the human;
receiving a pose display instruction via a graphical user interface;
receiving a garment digital twin (GDT) of the at least one garment; and
visualizing the garment digital twin on the fully animatable body model, wherein the fully animatable body model is adopting a pose according to the pose display instruction, wherein the garment digital twin is deformed due to the pose of the fully animatable body model, the deformation taking into account at least gravity, fabric properties of a fabric of the garment, and geometric constraints imposed by the fully animatable body model in the pose according to the pose display instruction on the garment digital twin.

### Claim 13 (depends on 12)

Computer implemented method according to claim 12, wherein the pose display instruction is provided in parallel to the visualization, wherein a body scanner captures a pose of the human, wherein the captured pose is provided as pose display instruction.

### Claim 14 (depends on 13)

Computer implemented method according to claim 13, wherein the pose display instruction captures a real-time motion of the human, wherein the visualization of the at least one garment on the fully animatable body model follows the real-time motion in parallel.

### Claim 15 (depends on 12)

Computer implemented method according to claim 12, wherein the fully animatable body model is provided with program code being stored on a machine readable medium or embodied as an electromagnetic wave, for generating a fully animatable body model of a human for garment fitting purposes, the computer implemented method further comprising:
providing a pose instruction to the human, the pose instruction instructing the human to pose in at least a first and a second nominal body pose;
receiving at least:
a plurality of first 3D points, the first 3D points being based on first scan data representing a surface of the human while in a first actual body pose; and
plurality of second 3D points, the second 3D points being based on second scan data representing a surface of the human while in a second actual body pose, the first and second actual body pose respectively corresponding to the first and second nominal body pose;
determining at least a first and a second kinematic tree from respectively the at least first and second scan data, the at least first and second kinematic tree respectively corresponding to the at least first and second actual body pose;
establishing a one-to-one correspondence between at least a part of the first 3D points and at least a part of the second 3D points;
determining an interpolating model between the at least first and second actual body pose, wherein the interpolating model takes at least a third kinematic tree as input, wherein the interpolating model is constrained by the one-to-one correspondence; and
providing the interpolating model as the fully animatable body model to a computer program configured to provide virtual fitting room services.

### Claim 16 (depends on 12)

Computer implemented method according to claim 12, wherein the garment digital twin is provided with program code being stored on a machine readable medium or embodied as an electromagnetic wave, for determining a best fitting garment for a human, the computer implemented method further comprising:
establishing access to a stored garment catalogue comprising a plurality of 3D garment digital twins (GDT), each GDT associated to at least one of a plurality of garment types;
receiving a body model of the human;
receiving a garment instruction from the human about a chosen garment type via a graphical user interface, the chosen garment type being one of the plurality of garment types;
determining a best fitting garment according to a best fitting criterion based on the GDTs associated to the chosen garment type and the body model of the human;
providing the human with information about the best fitting garment via the graphical user interface; and
visualizing the best fitting garment on the body model in a virtual 3D environment.

### Claim 17 (depends on 12)

Computer implemented method according to claim 12, wherein the human is provided with the option of sharing the fully animatable body model in a dressed state via social media, and wherein the computer implemented method is able to receive feedback from external sources via social media.

### Claim 18 (depends on 6)

Computer implemented method according to claim 6, wherein the human is provided with the option of sharing the fully animatable body model in a dressed state via social media, and wherein the computer implemented method is able to receive feedback from external sources via social media.
