# US 2025/0095262 A1 · Stylized animatable representation

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

- Number: US 2025/0095262 A1
- Document ID: US20250095262A1
- Status: Published application
- Kind: A1
- Application number: 18/961,418
- Filed: 2024-11-26
- Published: 2025-03-20
- Earliest claimed: 2022-11-22
- Assignees: Microsoft Technology Licensing, LLC
- Applicants: Microsoft Technology Licensing, LLC
- Inventors: Daniel Stephen WILDE; Xian XIAO; Marta Malgorzata WILCZKOWIAK; Thomas Joseph CASHMAN
- Web page: https://patentgrep.com/patent/US20250095262A1

## CPC

- G06T 13/40: of characters, e.g. humans, animals or virtual beings
- G06T 17/00: Three-dimensional [3D] modelling for computer graphics
- G06T 17/20: Finite element generation, e.g. wire-frame surface description, {tesselation}
- G06V 10/761: {Proximity, similarity or dissimilarity measures}
- G06V 10/762: using clustering, e.g. of similar faces in social networks
- G06V 20/653: {by matching three-dimensional models, e.g. conformal mapping of Riemann surfaces}
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A method for computing a stylized, animatable representation of a subject from a family of stylized animatable representations is described. The method comprises accessing a realistic representation of the subject and computing a mesh mapping using a first machine learning model that is trained using a supervised training methodology that uses a set of training examples comprising a plurality of two dimensional (2D) images of the subject and corresponding stylized pictures of the subject. The method also comprises the first trained machine learning model applying the mesh mapping to the realistic representation to produce a target mesh, and selecting the stylized animatable representation from the family, based on closeness of the target mesh with instances of the family.

## Claims

### Claim 1

A computerized method of computing a stylized, animatable representation of a subject from a family of stylized animatable representations, the method comprising:
accessing a realistic representation of the subject;
computing a mesh mapping using a machine learning model that is trained using a supervised training methodology that uses training examples comprising two dimensional (2D) images of the subject and corresponding stylized pictures of the subject, wherein computing the mesh mapping comprises:
inputting the realistic representation to the trained machine learning model; and
causing the trained machine learning model to compute a mesh mapping;
causing the trained machine learning model to apply the mesh mapping to the realistic representation to produce a target mesh; and
selecting the stylized animatable representation from the family, based on closeness of the target mesh with instances of the family.

### Claim 2 (depends on 1)

The method of claim 1, wherein the trained machine learning model produces an accurate target mesh even when the realistic representation differs from the training examples.

### Claim 3 (depends on 1)

The method of claim 1, wherein a 2D image is used to create the realistic representation using a technology to reconstruct a 3D model using dense landmarks, another machine learning model being used to predict locations of the dense landmarks in the 2D image, wherein the other trained machine learning model is trained using synthetic training data which gives ground truth landmark annotations.

### Claim 4 (depends on 1)

The method of claim 1, wherein the training examples are selected as nearest neighbors of the realistic representation.

### Claim 5 (depends on 1)

The method of claim 1, further comprising, prior to applying the mesh mapping, computing a retopology of the realistic representation.

### Claim 6 (depends on 1)

The method of claim 1, further comprising computing the mesh mapping by deriving the mesh mapping from a transformation.

### Claim 7 (depends on 1)

The method of claim 1, wherein the mesh mapping is computed by computing, for the training examples selected as nearest neighbors of the realistic representation, a separate transformation.

### Claim 8

An apparatus for computing a stylized, animatable representation of a subject from a family of stylized animatable representations, the apparatus comprising:
a processor;
a memory storing a realistic representation of the subject and storing instructions which when executed by the processor cause the processor to:
access a realistic representation of the subject;
compute a mesh mapping using a machine learning model that is trained using a supervised training methodology that uses training examples comprising two dimensional (2D) images of the subject and corresponding stylized pictures of the subject, wherein computing the mesh mapping comprises:
inputting the realistic representation to the trained machine learning model; and
causing the trained machine learning model to compute a mesh mapping;
cause the trained machine learning model to apply the mesh mapping to the realistic representation to produce a target mesh; and
select the stylized animatable representation from the family, based on closeness of the target mesh with instances of the family.

### Claim 9 (depends on 8)

The apparatus of claim 8, wherein the trained machine learning model produces an accurate target mesh even when the realistic representation differs from the training examples.

### Claim 10 (depends on 8)

The apparatus of claim 8, wherein a 2D image is used to create the realistic representation using a technology to reconstruct a 3D model using dense landmarks, another trained machine learning model being used to predict locations of the dense landmarks in the 2D image, wherein the other trained machine learning model is trained using synthetic training data which gives ground truth landmark annotations.

### Claim 11 (depends on 8)

The apparatus of claim 8, wherein the training examples are selected as nearest neighbors of the realistic representation.

### Claim 12 (depends on 8)

The apparatus of claim 8, wherein the instructions further cause the processor to compute the mesh mapping by deriving the mesh mapping from a transformation.

### Claim 13 (depends on 8)

The apparatus of claim 8, wherein the instructions further cause the processor to prior to applying the mesh mapping, compute a retopology of the realistic representation.

### Claim 14 (depends on 8)

The apparatus of claim 8, wherein the mesh mapping is computed by computing, for the training examples selected as nearest neighbors of the realistic representation, a separate transformation.

### Claim 15

A non-transitory computer-readable medium embodied with computer-executable instructions that, when executed by a processor, cause the processor to perform operations comprising:
accessing a realistic representation of a subject;
computing a mesh mapping using a machine learning model that is trained using a supervised training methodology that uses training examples comprising two dimensional (2D) images of the subject and corresponding stylized pictures of the subject, wherein computing the mesh mapping comprises:
inputting the realistic representation to the trained machine learning model; and
causing the trained machine learning model to compute a mesh mapping;
causing the trained machine learning model to apply the mesh mapping to the realistic representation to produce a target mesh; and
selecting a stylized animatable representation from a family of stylized animatable representations, based on closeness of the target mesh with instances of the family.

### Claim 16 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the trained machine learning model produces an accurate target mesh even when the realistic representation differs from the training examples.

### Claim 17 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein a 2D image is used to create the realistic representation using a technology to reconstruct a 3D model using dense landmarks, another trained machine learning model being used to predict locations of the dense landmarks in the 2D image, wherein the other trained machine learning model is trained using synthetic training data which gives ground truth landmark annotations.

### Claim 18 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the training examples are selected as nearest neighbors of the realistic representation.

### Claim 19 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the mesh mapping is computed by computing, for the training examples selected as nearest neighbors of the realistic representation, a separate transformation.

### Claim 20 (depends on 15)

The non-transitory computer-readable medium of claim 15, wherein the computer-executable instructions further cause the processor to perform operations comprising computing the mesh mapping by deriving the mesh mapping from a transformation.