# US 2025/0095258 A1 · Systems and methods for generating animations for 3d objects using machine learning

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

- Number: US 2025/0095258 A1
- Document ID: US20250095258A1
- Status: Published application
- Kind: A1
- Application number: 18/370,607
- Filed: 2023-09-20
- Published: 2025-03-20
- Earliest claimed: 2023-09-20
- Assignees: Google Inc.
- Applicants: Google LLC
- Inventors: Crystal Fong; Nicholas Wasilewski; Douglas Sim Dietrich, JR.
- Web page: https://patentgrep.com/patent/US20250095258A1

## CPC

- G06T 13/20: Three-dimensional [3D] animation
- G06V 10/70: using pattern recognition or machine learning (optical pattern recognition or electronic computations therefor G06V10/88)
- G06V 20/64: Three-dimensional [3D] objects
- G06T 2213/08: Animation software package
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A method includes identifying a first three-dimensional (3D) object comprising a first animation rig covering a first set of features associated with the first 3D object. An indication of the first 3D object is provided as input to a machine-learning model. The machine-learning model is trained to generate, using a second 3D object comprising a second animation rig, an animation sequence for the first 3D object. The second animation rig covers a second set of features associated with the second 3D object and the second set of features comprises the first set of features and one or more additional features. One or more outputs of the machine-learning model is obtained. The one or more obtained outputs comprise a plurality of animation frames reflecting an animation sequence for the first 3D object.

## Claims

### Claim 1

A method comprising:
identifying, by a processor, a first three-dimensional (3D) object comprising a first animation rig covering a first set of features associated with the first 3D object;
providing an indication of the first 3D object as input to a machine-learning model, wherein the machine-learning model is trained to generate, using a second 3D object comprising a second animation rig, an animation sequence for the first 3D object, wherein the second animation rig covers a second set of features associated with the second 3D object, the second set of features comprising the first set of features and one or more additional features; and
obtaining one or more outputs of the machine-learning model, wherein the one or more obtained outputs comprise a plurality of animation frames reflecting an animation sequence for the first 3D object.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
receiving, from a client device, a request to present, on a user interface, the animation sequence for the 3D object; and
providing, to the client device, the plurality of animation frames for presentation.

### Claim 3 (depends on 1)

The method of claim 1, wherein the first set of features comprises a first set of bones and the second set of features comprises a second set of bones, wherein a number of bones in the second set is greater than a number of bones in the first set.

### Claim 4 (depends on 3)

The method of claim 3, wherein the machine-learning model generates the plurality of animation frames by animating a subset of bones from the second set of bones and applying resulting animation data to the bones of the first 3D object.

### Claim 5 (depends on 1)

The method of claim 1, wherein the second 3D object comprises features from at least one type of real object and one type of fictional object.

### Claim 6 (depends on 1)

The method of claim 1, wherein the machine-learning model is trained to generate an animation sequence based on at least one of an idle motion or a reaction motion.

### Claim 7 (depends on 1)

The method of claim 1, further comprising:
providing, as input to the machine-learning model, an identifier associated with the first 3D object.

### Claim 8 (depends on 7)

The method of claim 7, wherein the identifier is determined using object recognition software.

### Claim 9 (depends on 1)

The method of claim 1, wherein the machine-learning model is trained based on the second 3D object and a plurality of media items.

### Claim 10

A system comprising:
a memory; and
a processing device, coupled to the memory, the processing device to perform operations comprising:
identifying a first three-dimensional (3D) object comprising a first animation rig covering a first set of features associated with the first 3D object;
providing an indication of the first 3D object as input to a machine-learning model, wherein the machine-learning model is trained to generate, using a second 3D object comprising a second animation rig, an animation sequence for the first 3D object, wherein the second animation rig covers a second set of features associated with the second 3D object, the second set of features comprising the first set of features and one or more additional features; and
obtaining one or more outputs of the machine-learning model, wherein the one or more obtained outputs comprise a plurality of animation frames reflecting an animation sequence for the first 3D object.

### Claim 11 (depends on 10)

The system of claim 10, wherein the operations further comprise:
receiving, from a client device, a request to present, on a user interface, the animation sequence for the 3D object; and
providing, to the client device, the plurality of animation frames for presentation.

### Claim 12 (depends on 10)

The system of claim 10, wherein the first set of features comprises a first set of bones and the second set of features comprises a second set of bones, wherein a number of bones in the second set is greater than a number of bones in the first set.

### Claim 13 (depends on 12)

The system of claim 12, wherein the machine-learning model generates the plurality of animation frames by animating a subset of bones from the second set of bones and applying resulting animation data to the bones of the first 3D object.

### Claim 14 (depends on 10)

The system of claim 10, wherein the second 3D object comprises features from at least one type of real object and one type of fictional object.

### Claim 15 (depends on 10)

The system of claim 10, wherein the machine-learning model is trained to generate an animation sequence based on at least one of an idle motion or a reaction motion.

### Claim 16 (depends on 10)

The system of claim 10, wherein the operations further comprise:
providing, as input to the machine-learning model, an identifier associated with the first 3D object.

### Claim 17 (depends on 16)

The system of claim 16, wherein the identifier is determined using object recognition software.

### Claim 18 (depends on 16)

The system of claim 16, wherein the machine-learning model is trained based on the second 3D object and a plurality of media items.

### Claim 19

A non-transitory computer-readable medium comprising instructions that, responsive to execution by a processing device, cause the processing device to perform operations comprising:
identifying a first three-dimensional (3D) object comprising a first animation rig covering a first set of features associated with the first 3D object;
providing an indication of the first 3D object as input to a machine-learning model, wherein the machine-learning model is trained to generate, using a second 3D object comprising a second animation rig, an animation sequence for the first 3D object, wherein the second animation rig covers a second set of features associated with the second 3D object, the second set of features comprising the first set of features and one or more additional features; and
obtaining one or more outputs of the machine-learning model, wherein the one or more obtained outputs comprise a plurality of animation frames reflecting an animation sequence for the first 3D object.

### Claim 20 (depends on 19)

The non-transitory computer readable storage medium of claim 19, wherein the first 3D object comprises a first set of bones and the second 3D object comprises a second set of bones, wherein the second set of bones is greater than the first set of bones.
