Google llc (20240127523). PUPPETEERING A REMOTE AVATAR BY FACIAL EXPRESSIONS simplified abstract

PUPPETEERING A REMOTE AVATAR BY FACIAL EXPRESSIONS

Organization Name

google llc

Inventor(s)

Tarek Hefny of Redmond WA (US)

Nicholas Reiter of Mountain View CA (US)

Brandon Young of Mountain View CA (US)

Arun Kandoor of Santa Clara CA (US)

Dillon Cower of Mountain View CA (US)

PUPPETEERING A REMOTE AVATAR BY FACIAL EXPRESSIONS - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240127523 titled 'PUPPETEERING A REMOTE AVATAR BY FACIAL EXPRESSIONS

Simplified Explanation

The patent application describes a method for creating a three-dimensional avatar of a face by receiving facial frameworks and captured images, projecting the images onto the frameworks, determining facial texture, updating the texture based on new frameworks, and displaying the avatar.

• Receiving facial frameworks and captured images of a face
• Projecting captured images onto facial frameworks
• Determining facial texture based on projected images
• Updating facial texture with new facial frameworks
• Displaying the updated facial texture as a three-dimensional avatar

Potential Applications

This technology could be used in virtual reality applications, facial recognition software, and entertainment industries for creating realistic avatars.

Problems Solved

This technology solves the problem of accurately representing facial features in a three-dimensional avatar by updating facial texture based on new information.

Benefits

The benefits of this technology include creating more realistic and accurate three-dimensional avatars, improving user experience in virtual environments, and enhancing facial recognition capabilities.

Potential Commercial Applications

Potential commercial applications of this technology include virtual reality gaming, virtual meetings, facial animation software, and personalized avatar creation services.

Possible Prior Art

One possible prior art for this technology could be facial recognition software that uses facial landmarks to create three-dimensional representations of faces.

How does this technology handle changes in facial expressions over time?

The method described in the patent application updates the facial texture based on new facial frameworks, but it is unclear how it handles changes in facial expressions over time. Further research and development may be needed to address this issue.

What are the limitations of this technology in terms of facial recognition accuracy?

While the technology aims to create realistic three-dimensional avatars, its limitations in accurately representing facial features may impact its effectiveness in facial recognition applications. Further testing and refinement may be necessary to improve accuracy.

Original Abstract Submitted

a method includes receiving a first facial framework and a first captured image of a face. the first facial framework corresponds to the face at a first frame and includes a first facial mesh of facial information. the method also includes projecting the first captured image onto the first facial framework and determining a facial texture corresponding to the face based on the projected first captured image. the method also includes receiving a second facial framework at a second frame that includes a second facial mesh of facial information and updating the facial texture based on the received second facial framework. the method also includes displaying the updated facial texture as a three-dimensional avatar. the three-dimensional avatar corresponds to a virtual representation of the face.