Google llc (20240290025). AVATAR BASED ON MONOCULAR IMAGES simplified abstract

AVATAR BASED ON MONOCULAR IMAGES

Organization Name

google llc

Inventor(s)

Yinda Zhang of Palo Alto CA (US)

Sean Ryan Francesco Fanello of San Francisco CA (US)

Ziqian Bai of Burnaby (CA)

Feitong Tan of Mountain View CA (US)

Zeng Huang of Los Angeles CA (US)

Kripasindhu Sarkar of Zurich (CH)

Danhang Tang of West Hollywood CA (US)

Di Qiu of Kitchener (CA)

Abhimitra Meka of San Francisco CA (US)

Ruofei Du of San Francisco CA (US)

Mingsong Dou of Cupertino CA (US)

Sergio Orts Escolano of Zurich (CH)

Rohit Kumar Pandey of Sunnyvale CA (US)

Thabo Beeler of Egg (CH)

AVATAR BASED ON MONOCULAR IMAGES - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240290025 titled 'AVATAR BASED ON MONOCULAR IMAGES

The method described in the patent application involves creating an avatar of a user based on a sequence of monocular images and modifying the avatar based on gestures captured in a second sequence of images.

• Receiving a sequence of monocular images of a user's portion
• Generating an avatar based on the first sequence using a feature vector associated with a vertex
• Receiving a second sequence of images of the user's portion
• Modifying the avatar based on gestures captured in the second sequence by displacing the vertex

Potential Applications: - Virtual reality applications - Gaming industry for personalized avatars - Teleconferencing and virtual meetings

Problems Solved: - Creating realistic avatars from monocular images - Enhancing user interaction in virtual environments

Benefits: - Personalized avatars for users - Improved user experience in virtual settings - Real-time gesture recognition for avatars

Commercial Applications: Title: "Enhanced Avatar Creation Technology for Virtual Environments" This technology can be used in virtual reality games, virtual meetings, and other interactive virtual environments to create personalized avatars that mimic user gestures in real-time.

Questions about the technology: 1. How does this technology improve user engagement in virtual environments? 2. What are the potential limitations of using monocular images for avatar creation?

Original Abstract Submitted

a method comprises receiving a first sequence of images of a portion of a user, the first sequence of images being monocular images; generating an avatar based on the first sequence of images, the avatar being based on a model including a feature vector associated with a vertex; receiving a second sequence of images of the portion of the user; and based on the second sequence of images, modifying the avatar with a displacement of the vertex to represent a gesture of the avatar.