# US 2018/0025506 A1 · Avatar-based video encoding

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

- Number: US 2018/0025506 A1
- Document ID: US20180025506A1
- Status: Published application
- Kind: A1
- Application number: 15/450,295
- Filed: 2017-03-06
- Published: 2018-01-25
- Earliest claimed: 2013-12-18
- Assignees: Intel Corporation
- Applicants: Intel Corporation
- Inventors: Wenlong Li; Yangzhou Du; Xiaofeng Tong
- Web page: https://patentgrep.com/patent/US20180025506A1

## CPC

- G06T 7/73: using feature-based methods
- G06T 13/40: of characters, e.g. humans, animals or virtual beings
- G06T 13/80: Two-dimensional [2D] animation, e.g. using sprites
- G06V 40/171: {Local features and components; Facial parts (eye characteristics G06V40/18); Occluding parts, e.g. glasses; Geometrical relationships}
- G06V 40/176: {Dynamic expression}
- H04N 7/147: {Communication arrangements, e.g. identifying the communication as a video-communication, intermediate storage of the signals (selecting H04Q)}
- H04N 7/157: {defining a virtual conference space and using avatars or agents (computer conference optimisation or adaptation H04L12/1827)}
- G06T 2207/30201: Face
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION

## Abstract

Techniques are disclosed for performing avatar-based video encoding. In some embodiments, a video recording of an individual may be encoded utilizing an avatar that is driven by the facial expression(s) of the individual. In some such cases, the resultant avatar animation may accurately mimic facial expression(s) of the recorded individual. Some embodiments can be used, for example, in video sharing via social media and networking websites. Some embodiments can be used, for example, in video-based communications (e.g., peer-to-peer video calls; videoconferencing). In some instances, use to the disclosed techniques may help to reduce communications bandwidth use, preserve the individual's anonymity, and/or provide enhanced entertainment value (e.g., amusement) for the individual, for example.

## Claims

### Claim 1

A non-transitory computer-readable medium encoded with instructions that, when executed by one or more processors, cause a process for to be carried out, the process comprising:
extracting from a video a video frame that captures a front-face image of a person;
constructing from the front-face image of the person an avatar model configured to be animated based on one or more facial expressions of the person previously detected; and
reconstructing the recorded video as an avatar-based video using the avatar model, wherein reconstructing comprises categorizing a movement of the user in the recorded video as a facial expression movement, and processing the movement as a facial expression in response to categorizing the movement.