Method and device for creating head avatar using shot video
AssigneeKorea Institute of Science and Technology
InventorsJunseok Kang, Sangchul Ahn
Life of this patent
Estimating the term…
Abstract
According to a method and device for generating a head avatar using a shot video, a head mesh of neutral look and a head texture map of neutral look are generated based on a base mesh of a base model and at least one shooting image representing a face of neutral look among a plurality of shooting images generated from a camera shot video, and a head mesh reflecting a certain facial expression and a head texture reflecting the certain facial expression are generated based on at least one shooting image representing a face of a certain facial expression among the plurality of shooting images, the head mesh of neutral look, and the head texture map of neutral look.
Claims18
A method of creating a head avatar, the method comprising:
- inputting a shot video obtained by shooting a face of a shooting target using a camera and a base model that is a mesh model representing a shape of a head of a person;
- generating a plurality of shooting images representing a face of neutral look of the shooting target and a face of a certain facial expression of the shooting target from the input shot video;
- generating a head mesh of neutral look of the shooting target and a head texture map of neutral look of the shooting target based on the base mesh of the input base model and at least one shooting image representing the face of neutral look among the plurality of generated shooting images;
- and
- generating a head mesh reflecting the certain facial expression and a head texture reflecting the certain facial expression based on at least one shooting image representing a face of the certain facial expression among the plurality of generated shooting images, the generated head mesh of neutral look, and the generated head texture map of neutral look.
An avatar creation device comprising:
- a data input unit configured to receive a shot video obtained by shooting a face of a shooting target using a camera and a base model that is a mesh model representing a shape of a head of a person;
- a preprocessor configured to generate a plurality of shooting images representing a face of neutral look of the shooting target and a face of a certain facial expression of the shooting target from the input shot video;
- a first head avatar creation unit configured to generate a head mesh of neutral look of the shooting target and a head texture map of neutral look of the shooting target based on at least one shooting image representing the face of neutral look among the plurality of generated shooting images and the base mesh of the input base model;
- and
- a second head avatar creation unit configured generate a head mesh reflecting the certain facial expression and a head texture reflecting the certain facial expression based on at least one shooting image representing a face of the certain facial expression among the plurality of generated shooting images, the generated head mesh of neutral look, and the generated head texture map of neutral look.
Dependencies are inferred from the claim text.