Extracting method, system and device for virtual character expressions and actions and medium

Abstract

The invention discloses a virtual character expression action extraction method, device and apparatus, and a storage medium. The method comprises the following steps: acquiring a character action video; and extracting character action information from the character action video, constructing a character action library, obtaining a corresponding lip image according to a voice signal, embedding thelip image into a face image corresponding to the character action library; generating an image containing character expressions and actions; and extracting character expression actions from the image.Different second label information can be generated by constructing a character action library and simply modifying two-dimensional point coordinates or the shape of a two-dimensional mask, so that the content of the character action library can be enriched; according to the method, different expression actions can be extracted at any time while the character expression action extraction operation is simplified, rich character action libraries can be provided, new actions can be conveniently added into the character action libraries, and the working efficiency is improved. The method is widely applied to the technical field of image processing.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to a method, system, device and storage medium for extracting facial expressions of virtual characters. Background technique [0002] The extraction of existing avatar expressions and actions is usually based on the High Fidelity of 3D cameras, which captures human expressions and head movements, such as blinking and lip movements, and synchronizes them to the avatar, providing flexible scene editing and richer interactions. However, such applications rely on auxiliary peripherals, such as 3D cameras; and most of the existing all-round experience types only capture parameters such as user blinks, mouth shapes, and head movements, lacking the capture of facial expressions and lack of understanding of facial expressions. Simultaneous capture of body movements; at the same time, in the process of arriving at the virtual character, it is necessary to manually mark t...

AI Technical Summary

Problems solved by technology

[0002] Existing extraction of facial expressions and movements of virtual characters is usually based on the High Fidelity of 3D cameras, capturing human expressions and head movements, such as blinking and lip movements, and synchronizing them to virtual characters, providing flexible scene editing and richer interactions experience, but such applications rely on auxiliary peripherals, such as 3D cameras, etc.; and most of the existing omni-directional experience models only capture parameters such as user blinks, mouth movements, and head movements, lacking in capturing facial expressions and lack of expression recognition. Synchronous capture with body movements; at the same time, in the process of getting to the virtual character, it is necessary to manually mark the corresponding expressions or movements one by one, and the work efficiency is low

Images