A specific animation face generation method, terminal equipment and storage medium

Abstract

The invention relates to a specific animation face generation method, terminal device and storage mediumanimation, and the method achieves the color pixel style migration and preliminary animation stylization from a real face to a animation face through combining with a conventional neural style migration technology based on a convolutional neural network. In combination with an existing style migration technology based on a generative adversarial network, domain style migration from a preliminarily animation stylized real face to a specific animation face is realized, and a animation real face image of a specific animation figure is obtained. According to the method, color features can be extracted, facial structure features can be maintained, and facial deformation is reduced; and a required image can be generated for a specific animation character.

Description

technical field [0001] The present invention relates to the technical field of animation image generation, in particular to a method for generating a specific animation face, a terminal device and a storage medium. Background technique [0002] As a leisure and hobby activity, animation has accompanied the growth of a large number of teenagers. Anime has always been loved by everyone because of its rich stories, delicate pictures, and fullness of characters. Detective Conan, One Piece, Pokémon and other classic animations are even more famous and popular. Therefore, there is a demand: many people are willing to animate their real face images, create animated real face images, or even animate real face images of specific anime characters. [0003] But the current situation is: it is time-consuming and labor-intensive to create animation of real human faces by comic writers, and there is no technology that can directly convert real human face images into specific animation c...

AI Technical Summary

Problems solved by technology

Although the existing style transfer technology based on generative confrontation networks can generate anime faces through random noise, it does not combine real faces to generate them, nor can it target the generation of specific anime characters; although it has been able to generate anime scenes from real scenes, However, when applied to human faces, it will cause problems such as facial deformation, and it is impossible to accurately generate animation images of real human faces.

[0006] On this basis, many new technologies have been extended and developed to realize photo sketching, photo animation stylization, comic avatar style transfer, etc., but they all have their own shortcomings, and it is impossible to realize the animation of specific animation characters.

Images