A method and device for driving an animation image based on artificial intelligence

Abstract

The embodiment of the present application discloses an artificial intelligence-based animation image driving method. When an animation image has a corresponding pinch-face base, and an animation image does not have a corresponding pinch-face base, the one with the pinch-face base can be used as the driving method. The image does not have the image of the driven party as the pinch face base. Obtain the expression base corresponding to the image of the driver and the expression base corresponding to the image of the driven party, and determine the mapping relationship between the expression parameters according to the expression base corresponding to the image of the driver and the expression base corresponding to the image of the driven party. According to the mapping relationship, The avatar of the driven party is driven by using the known expression parameters of the driving party avatar and the aforementioned mapping relationship, so that the avatar of the driven party makes the actual expression identified by the known expression parameters. As a result, the new animation image can be directly driven by the known expression parameters of other animation images without processing the face-pinching base corresponding to the new animation image, which speeds up the introduction of the new animation image.

Description

technical field [0001] The present application relates to the field of data processing, in particular to an artificial intelligence-based animation image driving method and device. Background technique [0002] At present, human-computer interaction is relatively common, and users can interact with animated images. For any segment of speech, the driving network can drive an animated image to make the mouth shape corresponding to the segment of speech. In this scenario, the presence of animated images can greatly enhance the sense of reality, improve expressiveness, and bring users a more immersive experience. Animated images can be obtained in various ways, such as being manually designed by a designer. [0003] When an animation image is driven through a driving network, it is often required that the animation image has corresponding expression bases and pinching face bases. The expression base is composed of deformable networks representing different expressions. Each d...

AI Technical Summary

Problems solved by technology

However, the face-pinching base itself is obtained by decomposing a large amount of face data through principal component analysis. It has no clear semantic information and is not accurately associated with the mesh vertices of the model. It is difficult to obtain by manual design.

As a result, the corresponding pinch-face base can only be determined through complex data processing, which delays the launch of new animation images

Images