Method and device for driving animated image based on artificial intelligence

摘要

Disclosed is a method for driving an animation image based on artificial intelligence. When an animated image has a corresponding face pinch base and other animated images do not have a corresponding face pinch base, an animated image with a face pinch base can be used as a driving party image, and an animated image without a face pinch base is driven Can be used as a party image. The method includes: acquiring an expression base corresponding to the driven party image and an expression base corresponding to the driven party image; determining a mapping relationship between expression parameters according to the expression base corresponding to the driven party image and the expression base corresponding to the driven party image; and driving the driving party image by using the mapping relation and the known facial expression parameter of the driving party image according to the mapping relationship, so that the driven party image makes an actual facial expression identified by the known facial expression parameter. Therefore, the new animated image can be directly driven by the known expression parameters of other animated images without performing processing for obtaining the face pinch base corresponding to the new animated image, thereby increasing the push-out speed of the new animated images can do it