MODELING METHOD OF AUTOMATIC CHARACTER FACIAL EXPRESSION USING DEEP LEARNING TECHNOLOGY

摘要

The present invention relates to a deep learning based character facial expression generation method. According to an embodiment of the present invention, the deep learning based character facial expression generation method comprises: (a) a step of obtaining a plurality of three-dimensional facial expression data corresponding to a plurality of facial expressions of a specific person; (b) a step of designating a part of the plurality of three-dimensional facial expression data as a basic facial expression model; (c) a deep learning based facial expression modeling step of generating a three-dimensional facial expression model for each of the plurality of three-dimensional facial expression data based on differences from the basic facial expression model; and (d) a step of generating a facial expression of a character corresponding to the specific person according to the three-dimensional facial expression model. According to an embodiment of the present invention, a character capable of automatically acting a facial expression can be made only by photographing a person who makes an expression by using an RGBD camera technique and a deep learning technique.