METHOD AND APPARATUS FOR GENERATING VIRTUAL AVATAR, DEVICE, STORAGE MEDIUM AND COMPUTER PROGRAM

摘要

Embodiments of the present application relate to the field of deep learning and image technology, and in particular, to the field of internet software technology, and discloses a method, an apparatus, a device, and a storage medium for creating a virtual shape. A specific implementation method is, based on at least two real facial feature templates, determining a template coefficient of a target face among images to be processed, and at least two virtual facial feature templates related to the template coefficient and the at least two real facial feature templates. According to, the virtual shape of the target face is determined. The technical solution of the embodiment of the present application may improve the biofidelity of the virtual shape while performing virtualization on the target face.