Method and device for generating face image and training model of face image and electronic equipment

Abstract

The embodiment of the invention provides a method and a device for generating a face image and training a model of the face image, and electronic equipment. The method for generating the human face image comprises the following steps: acquiring a first image containing human face coordinate information; obtaining a position parameter of a face local feature in the first image based on the first image and a principal component analysis base corresponding to the human face coordinate information; synthesizing a mask normal map generated based on the position parameters and a background image corresponding to the mask normal map to obtain a second image; generating a texture image corresponding to the second image through a generative adversarial network, and performing texture enhancement onthe second image based on the texture image to obtain a target human face image containing the human face feature normal information and the human face texture information. According to the invention, the accuracy of the face features is ensured, the consistency of the human face texture information and the normal information is improved, and the details and authenticity of the human face image are ensured.

Description

technical field [0001] The present application relates to the field of computer technology, in particular, to a method, device, computer-readable medium and electronic equipment for generating face images and model training thereof. Background technique [0002] In some 3D application scenarios, it is necessary to shape the facial image of the human face. At the same time, accurate and subtle facial texture information is required during the facial shaping process, such as key information such as the pores, eyebrows, and beard of the human face. Generally, the face is shaped by the facial normal map, but the normal map obtained in this way is blurred and the details of the facial texture information are not clear, or the normal map and the face texture information are inconsistent, which reduces the effect of facial shaping. . Contents of the invention [0003] Embodiments of the present application provide a method, device, computer-readable medium, and electronic equipm...

AI Technical Summary

Problems solved by technology

Generally, the face is shaped by the facial normal map, but the normal map obtained in this way is blurred and the details of the facial texture information are not clear, or the normal map and the face texture information are inconsistent, which reduces the effect of facial shaping.

Images