Face image processing method, device, electronic device and storage medium

Abstract

The present disclosure provides a face image processing method, device, electronic equipment, and storage medium, and relates to technical fields such as image processing, augmented reality, computer vision, and deep learning. The method includes: obtaining a three-dimensional face model of a face image to be processed, the three-dimensional face model including a plurality of grid nodes; determining the area to be transformed of the three-dimensional face model; The rigid transformation relationship between them; based on the rigid transformation relationship, the area to be transformed is processed to obtain a stylized face model corresponding to the face image to be processed. The disclosed technical solution is based on the rigid transformation relationship between the standard three-dimensional face model and the standard stylized face model, and processes the area to be transformed of the face image to be processed, so that the stylized face model obtained in this way maintains the stylization Under the premise of the overall style of the face model, the similarity between the stylized face model and the face image to be processed is greatly improved.

Description

technical field [0001] The present disclosure relates to the field of computer technology, in particular to fields such as image processing, augmented reality, computer vision, and deep learning. Background technique [0002] With the gradual digitalization and virtualization of people's life content, and the popularization of concepts such as digital world and digital twin, the application demand of virtual reality and augmented reality is bound to explode. As an important proxy form of people in the digital world, avatars currently rely on designer customization for their personalized production, which is expensive. Generally speaking, it costs tens of thousands of dollars to produce a low-quality proxy model. If you customize a high-precision model, for example, making a digital host with a high degree of similarity for a specific person, the cost is generally around 1 million. [0003] In order to reduce the cost, the personalized virtual image solution in the prior art...

AI Technical Summary

Problems solved by technology

Although the face reconstruction process can restore the shape of the face in the photo, the subsequent stylized model generation process will naturally weaken the face features of the original image due to the need to show style features such as big eyes and small noses

Images