Image processing method and device and device for image processing

Abstract

The embodiment of the invention provides an image processing method and device and a device for image processing. The method comprises the following steps: acquiring a first texture image corresponding to a first face image and a second texture image corresponding to a second face image; performing fusion processing on the first texture image and the second texture image based on a first dynamic mask to obtain a fused texture image, the first dynamic mask being used for indicating a to-be-fused region in the first face image; and rendering the second face image based on the fused texture image to obtain a target face image. According to the embodiment of the invention, the fusion region of the image can be limited within an effective range, and the face boundary of the preset to-be-fused region is fitted, so that the accuracy of face fusion is improved; and moreover, according to the embodiment of the invention, the color stability and authenticity of the generated target face image can be ensured, and the image quality of the generated target face image is improved.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to an image processing method, device and device for image processing. Background technique [0002] With the approach of computer technology, face generation technology has also been greatly developed. For example, through face generation technology, the face in the template image can be replaced with the face in the target image, or, through face generation technology, the features such as facial expressions in the template image can be changed to obtain a series of dynamic transformations face images. [0003] At present, there are mainly two methods for generating face images: the face image generation method based on deep learning and the face image generation method based on 3D face reconstruction. However, in the face image generation method based on deep learning, the face generation process is often driven by feature points, which cannot flexibly control the exp...

AI Technical Summary

Problems solved by technology

However, the face image generation method based on deep learning is often driven by feature points, which cannot flexibly control the expression and texture changes of the face; while the face image generation method based on 3D face reconstruction relies heavily on For datasets with multi-view images of the same person, the current frame will be affected by previous frames, and artifacts will be accumulated and magnified when generating longer videos

In short, the face images generated by the existing face generation methods are not realistic enough and the image quality is poor.

Images