Fusion method, device and computing equipment for a human face image

Abstract

The invention discloses a face image fusion method, which is suitable for merging the face in the target image into the face in the material image, comprising the steps of: separately calculating the three-dimensional models of the face in the material image and the target image, As the first three-dimensional model and the second three-dimensional model; respectively calculate the first projection matrix and the second projection matrix of the first three-dimensional model and the second three-dimensional model projected onto the plane; calculate the material image according to the first three-dimensional model and the first projection matrix The first texture coordinates of the face in the middle; calculate the second texture coordinates of the face in the target image according to the second three-dimensional model and the second projection matrix; replace the first texture coordinates with the second texture coordinates to obtain the reconstructed target image and merging the reconstructed face image of the target image with the material image to generate a fused image. The invention also discloses a corresponding human face image fusion device and computing equipment.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a fusion method, device and computing equipment of human face images. Background technique [0002] In the process of daily shooting and socializing, users hope to replace the face in one image with another, commonly known as face swapping. In the face-changing application, the face in the target image is usually fused (also called "replacement") into the corresponding face position in the source image. [0003] The common method used in existing face-changing applications is to cut out the face (or head) of a person A in the target image along the contour line, and then replace it with the face of person B in the source image. Face replacement can meet the needs of some users. However, it is difficult to replace two faces with a large difference in posture in the image, and generally serious facial features will be deformed, which is difficult to meet the needs of use...

AI Technical Summary

Problems solved by technology

However, it is difficult to replace two faces with a large difference in posture in the image, and generally there will be serious facial deformation, which is difficult to meet the needs of users

In addition, due to the different lighting and viewing angles when different images are taken, if the face part is directly replaced, it may cause mismatching of the color tone and incongruity between the character and the background due to the inconsistency between the face and the background color.

[0004] Therefore, there is a need for a face-changing application that can effectively solve problems such as face deformation caused by posture and other problems, and the inconsistency between the face and the background of the original image.

Images