Face image fusion method and device and calculation device

Abstract

A face image fusion method disclosed by the present invention is suitable for fusing the face of a target image into the face of a material image, and comprises the steps of respectively calculating the three dimensional models of the faces in the material image and the target image as a first three dimensional model and a second three dimensional model; respectively calculating a first projection matrix and a second projection matrix projected by the first and second three dimensional models to a plane; according to the first three dimensional model and the first projection matrix, calculating a first texture coordinate of the face in the material image; according to the second three dimensional model and the second projection matrix, calculating a second texture coordinate of the face in the target image; using the second texture coordinate to replace the first texture coordinate correspondingly to obtain a reconstructed face image of the target image; and fusing the reconstructed face image of the target image and the material image to generate a fused image. The present invention also discloses a corresponding face image fusion device and a calculation device.

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