Face image restoration method based on multi-scale local self-attention generative adversarial network

Abstract

The invention relates to a face image restoration method based on a multi-scale local self-attention generative adversarial network. The method comprises the following steps: acquiring a face missing image and a corresponding mask, and performing preprocessing; constructing a multi-scale-based local self-attention generative adversarial network, and performing training modeling on the multi-scale-based local self-attention generative adversarial network by using the defective face image data set to obtain a face repair model; and through the multi-scale local self-attention generative adversarial network model, repairing the defect face image to be detected. According to the invention, the multi-scale structure and the dual-channel local self-attention module are added into the generative network, so that the technical problems of unstable training, low repair precision and efficiency, lack of symmetry and mode collapse of the generative adversarial network in the face repair problem are effectively solved, and an efficient, accurate and stable repair method is provided for face repair.

Description

technical field

[0001] The invention belongs to the technical field of computer face image repair, and in particular relates to a face image repair method based on multi-scale local self-attention generation confrontation network. Background technique

[0002] Image restoration refers to restoring the damaged area of ​​the image through certain technical means, so that it has good consistency with the surrounding features, and ensures that the repaired image has the same semantic content as the original image. At present, the classic algorithms for repairing face images mainly include diffusion-based algorithms and image block-based matching algorithms. However, these classic image inpainting algorithms are mainly based on mathematical and physical models, so the input image is required to contain information similar to the missing area, such as similar pixels, structures or image blocks, and new content cannot be generated. If there is a large area missing in the image, th...

Images