Human face super-resolution method and device based on layered multi-scale residual fusion network

Abstract

The invention discloses a human face super-resolution method and device based on a layered multi-scale residual fusion network, and belongs to the field of human face image super-resolution, and the method comprises the steps: downsampling a high-resolution human face image to a target low-resolution human face image, partitioning the target low-resolution image to acquire overlapped image blocksafter partitioning of the overlapped image blocks; extracting a fine facial feature map by using a bottleneck attention module; sending the extracted fine facial feature map to a multi-scale residualerror module, extracting feature information by using different convolution layers in the multi-scale residual error module to share feature information by using a cross mode, and achieve multi-scalefeature information fusion by using a jump connection mode outside the multi-scale residual error module so as to more effectively improve SR performance; and updating a feature map of the target low-resolution face image through feature fusion to generate a high-resolution result. The network provided by the invention is superior to other latest face image super-resolution algorithms, and a faceimage with higher quality can be generated.

Description

technical field [0001] The invention belongs to the technical field of face image super-resolution, and more specifically relates to a face super-resolution method and device based on a layered multi-scale residual fusion network. Background technique [0002] Face super-resolution (Super-Resolution, SR) is a technology that infers potential high-resolution (High Resolution, HR) images from input low-resolution (Low Resolution, LR) face images, which can significantly enhance Detailed information of LR face images. Therefore, it is widely used in face recognition, criminal investigation, entertainment and other fields. [0003] Although face SR is also classified as natural image SR, most natural image based deep learning SR methods are not suitable for this case. Since the face structure has many prior knowledge different from natural images, natural image SR methods cannot fully utilize the unique prior information of face images, which makes the face SR task different f...

AI Technical Summary

Problems solved by technology

However, most of the existing face SR methods blindly increase the network depth in order to improve network performance, while ignoring the full utilization of face LR image features.

Images