Unlock instant, AI-driven research and patent intelligence for your innovation.

Face super-resolution method and device based on hierarchical multi-scale residual fusion network

A fusion network and super-resolution technology, applied in the field of face image super-resolution, can solve the problem of ignoring the full utilization of face LR image features and so on.

Active Publication Date: 2022-05-10
WUHAN INSTITUTE OF TECHNOLOGY
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

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.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Face super-resolution method and device based on hierarchical multi-scale residual fusion network
  • Face super-resolution method and device based on hierarchical multi-scale residual fusion network
  • Face super-resolution method and device based on hierarchical multi-scale residual fusion network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] The present invention proposes a face super-resolution method based on a layered multi-scale residual fusion network. The face image super-resolution method uses a bottleneck attention module to obtain fine face features. Then a multi-scale residual module is used to extract the hierarchical structure information, and through the effective fusion of the extracted hierarchical structure information, better visual effects can be obtained.

[0040]figure 1 It is a schematic flow chart of a multi-scale residual fusion network face super-resolution method provided by an embodiment of the present invention, as shown in figure 2 As shown, the overall network structure of a face super-resolution method based on a layered multi-scale residual fusion network proposed by the present invention, through the convolution layer (Convolution Layer), bottleneck attention module (Bottleneck Attention Module), multi-scale Multi-scale Residual Module, Hierarchical Feature Fusion Layer and ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a face super-resolution method and device based on layered multi-scale residual fusion network, which belongs to the field of face image super-resolution. The method includes: downsampling the high-resolution face image to the target high-resolution face image, the target low-resolution image is divided into blocks, and after overlapping image blocks are separated, the bottleneck attention module is used to extract fine facial feature maps; the extracted fine facial feature maps are sent to multiple In the scale residual module, different convolutional layers are used to extract feature information in the multi-scale residual module, and feature information sharing is realized by means of crossover. Improved SR performance; feature fusion is used to update the feature map of the target low-resolution face image to produce high-resolution results. The network proposed by the present invention is superior to other latest human face image super-resolution algorithms, and can generate higher quality human face images.

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...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06T3/40G06K9/62G06N3/04G06N3/08G06V10/80G06V10/82
CPCG06T3/4053G06N3/08G06N3/045G06F18/253
Inventor 卢涛王宇张彦铎吴云韬陈灯
Owner WUHAN INSTITUTE OF TECHNOLOGY