Face super-resolution method and device based on multi-view texture learning

A multi-view, low-resolution technology, applied in the field of face image super-resolution, can solve the problems of multi-view image limitations of face super-resolution algorithm, and achieve the effect of improving reconstruction performance

Active Publication Date: 2020-03-27
WUHAN INSTITUTE OF TECHNOLOGY +1
View PDF5 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, single-input face super-resolution algo...

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 multi-view texture learning
  • Face super-resolution method and device based on multi-view texture learning
  • Face super-resolution method and device based on multi-view texture learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not constitute a conflict with each other.

[0036] The present invention proposes a method for realizing face super-resolution based on learning multi-view texture compensation. The face image super-resolution method uses multi-view texture compensation to combine two face images to generate a high-resolution image as an output. Use the texture attention mechanism to transfer high-precision texture compensation information to the fixed vi...

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 multi-view texture learning. The method belongs to the field of human face image super-resolution, and comprises the following steps: firstly, down-sampling a high-resolution human face image pair to a target low-resolution human face image pair, carrying out blocking operation on the target low-resolution human face imagepair, separating out mutually overlapped image blocks, and extracting facial texture multi-scale features by using a residual pooling module network; then, the extracted face multi-scale features aresent to a texture attention module, texture information is fused and compensated by calculating an attention map, the most similar features are collected, and the SR performance is more effectively improved. Finally, a feature map of the target view image is updated by feature fusion to produce a high resolution result. The network provided by the invention is superior to other latest face image super-resolution algorithms, and a face image with higher quality can be generated.

Description

technical field [0001] The invention belongs to the field of super-resolution of human face images, and more specifically relates to a method and device for super-resolution of human faces based on multi-view texture learning. Background technique [0002] Face super-resolution (super resolution, SR) can reconstruct a high-resolution (High Resolution, HR) image from one or more low-resolution (Low Resolution, LR) input images. Due to its excellent ability to reconstruct image details, face SR is widely used in video surveillance, face recognition, entertainment, etc. Generally, face image super-resolution methods include three typical methods: interpolation-based, reconstruction-based and learning-based methods. Because the learning-based face super-resolution method utilizes additional prior knowledge from training samples to achieve the reconstruction task. Therefore, learning-based face image super-resolution has become more and more popular in recent years. [0003] A...

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
IPC IPC(8): G06T3/40G06T7/33G06T7/49G06K9/62
CPCG06T3/4053G06T7/337G06T7/49G06T2207/20021G06T2207/20221G06F18/253Y02D10/00
Inventor 卢涛王宇张彦铎姚全锋杨泳吴昊石子慧石仝彤陈冲许若波周强郝晓慧魏博识郎秀娟吴志豪王彬陈中婷王布凡刘奥琦陈润斌
Owner WUHAN INSTITUTE OF TECHNOLOGY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap