吉林大学学报（理学版）2024，Vol.62Issue(4)：895-904,10.DOI:10.13413/j.cnki.jdxblxb.2023204
基于3D先验特征的人脸超分辨率重建算法
Facial Super-resolution Reconstruction Algorithm Based on 3D Prior Features
摘要
Abstract
In order to effectively solve the problem of facial super-resolution feature recovery in complex environments,we proposed a novel facial super-resolution network.By integrating 3D rendering prior knowledge and a dual attention mechanism,the network enhanced the understanding of the facial spatial position and overall structure while improving the ability to recover detailed information.The experimental results on the CelebAMask-HQ dataset show that the proposed algorithm achieves peak signal-to-noise ratio and structural similarity of 28.76 dB and 0.827 5 for downsampled faces magnified by 4 times,and 26.29 dB and 0.754 9 for downsampled faces magnified by 8 times.Compared with the similar SAM3D algorithm,the proposed algorithm improves the peak signal-to-noise ratio and structural similarity by 4.09 and 1.93 percentage points when dealing with 4 times downsampling,and by 2.02 and 4.54 percentage points when dealing with 8 times downsampling,respectively.This proves the superiority of the proposed algorithm and also indicates that facial super-resolution recovery can achieve more realistic and clear visual effects in practical applications.关键词
机器视觉/人脸超分辨率/3D先验/注意力机制Key words
machine vision/facial super-resolution/3D prior/attention mechanism分类
信息技术与安全科学引用本文复制引用
姚汉群,刘广文,王超,杨依宁,才华,付强..基于3D先验特征的人脸超分辨率重建算法[J].吉林大学学报（理学版）,2024,62(4):895-904,10.基金项目
国家自然科学基金重大项目(批准号:61890963)和吉林省科技发展计划项目(批准号:20210204099YY). （批准号:61890963）
