计算机应用与软件2024，Vol.41Issue(7)：200-206,7.DOI:10.3969/j.issn.1000-386x.2024.07.030
基于先验特征与谱归一化的人脸超分辨
FACE SUPER-RESOLUTION BASED ON PRIOR FEATURES AND SPECTRAL NORMALIZATION
摘要
Abstract
The purpose of image super-resolution technology is to convert low-resolution(LR)images into high-resolution(HR)images without losing information.The realization of this technology on portraits has a wide range of application scenarios such as face recognition,face alignment,etc.,but the traditional super-resolution method has a low degree of recovery on face images and is unstable.In this regard,we propose a SN-FSRGAN model.Face prior features were used to guide super-resolution;and spectral normalization was introduced to stabilize GAN-based super-resolution network training results.Experiments on the Helen and CelebA datasets show that the proposed method has achieved better results in terms of PSNR,SSIM and visual senses compared with models such as ESRGAN and FSRGAN.关键词
人脸超分辨/生成对抗网络/人脸先验特征/谱归一化Key words
Face super-resolution/GAN/Face prior features/Spectral normalization分类
信息技术与安全科学引用本文复制引用
万杰林,冷拓,倪超杰..基于先验特征与谱归一化的人脸超分辨[J].计算机应用与软件,2024,41(7):200-206,7.基金项目
国家自然科学基金项目(12071282). （12071282）
