Computer Engineering and Applications ›› 2020, Vol. 56 ›› Issue (13): 210-215.DOI: 10.3778/j.issn.1002-8331.1906-0247

Previous Articles     Next Articles

Face Image Super-Resolution Based on Two-Layer Cascade Neural Network

LIU Jiapei, CAO Lin, DU Kangning   

  1. 1.Key Laboratory of the Ministry of Education for Optoelectronic Measurement Technology and Instrument, Beijing Information Science and Technology University, Beijing 100101, China
    2.School of Information and Communication Engineering, Beijing Information Science and Technology University, Beijing 100101, China
  • Online:2020-07-01 Published:2020-07-02

双层级联神经网络的人脸超分辨率重建

刘嘉佩,曹林,杜康宁   

  1. 1.北京信息科技大学 光电测试技术及仪器教育部重点实验室,北京100101
    2.北京信息科技大学 信息与通信工程学院,北京 100101

Abstract:

A two-layer cascade neural network is proposed for face super-resolution to solve the problems of the insufficient use of facial prior, facial features shifting and edge blurring in common deep learning based super-resolution methods. A facial prior estimation module is used in the net to capture the landmark information of the input and constrain the spatial consistency of the target image with the reconstructed image. Extensive experiments over CelebA and Helen datasets demonstrate that the proposed method is capable of accurately reconstructing facial features on frontal faces, and is also robust to different facial variations, such as side and occlusion face.

Key words: face image, super-resolution, cascade neural network, facial prior, landmark

摘要:

针对普通的基于卷积神经网络的人脸超分辨率方法未能结合人脸结构信息,重建图像易出现五官偏移、边缘模糊等问题,提出一种基于双层级联神经网络的人脸超分辨率重建方法。在重建网络中加入面部先验信息估计模块,捕捉输入图像的面部关键点信息,约束重建图像与目标图像的空间一致性。在CelebA与Helen数据集上的实验结果验证了该方法对正面人脸能够准确地重建面部五官,对侧面及遮挡人脸等不同的变形人脸也具有强鲁棒性。

关键词: 人脸图像, 超分辨率, 级联神经网络, 面部先验, 关键点