Learning wavelet coefficients for face super-resolution

被引:0
作者
Liu Ying
Sun Dinghua
Wang Fuping
Lim Keng Pang
Chiew Tuan Kiang
Lai Yi
机构
[1] Xi’an University of Posts and Telecommunications,Key Laboratory of Electronic Information Processing for Crime Scene Investigation
[2] Ministry of Public Security,undefined
[3] Xsecpro Pte Ltd,undefined
[4] Rekindle Pte Ltd,undefined
[5] International Joint-Research Center for Wireless Communication and Information Processing,undefined
来源
The Visual Computer | 2021年 / 37卷
关键词
Deep learning; CNN; Wavelet; Super-resolution;
D O I
暂无
中图分类号
学科分类号
摘要
Face image super-resolution imaging is an important technology which can be utilized in crime scene investigations and public security. Modern CNN-based super-resolution produces excellent results in terms of peak signal-to-noise ratio and the structural similarity index (SSIM). However, perceptual quality is generally poor, and the details of the facial features are lost. To overcome this problem, we propose a novel deep neural network to predict the super-resolution wavelet coefficients in order to obtain clearer facial images. Firstly, this paper uses prior knowledge of face images to manually emphases relevant facial features with more attention. Then, a linear low-rank convolution in the network is used. Finally, image edge features from canny detector are applied to enhance super-resolution images during training. The experimental results show that the proposed method can achieve competitive PSNR and SSIM and produces images with much higher perceptual quality.
引用
收藏
页码:1613 / 1622
页数:9
相关论文
共 27 条
[21]  
Huang H(undefined)undefined undefined undefined undefined-undefined
[22]  
He R(undefined)undefined undefined undefined undefined-undefined
[23]  
Sun Z(undefined)undefined undefined undefined undefined-undefined
[24]  
Mallat SG(undefined)undefined undefined undefined undefined-undefined
[25]  
Zhao H(undefined)undefined undefined undefined undefined-undefined
[26]  
Gallo O(undefined)undefined undefined undefined undefined-undefined
[27]  
Frosio I(undefined)undefined undefined undefined undefined-undefined