TY - JOUR
T1 - Face Super-Resolution via Joint Edge Information and Attention Aggregation Network
AU - Yu, Yue
AU - Jiang, Jielin
AU - Chang, Heyou
AU - Zheng, Hao
AU - Wang, Shuihua
N1 - Publisher Copyright:
© 2023 Elsevier Ltd
PY - 2023/10
Y1 - 2023/10
N2 - Face super-resolution (SR) is a specialized image super-resolution problem that is particularly relevant in various intelligent transportation scenes such as video surveillance and identification systems. Deep learning-steered solutions for face images often leverage facial priors (i.e., face parsing and landmark) to restore intricate facial components and have demonstrated promising performance. However, these methods typically rely on abundant manually labeled data and require lengthy training times. In this work, we introduce a meaningful approach called the Joint Edge Information and Attention Aggregation Network (JEANet) for the face SR problem. JEANet is established on our carefully designed Face Attention Aggregation Module (FAAM), which incorporates parallel connections of both channel-wise and spatial-wise features. Specifically, we integrate an attention fusion strategy into the residual blocks and elaborately employ edge blocks to extract edge information. Additionally, we introduce adaptive shortcuts that interpolate reconstruction parts at multiple scales. With the aid of adaptive shortcuts, JEANet effectively restores detailed images textures by leveraging contextual features optimally. These considerations enable the convolutional operations to flexibly distill information related to primary facial structures and progressively incorporate edge information to assemble local and global meaningful structures. Qualitative and quantitative evaluations demonstrate that our proposed method excels in recovering highly realistic face images compared to several competitive face SR methods.
AB - Face super-resolution (SR) is a specialized image super-resolution problem that is particularly relevant in various intelligent transportation scenes such as video surveillance and identification systems. Deep learning-steered solutions for face images often leverage facial priors (i.e., face parsing and landmark) to restore intricate facial components and have demonstrated promising performance. However, these methods typically rely on abundant manually labeled data and require lengthy training times. In this work, we introduce a meaningful approach called the Joint Edge Information and Attention Aggregation Network (JEANet) for the face SR problem. JEANet is established on our carefully designed Face Attention Aggregation Module (FAAM), which incorporates parallel connections of both channel-wise and spatial-wise features. Specifically, we integrate an attention fusion strategy into the residual blocks and elaborately employ edge blocks to extract edge information. Additionally, we introduce adaptive shortcuts that interpolate reconstruction parts at multiple scales. With the aid of adaptive shortcuts, JEANet effectively restores detailed images textures by leveraging contextual features optimally. These considerations enable the convolutional operations to flexibly distill information related to primary facial structures and progressively incorporate edge information to assemble local and global meaningful structures. Qualitative and quantitative evaluations demonstrate that our proposed method excels in recovering highly realistic face images compared to several competitive face SR methods.
KW - Attention mechanism
KW - Edge block
KW - Face super-resolution
KW - Residual block
UR - http://www.scopus.com/inward/record.url?scp=85170080728&partnerID=8YFLogxK
U2 - 10.1016/j.compeleceng.2023.108931
DO - 10.1016/j.compeleceng.2023.108931
M3 - Article
AN - SCOPUS:85170080728
SN - 0045-7906
VL - 111
JO - Computers and Electrical Engineering
JF - Computers and Electrical Engineering
M1 - 108931
ER -