TY - GEN
T1 - Dual residual networks leveraging the potential of paired operations for image restoration
AU - Liu, Xing
AU - Suganuma, Masanori
AU - Sun, Zhun
AU - Okatani, Takayuki
N1 - Funding Information:
This work was partly supported by JSPS KAKENHI Grant Number JP15H05919, JST CREST Grant Number JPMJCR14D1, Council for Science, Technology and Innovation (CSTI), Cross-ministerial Strategic Innovation Promotion Program (Infrastructure Maintenance, Renovation and Management ), and the ImPACT Program Tough Robotics Challenge of the Council for Science, Technology, and Innovation (Cabinet Office, Government of Japan).
Publisher Copyright:
© 2019 IEEE.
PY - 2019/6
Y1 - 2019/6
N2 - In this paper, we study design of deep neural networks for tasks of image restoration. We propose a novel style of residual connections dubbed 'dual residual connection', which exploits the potential of paired operations, e.g., up-and down-sampling or convolution with large-and small-size kernels. We design a modular block implementing this connection style; it is equipped with two containers to which arbitrary paired operations are inserted. Adopting the 'unraveled' view of the residual networks proposed by Veit et al., we point out that a stack of the proposed modular blocks allows the first operation in a block interact with the second operation in any subsequent blocks. Specifying the two operations in each of the stacked blocks, we build a complete network for each individual task of image restoration. We experimentally evaluate the proposed approach on five image restoration tasks using nine datasets. The results show that the proposed networks with properly chosen paired operations outperform previous methods on almost all of the tasks and datasets.
AB - In this paper, we study design of deep neural networks for tasks of image restoration. We propose a novel style of residual connections dubbed 'dual residual connection', which exploits the potential of paired operations, e.g., up-and down-sampling or convolution with large-and small-size kernels. We design a modular block implementing this connection style; it is equipped with two containers to which arbitrary paired operations are inserted. Adopting the 'unraveled' view of the residual networks proposed by Veit et al., we point out that a stack of the proposed modular blocks allows the first operation in a block interact with the second operation in any subsequent blocks. Specifying the two operations in each of the stacked blocks, we build a complete network for each individual task of image restoration. We experimentally evaluate the proposed approach on five image restoration tasks using nine datasets. The results show that the proposed networks with properly chosen paired operations outperform previous methods on almost all of the tasks and datasets.
KW - Computational Photography
KW - Deep Learning
KW - Image and Video Synthesis
KW - Low-level Vision
KW - Vision Applications and Syst
UR - http://www.scopus.com/inward/record.url?scp=85078705814&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85078705814&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2019.00717
DO - 10.1109/CVPR.2019.00717
M3 - Conference contribution
AN - SCOPUS:85078705814
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 7000
EP - 7009
BT - Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
PB - IEEE Computer Society
T2 - 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
Y2 - 16 June 2019 through 20 June 2019
ER -