TY - GEN
T1 - Image Super-Resolution via Dual-State Recurrent Networks
AU - Han, Wei
AU - Chang, Shiyu
AU - Liu, Ding
AU - Yu, Mo
AU - Witbrock, Michael
AU - Huang, Thomas S.
N1 - Publisher Copyright:
© 2018 IEEE.
Copyright:
Copyright 2019 Elsevier B.V., All rights reserved.
PY - 2018/12/14
Y1 - 2018/12/14
N2 - Advances in image super-resolution (SR) have recently benefited significantly from rapid developments in deep neural networks. Inspired by these recent discoveries, we note that many state-of-the-art deep SR architectures can be reformulated as a single-state recurrent neural network (RNN) with finite unfoldings. In this paper, we explore new structures for SR based on this compact RNN view, leading us to a dual-state design, the Dual-State Recurrent Network (DSRN). Compared to its single-state counterparts that operate at a fixed spatial resolution, DSRN exploits both low-resolution (LR) and high-resolution (HR) signals jointly. Recurrent signals are exchanged between these states in both directions (both LR to HR and HR to LR) via delayed feedback. Extensive quantitative and qualitative evaluations on benchmark datasets and on a recent challenge demonstrate that the proposed DSRN performs favorably against state-of-the-art algorithms in terms of both memory consumption and predictive accuracy. The code for our method is publicly available1.
AB - Advances in image super-resolution (SR) have recently benefited significantly from rapid developments in deep neural networks. Inspired by these recent discoveries, we note that many state-of-the-art deep SR architectures can be reformulated as a single-state recurrent neural network (RNN) with finite unfoldings. In this paper, we explore new structures for SR based on this compact RNN view, leading us to a dual-state design, the Dual-State Recurrent Network (DSRN). Compared to its single-state counterparts that operate at a fixed spatial resolution, DSRN exploits both low-resolution (LR) and high-resolution (HR) signals jointly. Recurrent signals are exchanged between these states in both directions (both LR to HR and HR to LR) via delayed feedback. Extensive quantitative and qualitative evaluations on benchmark datasets and on a recent challenge demonstrate that the proposed DSRN performs favorably against state-of-the-art algorithms in terms of both memory consumption and predictive accuracy. The code for our method is publicly available1.
UR - http://www.scopus.com/inward/record.url?scp=85062859914&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85062859914&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2018.00178
DO - 10.1109/CVPR.2018.00178
M3 - Conference contribution
AN - SCOPUS:85062859914
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 1654
EP - 1663
BT - Proceedings - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
PB - IEEE Computer Society
T2 - 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018
Y2 - 18 June 2018 through 22 June 2018
ER -