TY - GEN
T1 - Balanced Two-Stage Residual Networks for Image Super-Resolution
AU - Fan, Yuchen
AU - Shi, Honghui
AU - Yu, Jiahui
AU - Liu, Ding
AU - Han, Wei
AU - Yu, Haichao
AU - Wang, Zhangyang
AU - Wang, Xinchao
AU - Huang, Thomas S.
N1 - Publisher Copyright:
© 2017 IEEE.
PY - 2017/8/22
Y1 - 2017/8/22
N2 - In this paper, balanced two-stage residual networks (BTSRN) are proposed for single image super-resolution. The deep residual design with constrained depth achieves the optimal balance between the accuracy and the speed for super-resolving images. The experiments show that the balanced two-stage structure, together with our lightweight two-layer PConv residual block design, achieves very promising results when considering both accuracy and speed. We evaluated our models on the New Trends in Image Restoration and Enhancement workshop and challenge on image super-resolution (NTIRE SR 2017). Our final model with only 10 residual blocks ranked among the best ones in terms of not only accuracy (6th among 20 final teams) but also speed (2nd among top 6 teams in terms of accuracy). The source code both for training and evaluation is available in https://github.com/ychfan/sr-ntire2017.
AB - In this paper, balanced two-stage residual networks (BTSRN) are proposed for single image super-resolution. The deep residual design with constrained depth achieves the optimal balance between the accuracy and the speed for super-resolving images. The experiments show that the balanced two-stage structure, together with our lightweight two-layer PConv residual block design, achieves very promising results when considering both accuracy and speed. We evaluated our models on the New Trends in Image Restoration and Enhancement workshop and challenge on image super-resolution (NTIRE SR 2017). Our final model with only 10 residual blocks ranked among the best ones in terms of not only accuracy (6th among 20 final teams) but also speed (2nd among top 6 teams in terms of accuracy). The source code both for training and evaluation is available in https://github.com/ychfan/sr-ntire2017.
UR - http://www.scopus.com/inward/record.url?scp=85030220628&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85030220628&partnerID=8YFLogxK
U2 - 10.1109/CVPRW.2017.154
DO - 10.1109/CVPRW.2017.154
M3 - Conference contribution
AN - SCOPUS:85030220628
T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
SP - 1157
EP - 1164
BT - Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017
PB - IEEE Computer Society
T2 - 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2017
Y2 - 21 July 2017 through 26 July 2017
ER -