Paper Info
Title
Balanced Two-Stage Residual Networks for Image Super-Resolution.
Abstract
In this paper, balanced two-stage residual networks (BT SRN) 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).
Year
DOI
Venue
2017
10.1109/CVPRW.2017.154
IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
Field
DocType
Volume
Data mining,Logic gate,Source code,Computer science,Block design,Artificial intelligence,Image restoration,Artificial neural network,Residual,Pattern recognition,Ranking,Algorithm,Image resolution
Conference
2017
Issue
ISSN
Citations 
1
2160-7508
10
PageRank 
References 
Authors
0.50
28
9
Name
Order
Citations
PageRank
Yuchen Fan133217.14
Honghui Shi218320.24
Jiahui Yu326025.83
Ding Liu461132.97
Wei Han549613.24
Haichao Yu6163.02
Zhangyang Wang743775.27
Xinchao Wang847443.70
Thomas S. Huang9278152618.42