Balanced Two-Stage Residual Networks for Image Super-Resolution

Yuchen Fan, Honghui Shi, Jiahui Yu, Ding Liu, Wei Han, Haichao Yu, Zhangyang Wang, Xinchao Wang, Thomas S. Huang; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2017, pp. 161-168

Abstract


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.

Related Material


[pdf]
[bibtex]
@InProceedings{Fan_2017_CVPR_Workshops,
author = {Fan, Yuchen and Shi, Honghui and Yu, Jiahui and Liu, Ding and Han, Wei and Yu, Haichao and Wang, Zhangyang and Wang, Xinchao and Huang, Thomas S.},
title = {Balanced Two-Stage Residual Networks for Image Super-Resolution},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {July},
year = {2017}
}