Image Super-resolution Based on Recursive Residual Networks

被引：0
|
作者：
Zhou D.-W. [1 ]
Zhao L.-J. [1 ]
Duan R. [1 ]
Chai X.-L. [1 ]
机构：
[1] School of Control and Computer Engineering, North China Electric Power University, Beijing
来源：
Zidonghua Xuebao/Acta Automatica Sinica | 2019年 / 45卷 / 06期
关键词：
Convolutional neural network; Deep learning; Recursive structure; Residual learning; Super-resolution;
D O I：
10.16383/j.aas.c180334
中图分类号：
学科分类号：
摘要：
Despite the great success in single image super-resolution reconstruction achieved by deep convolutional neural network, the number of the computational parameters is often very large. This paper proposes a concise and compact recursive residual network. The local residual learning method is adopted to mitigate the di-culty of training very deep network, the recursive structure is conflgured to control the number of model parameters while increasing the model depth, the adjustable gradient clipping strategy is applied to prevent the gradient disappearance/gradient explosion, and a deconvolutional layer is set to directly up sample the image to a super-resolution image at the end of the residual network. According to benchmark tests, in the premise that the same quality super-resolution image is reconstructed, the number of parameters and the computational complexity of the proposed method are reduced to about 1/10 and 1/(2n2) of VDSR, respectively. Copyright © 2019 Acta Automatica Sinica. All rights reserved.
引用
收藏
页码：1157 / 1165
页数：8
相关论文
共 34 条
  • [1] Oktay O., Bai W., Lee M., Guerrero R., Kamnitsas K., Caballero J., Et al., Multi-input cardiac image super-resolution using convolutional neural networks, Proceedings of the 2016 International Conference on Medical Image Computing and Computer-assisted Intervention, pp. 246-254, (2016)
  • [2] Luo Y., Zhou L., Wang S., Wang Z.Y., Video satellite imagery super resolution via convolutional neural networks, IEEE Geoscience and Remote Sensing Letters, 14, 12, pp. 2398-2402, (2017)
  • [3] Rasti P., Uiboupin T., Escalera S., Anbarjafari G., Convolutional neural network super resolution for face recognition in surveillance monitoring, Proceedings of the 2016 International Conference on Articulated Motion and Deformable Objects, pp. 175-184, (2016)
  • [4] Lu Z.-F., Zhong B.-J., Image interpolation with predicted gradients, Acta Automatica Sinica, 44, 6, pp. 1072-1085, (2018)
  • [5] Xiong J.-J., Lu H.-Y., Zhang M.-H., Liu Q., Convolutional sparse coding in gradient domain for MRI reconstruction, Acta Automatica Sinica, 43, 10, pp. 1841-1849, (2017)
  • [6] Dong C., Chen C.L., He K.M., Tang X.O., Learning a deep convolutional network for image super-resolution, Proceedings of the 13th European Conference on Computer Vision, pp. 184-199, (2014)
  • [7] Dong C., Chen C.L., Tang X.O., Accelerating the supersesolution convolutional neural network, Proceedings of the 14th European Conference on Computer Vision, pp. 391-407, (2016)
  • [8] Kim J., Lee J.K., Lee K.M., Accurate image super-resolution using very deep convolutional networks, Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1646-1654, (2016)
  • [9] Lim B., Son S., Kim H., Nah S., Lee K.M., Enhanced deep residual networks for single image super-resolution, Proceedings of the 2017 IEEE Computer Vision and Pattern Recognition Workshops, pp. 1132-1140, (2017)
  • [10] Lai W.S., Huang J.B., Ahuja N., Yang M.H., Deep laplacian pyramid networks for fast and accurate super-resolution, Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, pp. 5835-5843, (2017)
1234