Share Email Print
cover

Proceedings Paper • new

Single image super-resolution based on convolutional neural networks
Author(s): Lamei Zou; Ming Luo; Weidong Yang; Peng Li; Liujia Jin
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

We present a deep learning method for single image super-resolution (SISR). The proposed approach learns end-to-end mapping between low-resolution (LR) images and high-resolution (HR) images. The mapping is represented as a deep convolutional neural network which inputs the LR image and outputs the HR image. Our network uses 5 convolution layers, which kernels size include 5×5, 3×3 and 1×1. In our proposed network, we use residual-learning and combine different sizes of convolution kernels at the same layer. The experiment results show that our proposed method performs better than the existing methods in reconstructing quality index and human visual effects on benchmarked images.

Paper Details

Date Published: 9 April 2018
PDF: 5 pages
Proc. SPIE 10609, MIPPR 2017: Pattern Recognition and Computer Vision, 106090M (9 April 2018); doi: 10.1117/12.2284377
Show Author Affiliations
Lamei Zou, Huazhong Univ. of Science and Technology (China)
Ming Luo, Huazhong Univ. of Science and Technology (China)
Weidong Yang, Huazhong Univ. of Science and Technology (China)
Peng Li, Huazhong Univ. of Science and Technology (China)
Liujia Jin, Huazhong Univ. of Science and Technology (China)


Published in SPIE Proceedings Vol. 10609:
MIPPR 2017: Pattern Recognition and Computer Vision
Zhiguo Cao; Yuehuang Wang; Chao Cai, Editor(s)

© SPIE. Terms of Use
Back to Top