9 April 2018 Single image super-resolution based on convolutional neural networks
Author Affiliations +
Proceedings Volume 10609, MIPPR 2017: Pattern Recognition and Computer Vision; 106090M (2018) https://doi.org/10.1117/12.2284377
Event: Tenth International Symposium on Multispectral Image Processing and Pattern Recognition (MIPPR2017), 2017, Xiangyang, China
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.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Lamei Zou, Lamei Zou, Ming Luo, Ming Luo, Weidong Yang, Weidong Yang, Peng Li, Peng Li, Liujia Jin, Liujia Jin, } "Single image super-resolution based on convolutional neural networks", Proc. SPIE 10609, MIPPR 2017: Pattern Recognition and Computer Vision, 106090M (9 April 2018); doi: 10.1117/12.2284377; https://doi.org/10.1117/12.2284377
PROCEEDINGS
5 PAGES


SHARE
Back to Top