Image Super Resolution Based on Fusing Multiple Convolution Neural Networks
Citations Over TimeTop 10% of 2017 papers
Abstract
In this paper, we focus on constructing an accurate super resolution system based on multiple Convolution Neural Networks (CNNs). Each individual CNN is trained separately with different network structure. A Context-wise Network Fusion (CNF) approach is proposed to integrate the outputs of individual networks by additional convolution layers. With fine-tuning the whole fused network, the accuracy is significantly improved compared to the individual networks. We also discuss other network fusion schemes, including Pixel-Wise network Fusion (PWF) and Progressive Network Fusion (PNF). The experimental results show that the CNF outperforms PWF and PNF. Using SRCNN as individual network, the CNF network achieves the state-of-the-art accuracy on benchmark image datasets.
Related Papers
- → Comparative analysis of different fusion rules for SAR and multi-spectral image fusion based on NSCT and IHS transform(2015)9 cited
- → Improvements of image fusion methods(2014)5 cited
- → Better and Faster Deep Image Fusion with Spatial Frequency(2021)1 cited
- Image fusion algorithm based on high frequency channel(2003)
- → Cognition-based Fusion Method for Infrared and Visible image(2018)