Research Article
Multi-scale Two-Way Deblurring Network for Non-uniform Single Image Deblurring
@INPROCEEDINGS{10.1007/978-3-030-89814-4_43, author={Zhongzhe Cheng and Bing Luo and Li Xu and Siwei Li and Kunshu Xiao and Zheng Pei}, title={Multi-scale Two-Way Deblurring Network for Non-uniform Single Image Deblurring}, proceedings={Mobile Multimedia Communications. 14th EAI International Conference, Mobimedia 2021, Virtual Event, July 23-25, 2021, Proceedings}, proceedings_a={MOBIMEDIA}, year={2021}, month={11}, keywords={Multi-scale network Two-way learning Non-uniform deblurred}, doi={10.1007/978-3-030-89814-4_43} }- Zhongzhe Cheng
Bing Luo
Li Xu
Siwei Li
Kunshu Xiao
Zheng Pei
Year: 2021
Multi-scale Two-Way Deblurring Network for Non-uniform Single Image Deblurring
MOBIMEDIA
Springer
DOI: 10.1007/978-3-030-89814-4_43
Abstract
We propose a new and effective image deblurring network based on deep learning. The motivation of this work is based on traditional algorithms and deep learning which take an easy-to-difficult approach to image deblurring. In traditional algorithms, a rough blur kernel is obtained first, and then a precise blur kernel is gradually refined. In deep learning, the pyramid structure is adopted to restore clear images from easy to difficult. We hope to recover the clear image by two-way approximation. One network recovers the roughly clear image from the blurred image, and the other network recovers part of the structural information from the blank image, and finally the two networks are added together to obtain the clear image. Experiments show that since we decomposed the original deblurring task into two different tasks, the network performance has been effectively improved. Compared with other latest networks, our network can get clearer images.
