Non-uniform image blind deblurring by two-stage fully convolution network

作     者：Wu, Chudan Wo, Yan Han, Guoqing Wu, Zhangyong Liang, Jiyun 

作者机构：South China Univ Technol Dept Comp Sci Guangzhou Peoples R China 

出 版 物：《IET IMAGE PROCESSING》 (IET影像处理)

年 卷 期：2020年第14卷第11期

页      面：2588-2596页

核心收录：

学科分类：0808[工学-电气工程] 1002[医学-临床医学] 08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：National Natural Science Foundation of Guangdong [2018A030313994, 2016A030313472] Guangzhou science and technology plan project 

主　　题：neural nets parameter estimation image restoration nonuniform image blind deblurring two-stage fully convolution network deep neural networks fully convolutional network blur restored image feed-forward pass parameter estimation subnet P-net pixel-wise parameters multiple blur types blur removal subnet G-net high quality latent sharp image PG-net parameter estimation method deblurring method 

摘      要：Deep neural networks have recently demonstrated high performance for deblurring. However, few methods are designed for both non-uniform image blur estimation and removal with highly efficient. In this study, the authors proposed a fully convolutional network that outputs estimated blur and restored image in one feed-forward pass for the non-uniformly blurred image of any input-size. The proposed network contains two subnets. The parameter estimation subnet P-net predicts pixel-wise parameters of multiple blur types with high accuracy. The output of P-net is used as a condition, which guides the blur removal subnet G-net to restore a high quality latent sharp image. P-net and G-net are ultimately integrated into a single framework called PG-net, which guarantees the consistency of parameter estimation and blur removal, thereby improves algorithm efficiency. Experiment results show that the authors blur parameter estimation method as well as their deblurring method outperforms the comparison methods both quantitatively and qualitatively.