Decoupling Induction and Multi-Order Attention Drop-Out Gating Based Joint Motion Deblurring and Image Super-Resolution

Authors:
Open Access
Publisher website
Google Scholar
Abstract
Resolution decrease and motion blur are two typical image degradation processes that are usually addressed by deep networks, specifically convolutional neural networks (CNNs). However, since real images are usually obtained through multiple degradations, the vast majority of current CNN methods that employ a single degradation process inevitably need to be improved to account for multiple degradation effects. In this work, motivated by degradation decoupling and multiple-order attention drop-out gating, we propose a joint deep recovery model to efficiently address motion blur and resolution reduction simultaneously. Our degradation decoupling style improves the continence and the efficiency of model construction and training. Moreover, the proposed multi-order attention mechanism comprehensively and hierarchically extracts multiple attention features and fuses them properly by drop-out gating. The proposed approach is evaluated using diverse benchmark datasets including natural and synthetic images. The experimental results show that our proposed method can efficiently complete joint motion blur and image super-resolution (SR).
Funding Information
  • National Natural Science Foundation of China (61971004, 2008085MF190, KJ2019A0083, KJ2021A1289, 2020A002)
  • Natural Science Foundation of Anhui Province (61971004, 2008085MF190, KJ2019A0083, KJ2021A1289, 2020A002)
  • Key Project of Natural Science of Anhui Provincial Department of Education (61971004, 2008085MF190, KJ2019A0083, KJ2021A1289, 2020A002)
  • Open Project Fund of the Key Laboratory of Computational Intelligence (61971004, 2008085MF190, KJ2019A0083, KJ2021A1289, 2020A002)
  • Signal Processing of the Ministry of Education (Anhui University) (61971004, 2008085MF190, KJ2019A0083, KJ2021A1289, 2020A002)

This publication has 32 references indexed in Scilit: