Deep self-supervised spatial-variant image deblurring.

Journal: Neural networks : the official journal of the International Neural Network Society
Published Date:

Abstract

Most existing model-based and learning-based image deblurring methods usually use synthetic blur-sharp training pairs to remove blur. However, these approaches do not perform well in real-world applications as the blur-sharp training pairs are difficult to be obtained and the blur in real-world scenarios is spatial-variant. In this paper, we propose a self-supervised learning-based image deblurring method that can deal with both uniform and spatial-variant blur distributions. Moreover, our method does not need for blur-sharp pairs for training. In our proposed method, we design the Deblurring Network (D-Net) and the Spatial Degradation Network (SD-Net). Specifically, the D-Net is designed for image deblurring while the SD-Net is used to simulate the spatial-variant degradation. Furthermore, the off-the-shelf pre-trained model is employed as the prior of our model, which facilitates image deblurring. Meanwhile, we design a recursive optimization strategy to accelerate the convergence of the model. Extensive experiments demonstrate that our proposed model achieves favorable performance against existing image deblurring methods.

Authors

  • Yaowei Li
    Water Conservancy College, North China University of Water Resources and Electric Power, Zhengzhou 450046, China.
  • Bo Jiang
    Jiangsu Co-Innovation Center of Efficient Processing and Utilization of Forest Resources, Nanjing Forestry University, Nanjing 210037, China. 111501206@njfu.edu.cn.
  • Zhenghao Shi
    Shaanxi Key Laboratory for Network Computing and Security Technology, School of Computer Science and Engineering, Xi'an University of Technology, Xi'an, China.
  • Xiaoxuan Chen
    State Key Laboratory of Oral Diseases, National Clinical Research Center for Oral Diseases, West China Hospital of Stomatology, Sichuan University, Chengdu, 610041, China.
  • Jinshan Pan