Learning Fully Convolutional Networks for Iterative Non-Blind Deconvolution

Jiawei Zhang, Jinshan Pan, Wei-Sheng Lai, Rynson W. H. Lau, Ming-Hsuan Yang

CVPR 2017

doi:10.1109/CVPR.2017.737 /cvpr/2017/zhang2017cvpr-learning-a/

Abstract

In this paper, we propose a fully convolutional network for iterative non-blind deconvolution. We decompose the non-blind deconvolution problem into image denoising and image deconvolution. We train a FCNN to remove noise in the gradient domain and use the learned gradients to guide the image deconvolution step. In contrast to the existing deep neural network based methods, we iteratively deconvolve the blurred images in a multi-stage framework. The proposed method is able to learn an adaptive image prior, which keeps both local (details) and global (structures) information. Both quantitative and qualitative evaluations on the benchmark datasets demonstrate that the proposed method performs favorably against state-of-the-art algorithms in terms of quality and speed.

PDF CVPR Semantic Scholar

Cite

Text

Zhang et al. "Learning Fully Convolutional Networks for Iterative Non-Blind Deconvolution." Conference on Computer Vision and Pattern Recognition, 2017. doi:10.1109/CVPR.2017.737

Markdown

[Zhang et al. "Learning Fully Convolutional Networks for Iterative Non-Blind Deconvolution." Conference on Computer Vision and Pattern Recognition, 2017.](https://mlanthology.org/cvpr/2017/zhang2017cvpr-learning-a/) doi:10.1109/CVPR.2017.737

BibTeX

@inproceedings{zhang2017cvpr-learning-a,
  title     = {{Learning Fully Convolutional Networks for Iterative Non-Blind Deconvolution}},
  author    = {Zhang, Jiawei and Pan, Jinshan and Lai, Wei-Sheng and Lau, Rynson W. H. and Yang, Ming-Hsuan},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2017},
  doi       = {10.1109/CVPR.2017.737},
  url       = {https://mlanthology.org/cvpr/2017/zhang2017cvpr-learning-a/}
}