ML Anthology

Scale-Recurrent Network for Deep Image Deblurring

Xin Tao, Hongyun Gao, Xiaoyong Shen, Jue Wang, Jiaya Jia
CVPR 2018
doi:10.1109/CVPR.2018.00853 /cvpr/2018/tao2018cvpr-scalerecurrent/

Abstract

In single image deblurring, the ``coarse-to-fine'' scheme, i.e. gradually restoring the sharp image on different resolutions in a pyramid, is very successful in both traditional optimization-based methods and recent neural-network-based approaches. In this paper, we investigate this strategy and propose a Scale-recurrent Network (SRN-DeblurNet) for this deblurring task. Compared with the many recent learning-based approaches, it has a simpler network structure, a smaller number of parameters and is easier to train. We evaluate our method on large-scale deblurring datasets with complex motion. Results show that our method can produce better quality results than state-of-the-arts, both quantitatively and qualitatively.

PDF CVPR Semantic Scholar

Cite

Text

Tao et al. "Scale-Recurrent Network for Deep Image Deblurring." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018. doi:10.1109/CVPR.2018.00853

Markdown

[Tao et al. "Scale-Recurrent Network for Deep Image Deblurring." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018.](https://mlanthology.org/cvpr/2018/tao2018cvpr-scalerecurrent/) doi:10.1109/CVPR.2018.00853

BibTeX

@inproceedings{tao2018cvpr-scalerecurrent,
  title     = {{Scale-Recurrent Network for Deep Image Deblurring}},
  author    = {Tao, Xin and Gao, Hongyun and Shen, Xiaoyong and Wang, Jue and Jia, Jiaya},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2018},
  doi       = {10.1109/CVPR.2018.00853},
  url       = {https://mlanthology.org/cvpr/2018/tao2018cvpr-scalerecurrent/}
}